@inproceedings{yu_3DV_2026,title={SocialGen: Modeling Multi-Human Social Interaction with Language Models},author={Yu, Heng and Zhang, Juze and Chen, Changan and Xiang, Tiange and Fang, Yusu and Niebles, Juan Carlos and Adeli, Ehsan},booktitle={International Conference on 3D Vision (3DV)},year={2026},month=mar,address={Vancouver, Canada},}
2025
Oral grafting_2025.png
Exploring Diffusion Transformer Designs via Grafting
Keshigeyan Chandrasegaran, Michael Poli, Daniel Y Fu, Dongjun Kim, Lea M Hadzic, Manling Li, Agrim Gupta, Stefano Massaroli, Azalia Mirhoseini, Juan Carlos Niebles, and 2 more authors
In Advances in Neural Information Processing Systems (NeurIPS). San Diego, California. Dec 2025
@inproceedings{chandrasegaran_NeurIPS_2025,title={Exploring Diffusion Transformer Designs via Grafting},author={Chandrasegaran, Keshigeyan and Poli, Michael and Fu, Daniel Y and Kim, Dongjun and Hadzic, Lea M and Li, Manling and Gupta, Agrim and Massaroli, Stefano and Mirhoseini, Azalia and Niebles, Juan Carlos and Ermon, Stefano and Fei-Fei, Li},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},address={San Diego, California},year={2025},month=dec,}
taming2025.gif
Taming generative video models for zero-shot optical flow extraction
Seungwoo Kim, Khai Loong Aw, Klemen Kotar, Cristobal Eyzaguirre, Wanhee Lee, Yunong Liu, Jared Watrous, Stefan Stojanov, Juan Carlos Niebles, Jiajun Wu, and 1 more author
In Advances in Neural Information Processing Systems (NeurIPS). San Diego, California. Dec 2025
@inproceedings{kim_NeurIPS_2025,title={Taming generative video models for zero-shot optical flow extraction},author={Kim, Seungwoo and Aw, Khai Loong and Kotar, Klemen and Eyzaguirre, Cristobal and Lee, Wanhee and Liu, Yunong and Watrous, Jared and Stojanov, Stefan and Niebles, Juan Carlos and Wu, Jiajun and Yamins, Daniel L. K.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},address={San Diego, California},year={2025},month=dec,}
apigenmt2025.png
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
Akshara Prabhakar, Zuxin Liu, Ming Zhu, Jianguo Zhang, Tulika Awalgaonkar, Shiyu Wang, Zhiwei Liu, Haolin Chen, Thai Hoang, Juan Carlos Niebles, and 5 more authors
In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track. San Diego, California. Dec 2025
@inproceedings{prabhakar_NeurIPS_2025,title={{APIGen-MT}: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay},author={Prabhakar, Akshara and Liu, Zuxin and Zhu, Ming and Zhang, Jianguo and Awalgaonkar, Tulika and Wang, Shiyu and Liu, Zhiwei and Chen, Haolin and Hoang, Thai and Niebles, Juan Carlos and Heinecke, Shelby and Yao, Weiran and Wang, Huan and Savarese, Silvio and Xiong, Caiming},booktitle={Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},address={San Diego, California},year={2025},month=dec,}
contra4_emnlp25.png
Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D
Artemis Panagopoulou, Le Xue, Honglu Zhou, Ran Xu, Caiming Xiong, Chris Callison-Burch, Mark Yatskar, and Juan Carlos Niebles
In Conference on Empirical Methods in Natural Language Processing (EMNLP). Suzhou, China. Nov 2025
@inproceedings{panagopoulou_EMNLP_2025,title={Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D},author={Panagopoulou, Artemis and Xue, Le and Zhou, Honglu and Xu, Ran and Xiong, Caiming and Callison-Burch, Chris and Yatskar, Mark and Niebles, Juan Carlos},booktitle={Conference on Empirical Methods in Natural Language Processing (EMNLP)},month=nov,year={2025},address={Suzhou, China},}
actionstudio_emnlp25.png
ActionStudio: A Lightweight Framework for Data and Training of Action Models
Jianguo Zhang, Thai Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, and 6 more authors
In Conference on Empirical Methods in Natural Language Processing (EMNLP). Suzhou, China. Nov 2025
@inproceedings{zhang_EMNLP_2025,title={{ActionStudio}: A Lightweight Framework for Data and Training of Action Models},author={Zhang, Jianguo and Hoang, Thai and Zhu, Ming and Liu, Zuxin and Wang, Shiyu and Awalgaonkar, Tulika and Prabhakar, Akshara and Chen, Haolin and Yao, Weiran and Liu, Zhiwei and Tan, Juntao and Niebles, Juan Carlos and Heinecke, Shelby and Wang, Huan and Savarese, Silvio and Xiong, Caiming},booktitle={Conference on Empirical Methods in Natural Language Processing (EMNLP)},month=nov,year={2025},address={Suzhou, China},}
Oral latte_emnlp2025.png
LATTE: Learning to Think with Vision Specialists
Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, and 2 more authors
In Conference on Empirical Methods in Natural Language Processing (EMNLP). Suzhou, China. Nov 2025
@inproceedings{ma_EMNLP_2025,title={{LATTE}: Learning to Think with Vision Specialists},author={Ma, Zixian and Zhang, Jianguo and Liu, Zhiwei and Zhang, Jieyu and Tan, Juntao and Shu, Manli and Niebles, Juan Carlos and Heinecke, Shelby and Wang, Huan and Xiong, Caiming and Krishna, Ranjay and Savarese, Silvio},booktitle={Conference on Empirical Methods in Natural Language Processing (EMNLP)},month=nov,year={2025},address={Suzhou, China},}
strefer_ICCVW2025.png
Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
Honglu Zhou, Xiangyu Peng, Shrikant Kendre, Michael S Ryoo, Silvio Savarese, Caiming Xiong, and Juan Carlos Niebles
In ICCV Workshop on What is Next in Multimodal Foundation Models?. Honolulu, Hawaii. Oct 2025
@inproceedings{Zhou_ICCVW_2025,author={Zhou, Honglu and Peng, Xiangyu and Kendre, Shrikant and Ryoo, Michael S and Savarese, Silvio and Xiong, Caiming and Niebles, Juan Carlos},title={Strefer: Empowering Video {LLMs} with Space-Time Referring and Reasoning via Synthetic Instruction Data},booktitle={ICCV Workshop on What is Next in Multimodal Foundation Models?},address={Honolulu, Hawaii},month=oct,year={2025},}
blip3_iccvw25.png
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Le Xue, Manli Shu, Anas Awadalla, Jun Wang, An Yan, Senthil Purushwalkam, Honglu Zhou, Viraj Prabhu, Yutong Dai, Michael S Ryoo, and 23 more authors
In ICCV Findings Workshop. Honolulu, Hawaii. Oct 2025
@inproceedings{Xue_ICCVW_2025,title={{xGen-MM (BLIP-3)}: A Family of Open Large Multimodal Models},author={Xue, Le and Shu, Manli and Awadalla, Anas and Wang, Jun and Yan, An and Purushwalkam, Senthil and Zhou, Honglu and Prabhu, Viraj and Dai, Yutong and Ryoo, Michael S and Kendre, Shrikant and Zhang, Jieyu and Lujan-Moreno, Gustavo Adolfo and Olson, Matthew Lyle and Hinck, Musashi and Cobbley, David and Tseng, Shao-Yen and Lal, Vasudev and Qin, Can and Zhang, Shu and Chen, Chia-Chih and Yu, Ning and Tan, Juntao and Awalgaonkar, Tulika Manoj and Heinecke, Shelby and Wang, Huan and Choi, Yejin and Schmidt, Ludwig and Savarese, Silvio and Chen, Zeyuan and Niebles, Juan Carlos and Xiong, Caiming and Xu, Ran},booktitle={ICCV Findings Workshop},address={Honolulu, Hawaii},month=oct,year={2025},}
uniegomotion.png
UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation
Chaitanya Patel, Hiroki Nakamura, Yuta Kyuragi, Kazuki Kozuka, Juan Carlos Niebles, and Ehsan Adeli
In IEEE/CVF International Conference on Computer Vision (ICCV). Honolulu, Hawaii. Oct 2025
@inproceedings{Patel_ICCV_2025,author={Patel, Chaitanya and Nakamura, Hiroki and Kyuragi, Yuta and Kozuka, Kazuki and Niebles, Juan Carlos and Adeli, Ehsan},title={{UniEgoMotion}: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Honolulu, Hawaii},month=oct,year={2025},}
lamsim-acl2025.png
LAM Simulator: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback
Thai Quoc Hoang , Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, and 5 more authors
@inproceedings{Hoang_ACLF_2025,title={{LAM Simulator}: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback},author={Hoang, Thai Quoc and Huang, Kung-Hsiang and Kokane, Shirley and Zhang, Jianguo and Liu, Zuxin and Zhu, Ming and Grigsby, Jake and Lan, Tian and Ryoo, Michael S and Wu, Chien-Sheng and Heinecke, Shelby and Wang, Huan and Savarese, Silvio and Xiong, Caiming and Niebles, Juan Carlos},booktitle={ACL Findings},address={Vienna, Austria},year={2025},month=jul,}
complex2025.png
Understanding Complexity in VideoQA via Visual Program Generation
Cristobal Eyzaguirre, Igor Vasiljevic, Achal Dave, Jiajun Wu, Rares Andrei Ambrus, Thomas Kollar, Juan Carlos Niebles, and Pavel Tokmakov
In International Conference on Machine Learning (ICML). Vancouver, Canada. Jul 2025
@inproceedings{Eyzaguirre_ICML_2025,title={Understanding Complexity in {VideoQA} via Visual Program Generation},author={Eyzaguirre, Cristobal and Vasiljevic, Igor and Dave, Achal and Wu, Jiajun and Ambrus, Rares Andrei and Kollar, Thomas and Niebles, Juan Carlos and Tokmakov, Pavel},booktitle={International Conference on Machine Learning (ICML)},address={Vancouver, Canada},year={2025},month=jul,}
mervICML25.png
Unifying Specialized Visual Encoders for Video Language Models
Jihoon Chung, Tyler Zhu, Max Gonzalez Saez-Diez, Juan Carlos Niebles, Honglu Zhou, and Olga Russakovsky
In International Conference on Machine Learning (ICML). Vancouver, Canada. Jul 2025
@inproceedings{Chung_ICML_2025,title={Unifying Specialized Visual Encoders for Video Language Models},author={Chung, Jihoon and Zhu, Tyler and Saez-Diez, Max Gonzalez and Niebles, Juan Carlos and Zhou, Honglu and Russakovsky, Olga},booktitle={International Conference on Machine Learning (ICML)},address={Vancouver, Canada},year={2025},month=jul,}
adaptvis2025.png
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
Shiqi Chen, Tongyao Zhu , Ruochen Zhou, Jinghan Zhang, Siyang Gao, Juan Carlos Niebles, Mor Geva, Junxian He, Jiajun Wu, and Manling Li
In International Conference on Machine Learning (ICML). Vancouver, Canada. Jul 2025
@inproceedings{Chen_ICML_2025,title={Why Is Spatial Reasoning Hard for {VLMs}? An Attention Mechanism Perspective on Focus Areas},author={Chen, Shiqi and Zhu, Tongyao and Zhou, Ruochen and Zhang, Jinghan and Gao, Siyang and Niebles, Juan Carlos and Geva, Mor and He, Junxian and Wu, Jiajun and Li, Manling},booktitle={International Conference on Machine Learning (ICML)},address={Vancouver, Canada},year={2025},month=jul,}
viunit_cvpr25.jpg
ViUniT: Visual Unit Tests for More Robust Visual Programming
Artemis Panagopoulou, Honglu Zhou, Silvio Savarese, Caiming Xiong, Chris Callison-Burch, Mark Yatskar, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, Tennessee. Jun 2025
@inproceedings{Artemis_CVPR_2025,title={{ViUniT}: Visual Unit Tests for More Robust Visual Programming},author={Panagopoulou, Artemis and Zhou, Honglu and Savarese, Silvio and Xiong, Caiming and Callison-Burch, Chris and Yatskar, Mark and Niebles, Juan Carlos},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Nashville, Tennessee},year={2025},month=jun,doi={10.1109/CVPR52734.2025.02295}}
tstarCVPR2025.png
Re-thinking Temporal Search for Long-Form Video Understanding
@inproceedings{Ye_CVPR_2025,author={Ye, Jinhui and Wang, Zihan and Sun, Haosen and Chandrasegaran, Keshigeyan and Durante, Zane and Eyzaguirre, Cristobal and Bisk, Yonatan and Niebles, Juan Carlos and Adeli, Ehsan and Fei-Fei, Li and Wu, Jiajun and Li, Manling},title={Re-thinking Temporal Search for Long-Form Video Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Nashville, Tennessee},year={2025},month=jun,doi={10.1109/CVPR52734.2025.00802}}
@inproceedings{Patel_CVPRW_2025,author={Patel, Chaitanya and Niebles, Juan Carlos and Adeli, Ehsan},title={{AdaVid}: Adaptive Video-Language Pretraining},booktitle={CVPR 2025 Workshop on Efficient and On-Device Generation (EDGE)},address={Nashville, Tennessee},year={2025},month=jun,}
Oral xlam.jpg
xLAM: A Family of Large Action Models to Empower AI Agent Systems
Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, and 12 more authors
In The 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025). Albuquerque, New Mexico. Apr 2025
@inproceedings{Zhang_NAACL_2025,author={Zhang, Jianguo and Lan, Tian and Zhu, Ming and Liu, Zuxin and Hoang, Thai and Kokane, Shirley and Yao, Weiran and Tan, Juntao and Prabhakar, Akshara and Chen, Haolin and Liu, Zhiwei and Feng, Yihao and Awalgaonkar, Tulika and Murthy, Rithesh and Hu, Eric and Chen, Zeyuan and Xu, Ran and Niebles, Juan Carlos and Heinecke, Shelby and Wang, Huan and Savarese, Silvio and Xiong, Caiming},title={{xLAM}: A Family of Large Action Models to Empower {AI} Agent Systems},booktitle={The 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)},address={Albuquerque, New Mexico},month=apr,year={2025},doi={10.18653/v1/2025.naacl-long.578}}
vlmq2025.png
VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making
Jake Grigsby, Yuke Zhu, Michael S Ryoo, and Juan Carlos Niebles
In ICLR 2025 Workshop on Scaling Self-Improving Foundation Models without Human Supervision. Singapore. Apr 2025
@inproceedings{Grigsby_ICLRW_2025,title={{VLM} {Q}-Learning: Aligning Vision-Language Models for Interactive Decision-Making},author={Grigsby, Jake and Zhu, Yuke and Ryoo, Michael S and Niebles, Juan Carlos},booktitle={ICLR 2025 Workshop on Scaling Self-Improving Foundation Models without Human Supervision},address={Singapore},month=apr,year={2025},}
toolscan_ICLRW25.png
ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs
Shirley Kokane, Ming Zhu, Tulika Manoj Awalgaonkar, Jianguo Zhang, Akshara Prabhakar, Thai Quoc Hoang, Zuxin Liu, Rithesh R N, Liangwei Yang, Weiran Yao, and 7 more authors
In ICLR 2025 Workshop on Building Trust in Language Models and Applications. Singapore. Apr 2025
@inproceedings{Kokane_ICLRW_2025,title={{ToolScan}: A Benchmark for Characterizing Errors in Tool-Use LLMs},author={Kokane, Shirley and Zhu, Ming and Awalgaonkar, Tulika Manoj and Zhang, Jianguo and Prabhakar, Akshara and Hoang, Thai Quoc and Liu, Zuxin and N, Rithesh R and Yang, Liangwei and Yao, Weiran and Tan, Juntao and Liu, Zhiwei and Wang, Huan and Niebles, Juan Carlos and Heinecke, Shelby and Xiong, Caiming and Savarese, Silvio},booktitle={ICLR 2025 Workshop on Building Trust in Language Models and Applications},address={Singapore},year={2025},month=apr,}
Protecting Images From Manipulations With Deep Optical Signatures
Kevin Arias, Pablo Gomez, Carlos Hinojosa, Juan Carlos Niebles, and Henry Arguello
IEEE Journal of Selected Topics in Signal Processing. Apr 2025
@article{AriasJSTSP2025,author={Arias, Kevin and Gomez, Pablo and Hinojosa, Carlos and Niebles, Juan Carlos and Arguello, Henry},journal={IEEE Journal of Selected Topics in Signal Processing},title={Protecting Images From Manipulations With Deep Optical Signatures},year={2025},month=apr,doi={10.1109/JSTSP.2025.3554136},}
@inproceedings{Eyzaguirre_NeurIPS_2024,author={Eyzaguirre, Cristobal and Tang, Eric and Buch, Shyamal and Gaidon, Adrien and Wu, Jiajun and Niebles, Juan Carlos},title={Streaming Detection of Queried Event Start},booktitle={Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},address={Vancouver, Canada},month=dec,year={2024},}
neurips24-apigen.jpg
APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
Zuxin Liu, Thai Quoc Hoang, Jianguo Zhang, Ming Zhu, Tian Lan, Shirley Kokane, Juntao Tan, Weiran Yao, Zhiwei Liu, Yihao Feng, and 7 more authors
In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track. Vancouver, Canada. Dec 2024
@inproceedings{Zuxin_NeurIPS_2024,author={Liu, Zuxin and Hoang, Thai Quoc and Zhang, Jianguo and Zhu, Ming and Lan, Tian and Kokane, Shirley and Tan, Juntao and Yao, Weiran and Liu, Zhiwei and Feng, Yihao and Murthy, Rithesh and Yang, Liangwei and Savarese, Silvio and Niebles, Juan Carlos and Wang, Huan and Heinecke, Shelby and Xiong, Caiming},title={{APIGen}: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets},booktitle={Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},address={Vancouver, Canada},month=dec,year={2024},}
neurips24ikea.jpg
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
Yunong Liu, Weiyu Liu, Shubh Khanna, Cristobal Eyzaguirre, Manling Li, Juan Carlos Niebles, Vineeth Ravi, Saumitra Mishra, and Jiajun Wu
In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track. Vancouver, Canada. Dec 2024
@inproceedings{Yunong_NeurIPS_2024,author={Liu, Yunong and Liu, Weiyu and Khanna, Shubh and Eyzaguirre, Cristobal and Li, Manling and Niebles, Juan Carlos and Ravi, Vineeth and Mishra, Saumitra and Wu, Jiajun},title={{IKEA} Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos},booktitle={Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},address={Vancouver, Canada},month=dec,year={2024},}
practCONLL24.jpg
PRACT: Optimizing Principled Reasoning and Acting of LLM Agent
Zhiwei Liu, Weiran Yao, Jianguo Zhang, Zuxin Liu, Liangwei Yang, Rithesh R N, Tian Lan, Ming Zhu, Juntao Tan, Shirley Kokane, and 6 more authors
In Proceedings of the 28th Conference on Computational Natural Language Learning (CoNLL). Miami, FL. Nov 2024
@inproceedings{Liu_CONLL_2024,title={{PRACT}: Optimizing Principled Reasoning and Acting of {LLM} Agent},author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Liu, Zuxin and Yang, Liangwei and R N, Rithesh and Lan, Tian and Zhu, Ming and Tan, Juntao and Kokane, Shirley and Hoang, Thai Quoc and Niebles, Juan Carlos and Heinecke, Shelby and Wang, Huan and Savarese, Silvio and Xiong, Caiming},booktitle={Proceedings of the 28th Conference on Computational Natural Language Learning (CoNLL)},month=nov,year={2024},address={Miami, FL},doi={10.18653/v1/2024.conll-1.33},}
xinstruct.jpg
X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning
Artemis Panagopoulou, Le Xue, Ning Yu, Junnan Li, Dongxu Li, Shafiq Joty, Ran Xu, Silvio Savarese, Caiming Xiong, and Juan Carlos Niebles
In European Conference on Computer Vision (ECCV). Milan, Italy. Oct 2024
@inproceedings{ArtemisECCV2024,author={Panagopoulou, Artemis and Xue, Le and Yu, Ning and Li, Junnan and Li, Dongxu and Joty, Shafiq and Xu, Ran and Savarese, Silvio and Xiong, Caiming and Niebles, Juan Carlos},title={{X-InstructBLIP}: A Framework for Aligning Image, 3D, Audio, Video to {LLM}s and its Emergent Cross-modal Reasoning},booktitle={European Conference on Computer Vision (ECCV)},address={Milan, Italy},month=oct,year={2024},doi={10.1007/978-3-031-72995-9_11},}
layoutDETR2024.jpg
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Ning Yu, Chia-Chih Chen, Zeyuan Chen, Rui Meng, Gang Wu, Paul Josel, Juan Carlos Niebles, Caiming Xiong, and Ran Xu
In European Conference on Computer Vision (ECCV). Milan, Italy. Oct 2024
@inproceedings{YuECCV2024,author={Yu, Ning and Chen, Chia-Chih and Chen, Zeyuan and Meng, Rui and Wu, Gang and Josel, Paul and Niebles, Juan Carlos and Xiong, Caiming and Xu, Ran},title={{LayoutDETR}: Detection Transformer Is a Good Multimodal Layout Designer},booktitle={European Conference on Computer Vision (ECCV)},address={Milan, Italy},month=oct,year={2024},doi={10.1007/978-3-031-72661-3_10},}
xgen-vidsyn.gif
xGen-VideoSyn: High-fidelity Text-to-Video Synthesis with Compressed Representations
Can Qin, Congying Xia, Krithika Ramakrishnan, Michael Ryoo, Lifu Tu, Yihao Feng, Manli Shu, Honglu Zhou, Anas Awadalla, Jun Wang, and 9 more authors
In AI for Visual Arts Workshop and Challenges (AI4VA), in conjunction with ECCV. Milan, Italy. Sep 2024
@inproceedings{CanAI4VA2024,title={{xGen-VideoSyn}: High-fidelity Text-to-Video Synthesis with Compressed Representations},author={Qin, Can and Xia, Congying and Ramakrishnan, Krithika and Ryoo, Michael and Tu, Lifu and Feng, Yihao and Shu, Manli and Zhou, Honglu and Awadalla, Anas and Wang, Jun and Purushwalkam, Senthil and Xue, Le and Zhou, Yingbo and Wang, Huan and Savarese, Silvio and Niebles, Juan Carlos and Chen, Zeyuan and Xiong, Caiming and Xu, Ran},booktitle={AI for Visual Arts Workshop and Challenges (AI4VA), in conjunction with ECCV},address={Milan, Italy},month=sep,year={2024},}
ulip2cvpr24.jpg
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Le Xue, Ning Yu, Shu Zhang, Artemis Panagopoulou, Junnan Li, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, and 1 more author
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, Washington. Jun 2024
@inproceedings{Xue_CVPR_2024,author={Xue, Le and Yu, Ning and Zhang, Shu and Panagopoulou, Artemis and Li, Junnan and Martín-Martín, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio},title={{ULIP-2}: Towards Scalable Multimodal Pre-training for {3D} Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Seattle, Washington},month=jun,year={2024},doi={10.1109/CVPR52733.2024.02558},}
shu-icra24.jpg
Hierarchical Point Attention for Indoor 3D Object Detection
Manli Shu, Le Xue, Ning Yu, Roberto Martín-Martín, Caiming Xiong, Tom Goldstein, Juan Carlos Niebles, and Ran Xu
In IEEE International Conference on Robotics and Automation (ICRA). Yokohama, Japan. May 2024
@inproceedings{Shu_ICRA_2024,author={Shu, Manli and Xue, Le and Yu, Ning and Martín-Martín, Roberto and Xiong, Caiming and Goldstein, Tom and Niebles, Juan Carlos and Xu, Ran},title={Hierarchical Point Attention for Indoor 3D Object Detection},booktitle={IEEE International Conference on Robotics and Automation (ICRA)},address={Yokohama, Japan},month=may,year={2024},doi={10.1109/ICRA57147.2024.10610108},}
Spotlight yao-iclr24.png
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh R. N., Zeyuan Chen, Jianguo Zhang, Devansh Arpit, and 5 more authors
In The Twelfth International Conference on Learning Representations (ICLR). Vienna, Austria. May 2024
@inproceedings{Yao_ICLR_2024,author={Yao, Weiran and Heinecke, Shelby and Niebles, Juan Carlos and Liu, Zhiwei and Feng, Yihao and Xue, Le and N., Rithesh R. and Chen, Zeyuan and Zhang, Jianguo and Arpit, Devansh and Xu, Ran and Mui, Phil L. and Wang, Huan and Xiong, Caiming and Savarese, Silvio},title={Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization},booktitle={The Twelfth International Conference on Learning Representations (ICLR)},address={Vienna, Austria},month=may,year={2024},}
rex-iclr24.jpg
REX: Rapid Exploration and eXploitation for AI agents
Rithesh Murthy, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Le Xue, Weiran Yao, Yihao Feng, Zeyuan Chen, Akash Gokul, Devansh Arpit, and 5 more authors
In ICLR 2024 Workshop on LLM Agents. Vienna, Austria. May 2024
@inproceedings{murthy2023rex,title={{REX}: {R}apid {E}xploration and e{X}ploitation for {AI} agents},author={Murthy, Rithesh and Heinecke, Shelby and Niebles, Juan Carlos and Liu, Zhiwei and Xue, Le and Yao, Weiran and Feng, Yihao and Chen, Zeyuan and Gokul, Akash and Arpit, Devansh and Xu, Ran and Mui, Phil and Wang, Huan and Xiong, Caiming and Savarese, Silvio},booktitle={ICLR 2024 Workshop on LLM Agents},address={Vienna, Austria},month=may,year={2024},}
bolaa-iclr24.jpg
BOLAA: Benchmarking and orchestrating LLM-augmented autonomous agents
Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, and 5 more authors
In ICLR 2024 Workshop on LLM Agents. Vienna, Austria. May 2024
@inproceedings{liu2023bolaa,title={{BOLAA}: Benchmarking and orchestrating {LLM}-augmented autonomous agents},author={Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and Xu, Ran and Mui, Phil and Wang, Huan and Xiong, Caiming and Savarese, Silvio},booktitle={ICLR 2024 Workshop on LLM Agents},address={Vienna, Austria},month=may,year={2024},}
ohana-iclr24.jpg
The AgentOhana: Designing Unified Data and Training Pipeline for Effective Agent Learning
@inproceedings{zhang2024ohana,title={The {AgentOhana}: Designing Unified Data and Training Pipeline for Effective Agent Learning},author={Zhang, Jianguo and Lan, Tian and Murthy, Rithesh and Liu, Zhiwei and Yao, Weiran and Tan, Juntao and Hoang, Thai and Yang, Liangwei and Feng, Yihao and Liu, Zuxin and Awalgaonkar, Tulika and Niebles, Juan Carlos and Savarese, Silvio and Heinecke, Shelby and Wang, Huan and Xiong, Caiming},booktitle={ICLR 2024 Workshop on LLM Agents},address={Vienna, Austria},month=may,year={2024},}
Causal Layering via Conditional Entropy
Itai Feigenbaum, Devansh Arpit, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese, and Huan Wang
In Conference on Causal Learning and Reasoning (CLeaR). Los Angeles, California. Apr 2024
@inproceedings{Itai_CLeaR_2024,author={Feigenbaum, Itai and Arpit, Devansh and Heinecke, Shelby and Niebles, Juan Carlos and Yao, Weiran and Xiong, Caiming and Savarese, Silvio and Wang, Huan},title={Causal Layering via Conditional Entropy},booktitle={Conference on Causal Learning and Reasoning (CLeaR)},address={Los Angeles, California},month=apr,year={2024},}
2023
UniControl2023.jpg
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang , Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, and 3 more authors
In Advances in Neural Information Processing Systems (NeurIPS). New Orleans, USA. Dec 2023
@inproceedings{Qin_NeurIPS_2023,author={Qin, Can and Zhang, Shu and Yu, Ning and Feng, Yihao and Yang, Xinyi and Zhou, Yingbo and Wang, Huan and Niebles, Juan Carlos and Xiong, Caiming and Savarese, Silvio and Ermon, Stefano and Fu, Yun and Xu, Ran},title={UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},address={New Orleans, USA},month=dec,year={2023},}
temp-neurips23.jpg
Temporally Disentangled Representation Learning under Unknown Nonstationarity
Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, and Kun Zhang
In Advances in Neural Information Processing Systems (NeurIPS). New Orleans, USA. Dec 2023
@inproceedings{Song_NeurIPS_2023,author={Song, Xiangchen and Yao, Weiran and Fan, Yewen and Dong, Xinshuai and Chen, Guangyi and Niebles, Juan Carlos and Xing, Eric and Zhang, Kun},title={Temporally Disentangled Representation Learning under Unknown Nonstationarity},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},address={New Orleans, USA},month=dec,year={2023},}
QichenICCV23.jpg
Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation
Qichen Fu, Xingyu Liu, Ran Xu, Juan Carlos Niebles, and Kris M. Kitani
In IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France. Oct 2023
@inproceedings{Fu_ICCV_2023,author={Fu, Qichen and Liu, Xingyu and Xu, Ran and Niebles, Juan Carlos and Kitani, Kris M.},title={Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Paris, France},month=oct,year={2023},doi={10.1109/ICCV51070.2023.02157},}
paprika-cvpr23.png
Procedure-Aware Pretraining for Instructional Video Understanding
Honglu Zhou, Roberto Martín-Martín, Mubbasir Kapadia, Silvio Savarese, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada. Jun 2023
@inproceedings{Zhou_CVPR_2023,author={Zhou, Honglu and Mart\'{i}n-Mart\'{i}n, Roberto and Kapadia, Mubbasir and Savarese, Silvio and Niebles, Juan Carlos},title={Procedure-Aware Pretraining for Instructional Video Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Vancouver, Canada},month=jun,year={2023},doi={10.1109/CVPR52729.2023.01033},}
ulip-cvpr23.png
ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding
Le Xue, Mingfei Gao, Chen Xing, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, and Silvio Savarese
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada. Jun 2023
@inproceedings{Xue_CVPR_2023,author={Xue, Le and Gao, Mingfei and Xing, Chen and Martín-Martín, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio},title={{ULIP}: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Vancouver, Canada},month=jun,year={2023},doi={10.1109/CVPR52729.2023.00120}}
mfovis-cvpr23.png
Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
Vibashan VS, Ning Yu, Chen Xing, Can Qin, Mingfei Gao, Juan Carlos Niebles , Vishal M. Patel, and Ran Xu
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada. Jun 2023
@inproceedings{VS_CVPR_2023,author={VS, Vibashan and Yu, Ning and Xing, Chen and Qin, Can and Gao, Mingfei and Niebles, Juan Carlos and Patel, Vishal M. and Xu, Ran},title={Mask-free {OVIS}: Open-Vocabulary Instance Segmentation without Manual Mask Annotations},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Vancouver, Canada},month=jun,year={2023},doi={10.1109/CVPR52729.2023.02254}}
previts_wacv23.jpg
PreViTS: Contrastive Pretraining with Video Tracking Supervision
Brian Chen, Ramprasaath R. Selvaraju, Shih-Fu Chang, Juan Carlos Niebles, and Nikhil Naik
In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Hawaii, USA. Jan 2023
@inproceedings{Chen_WACV_2023,author={Chen, Brian and Selvaraju, Ramprasaath R. and Chang, Shih-Fu and Niebles, Juan Carlos and Naik, Nikhil},title={{PreViTS}: Contrastive Pretraining with Video Tracking Supervision},booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},address={Hawaii, USA},month=jan,year={2023},doi={10.1109/WACV56688.2023.00161}}
2022
luo2022moma.jpg
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing
Zelun Luo, Zane Durante, Linden Li, Wanze Xie, Ruochen Liu, Emily Jin , Zhuoyi Huang, Lun Yu Li, Jiajun Wu, Juan Carlos Niebles, and 2 more authors
In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track. New Orleans, USA. Dec 2022
@inproceedings{Luo_NeurIPS_2022,author={Luo, Zelun and Durante, Zane and Li, Linden and Xie, Wanze and Liu, Ruochen and Jin, Emily and Huang, Zhuoyi and Li, Lun Yu and Wu, Jiajun and Niebles, Juan Carlos and Adeli, Ehsan and Fei-Fei, Li},title={{MOMA-LRG}: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing},booktitle={Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},address={New Orleans, USA},month=dec,year={2022},}
Oral eccv22Priv.jpg
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens
Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, and Juan Carlos Niebles
In European Conference on Computer Vision (ECCV). Tel-Aviv, Israel. Oct 2022
@inproceedings{Hinojosa_ECCV_2022,author={Hinojosa, Carlos and Marquez, Miguel and Arguello, Henry and Adeli, Ehsan and Fei-Fei, Li and Niebles, Juan Carlos},title={{PrivHAR}: Recognizing Human Actions From Privacy-preserving Lens},booktitle={European Conference on Computer Vision (ECCV)},address={Tel-Aviv, Israel},month=oct,year={2022},doi={10.1007/978-3-031-19772-7_19},}
eccv22Open.jpg
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
Mingfei Gao, Chen Xing, Juan Carlos Niebles, Junnan Li, Ran Xu, Wenhao Liu, and Caiming Xiong
In European Conference on Computer Vision (ECCV). Tel-Aviv, Israel. Oct 2022
@inproceedings{Gao_ECCV_2022,author={Gao, Mingfei and Xing, Chen and Niebles, Juan Carlos and Li, Junnan and Xu, Ran and Liu, Wenhao and Xiong, Caiming},title={Open Vocabulary Object Detection with Pseudo Bounding-Box Labels},booktitle={European Conference on Computer Vision (ECCV)},address={Tel-Aviv, Israel},month=oct,year={2022},doi={10.1007/978-3-031-20080-9_16},}
Oral cvpr22-atp.jpg
Revisiting the ‘Video’ in Video-Language Understanding
@inproceedings{Buch_CVPR_2022,author={Buch, Shyamal and Eyzaguirre, Cristobal and Gaidon, Adrien and Wu, Jiajun and Fei-Fei, Li and Niebles, Juan Carlos},title={Revisiting the `Video' in Video-Language Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={New Orleans, USA},month=jun,year={2022},doi={10.1109/CVPR52688.2022.00293},}
cvpr22-align.jpg
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
Dongxu Li, Junnan Li, Hongdong Li, Juan Carlos Niebles, and Steven CH Hoi
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, USA. Jun 2022
@inproceedings{Li_CVPR_2022,author={Li, Dongxu and Li, Junnan and Li, Hongdong and Niebles, Juan Carlos and Hoi, Steven CH},title={Align and Prompt: Video-and-Language Pre-training with Entity Prompts},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={New Orleans, USA},month=jun,year={2022},doi={10.1109/CVPR52688.2022.00490},}
2021
neurips21-moma.jpg
MOMA: Multi-Object Multi-Actor Activity Parsing
Zelun Luo, Wanze Xie, Siddharth Kapoor, Yiyun Liang, Michael Cooper, Juan Carlos Niebles, Ehsan Adeli, and Fei-Fei Li
In Advances in Neural Information Processing Systems (NeurIPS). Online. Dec 2021
@inproceedings{Luo_NeurIPS_2021,author={Luo, Zelun and Xie, Wanze and Kapoor, Siddharth and Liang, Yiyun and Cooper, Michael and Niebles, Juan Carlos and Adeli, Ehsan and Li, Fei-Fei},title={{MOMA}: Multi-Object Multi-Actor Activity Parsing},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},month=dec,year={2021},address={Online},}
tnt-bmvc21.jpg
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification
Andrés Villa, Juan-Manuel Perez-Rua, Vladimir Araujo, Juan Carlos Niebles, Victor Escorcia, and Alvaro Soto
In British Machine Vision Conference (BMVC). Online. Nov 2021
@inproceedings{Villa_BMVC_2021,author={Villa, Andr\'{e}s and Perez-Rua, Juan-Manuel and Araujo, Vladimir and Niebles, Juan Carlos and Escorcia, Victor and Soto, Alvaro},title={{TNT}: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification},booktitle={British Machine Vision Conference (BMVC)},address={Online},month=nov,year={2021},}
Oral carlos_iccv2021.jpg
Learning Privacy-preserving Optics for Human Pose Estimation
@inproceedings{Hinojosa_ICCV_2021,author={Hinojosa, Carlos and Niebles, Juan Carlos and Arguello, Henry},title={Learning Privacy-preserving Optics for Human Pose Estimation},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Online},month=oct,year={2021},doi={10.1109/ICCV48922.2021.00257},}
@inproceedings{Ji_ICCV_2021,author={Ji, Jingwei and Desai, Rishi and Niebles, Juan Carlos},title={Detecting Human-Object Relationships in Videos},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Online},month=oct,year={2021},doi={10.1109/ICCV48922.2021.00800},}
vida_iccv_2021.jpg
TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
Vida Adeli, Mahsa Ehsanpour, Ian Reid, Juan Carlos Niebles, Silvio Savarese, Ehsan Adeli, and Hamid Rezatofighi
In IEEE/CVF International Conference on Computer Vision (ICCV). Online. Oct 2021
@inproceedings{Adeli_ICCV_2021,author={Adeli, Vida and Ehsanpour, Mahsa and Reid, Ian and Niebles, Juan Carlos and Savarese, Silvio and Adeli, Ehsan and Rezatofighi, Hamid},title={{TRiPOD}: Human Trajectory and Pose Dynamics Forecasting in the Wild},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Online},month=oct,year={2021},doi={10.1109/ICCV48922.2021.01314},}
media2021-gait.jpg
Quantifying Parkinson’s Disease Motor Severity Under Uncertainty Using MDS-UPDRS Videos
Mandy Lu, Qingyu Zhao, Kathleen L Poston, Edith V Sullivan, Adolf Pfefferbaum, Marian Shahid, Maya Katz, Leila Montaser Kouhsari, Kevin Schulman, Arnold Milstein, and 5 more authors
@article{Lu_MedIA_2021,author={Lu, Mandy and Zhao, Qingyu and Poston, Kathleen L and Sullivan, Edith V and Pfefferbaum, Adolf and Shahid, Marian and Katz, Maya and Kouhsari, Leila Montaser and Schulman, Kevin and Milstein, Arnold and Niebles, Juan Carlos and Henderson, Victor W and Fei-Fei, Li and Pohl, Kilian M and Adeli, Ehsan},title={Quantifying Parkinson’s Disease Motor Severity Under Uncertainty Using {MDS-UPDRS} Videos},journal={Medical Image Analysis},volume={73},month=oct,year={2021},doi={10.1016/j.media.2021.102179},}
homage_cvpr21.jpg
Home Action Genome: Cooperative Compositional Action Understanding
Nishant Rai, Haofeng Chen, Jingwei Ji, Rishi Desai, Kazuki Kozuka, Shun Ishizaka, Ehsan Adeli, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Online. Jun 2021
@inproceedings{Rai_CVPR_2021,author={Rai, Nishant and Chen, Haofeng and Ji, Jingwei and Desai, Rishi and Kozuka, Kazuki and Ishizaka, Shun and Adeli, Ehsan and Niebles, Juan Carlos},title={Home Action Genome: Cooperative Compositional Action Understanding},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Online},month=jun,year={2021},doi={10.1109/CVPR46437.2021.01103},}
metadata_cvpr21.jpg
Metadata Normalization
Mandy Lu, Qinyu Zhao, Jiequan Zhang, Kilian Pohl, Li Fei-Fei, Juan Carlos Niebles, and Ehsan Adeli
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Online. Jun 2021
@inproceedings{Lu_CVPR_2021,author={Lu, Mandy and Zhao, Qinyu and Zhang, Jiequan and Pohl, Kilian and Fei-Fei, Li and Niebles, Juan Carlos and Adeli, Ehsan},title={Metadata Normalization},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Online},month=jun,year={2021},doi={10.1109/CVPR46437.2021.01077},}
ehsan_wacv2021.jpg
Representation Learning with Statistical Independence to Mitigate Bias
Ehsan Adeli, Qinyu Zhao, Adolf Pfefferbaum, Edith Sullivan, Li Fei-Fei, Juan Carlos Niebles, and Kilian Pohl
In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Online. Jan 2021
@inproceedings{Adeli_WACV_2021,author={Adeli, Ehsan and Zhao, Qinyu and Pfefferbaum, Adolf and Sullivan, Edith and Fei-Fei, Li and Niebles, Juan Carlos and Pohl, Kilian},title={Representation Learning with Statistical Independence to Mitigate Bias},booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},address={Online},month=jan,year={2021},doi={10.1109/WACV48630.2021.00256}}
2020
vida_ral2020.jpg
Socially and Contextually Aware Human Motion and Pose Forecasting
Vida Adeli, Ehsan Adeli, Ian Reid, Juan Carlos Niebles, and Hamid Rezatofighi
IEEE Robotics and Automation Letters (RA-L). Oct 2020
@article{Adeli_RAL_2020,author={Adeli, Vida and Adeli, Ehsan and Reid, Ian and Niebles, Juan Carlos and Rezatofighi, Hamid},title={Socially and Contextually Aware Human Motion and Pose Forecasting},journal={IEEE Robotics and Automation Letters (RA-L)},doi={10.1109/LRA.2020.3010742},volume={5},number={4},month=oct,year={2020},}
mandy_miccai2020.jpg
Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson’s Disease Motor Severity
Mandy Lu, Kathleen Poston, Adolf Pfefferbaum, Edith V. Sullivan, Li Fei-Fei, Kilian M. Pohl, Juan Carlos Niebles, and Ehsan Adeli
In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). Online. Oct 2020
@inproceedings{Lu_MICCAI_2020,author={Lu, Mandy and Poston, Kathleen and Pfefferbaum, Adolf and Sullivan, Edith V. and Fei-Fei, Li and Pohl, Kilian M. and Niebles, Juan Carlos and Adeli, Ehsan},title={Vision-based Estimation of {MDS-UPDRS} Gait Scores for Assessing Parkinson’s Disease Motor Severity},booktitle={International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},address={Online},month=oct,year={2020},doi={10.1007/978-3-030-59716-0_61},}
vqa_ivc2020.jpg
Explaining VQA predictions using visual grounding and a knowledge base
Felipe Riquelme, Alfredo De Goyeneche, Yundong Zhang, Juan Carlos Niebles, and Alvaro Soto
@article{Riquelme_IVC_2020,author={Riquelme, Felipe and Goyeneche, Alfredo De and Zhang, Yundong and Niebles, Juan Carlos and Soto, Alvaro},title={Explaining VQA predictions using visual grounding and a knowledge base},journal={Image and Vision Computing},volume={101},month=sep,year={2020},doi={10.1016/j.imavis.2020.103968},}
rubiks.jpg
RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition
Linxi Fan, Shyamal Buch, Guanhzi Wang, Ryan Cao, Yuke Zhu, Juan Carlos Niebles, and Li Fei-Fei
In European Conference on Computer Vision (ECCV). Online. Aug 2020
@inproceedings{Fan_ECCV_2020,author={Fan, Linxi and Buch, Shyamal and Wang, Guanhzi and Cao, Ryan and Zhu, Yuke and Niebles, Juan Carlos and Fei-Fei, Li},title={RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition},booktitle={European Conference on Computer Vision (ECCV)},address={Online},month=aug,year={2020},doi={10.1007/978-3-030-58529-7_30},}
procedure2020.jpg
Procedure Planning in Instructional Videos
Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei, and Juan Carlos Niebles
In European Conference on Computer Vision (ECCV). Online. Aug 2020
@inproceedings{Chang_ECCV_2020,author={Chang, Chien-Yi and Huang, De-An and Xu, Danfei and Adeli, Ehsan and Fei-Fei, Li and Niebles, Juan Carlos},title={Procedure Planning in Instructional Videos},booktitle={European Conference on Computer Vision (ECCV)},address={Online},month=aug,year={2020},doi={10.1007/978-3-030-58621-8_20},}
seg-ral2020.jpg
Segmenting the Future
Hsu-kuang Chiu, Ehsan Adeli, and Juan Carlos Niebles
IEEE Robotics and Automation Letters (RA-L). Jul 2020
@article{Chiu_RAL_2020,author={Chiu, Hsu-kuang and Adeli, Ehsan and Niebles, Juan Carlos},title={Segmenting the Future},journal={IEEE Robotics and Automation Letters (RA-L)},volume={5},number={3},month=jul,year={2020},doi={10.1109/LRA.2020.2992184},}
actiongenome-cvpr2020.jpg
Action Genome: Actions as Compositions of Spatio-temporal Scene Graphs
Jingwei Ji, Ranjay Krishna, Li Fei-Fei, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, Washington, USA. Jun 2020
@inproceedings{Ji_CVPR_2020,author={Ji, Jingwei and Krishna, Ranjay and Fei-Fei, Li and Niebles, Juan Carlos},title={Action Genome: Actions as Compositions of Spatio-temporal Scene Graphs},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Seattle, Washington, USA},month=jun,year={2020},doi={10.1109/CVPR42600.2020.01025},}
stgraph-cvpr2020.jpg
Spatio-Temporal Graph for Video Captioning with Knowledge Distillation
Boxiao Pan, Haoye Cai, De-An Huang, Kuan-Hui Lee, Adrien Gaidon, Ehsan Adeli, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, Washington, USA. Jun 2020
@inproceedings{Pan_CVPR_2020,author={Pan, Boxiao and Cai, Haoye and Huang, De-An and Lee, Kuan-Hui and Gaidon, Adrien and Adeli, Ehsan and Niebles, Juan Carlos},title={Spatio-Temporal Graph for Video Captioning with Knowledge Distillation},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Seattle, Washington, USA},month=jun,year={2020},doi={10.1109/CVPR42600.2020.01088},}
tam-cvpr2020.jpg
Few-Shot Video Classification via Temporal Alignment
Kaidi Cao, Jingwei Ji, Zhangjie Cao, Chien-Yi Chang, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, Washington, USA. Jun 2020
@inproceedings{Cao_CVPR_2020,author={Cao, Kaidi and Ji, Jingwei and Cao, Zhangjie and Chang, Chien-Yi and Niebles, Juan Carlos},title={Few-Shot Video Classification via Temporal Alignment},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Seattle, Washington, USA},month=jun,year={2020},doi={10.1109/CVPR42600.2020.01063},}
bingbin-icra2020.jpg
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
Bingbin Liu, Ehsan Adeli, Zhangjie Cao, Kuan-Hui Lee, Abhijeet Shenoi, Adrien Gaidon, and Juan Carlos Niebles
IEEE Robotics and Automation Letters (RA-L) and IEEE International Conference on Robotics and Automation (ICRA). Paris, France. May 2020
@article{Liu_RAL_2020,author={Liu, Bingbin and Adeli, Ehsan and Cao, Zhangjie and Lee, Kuan-Hui and Shenoi, Abhijeet and Gaidon, Adrien and Niebles, Juan Carlos},title={Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction},journal={IEEE Robotics and Automation Letters (RA-L) and IEEE International Conference on Robotics and Automation (ICRA)},volume={5},number={2},address={Paris, France},month=may,year={2020},doi={10.1109/LRA.2020.2976305},}
dean-icra2020.jpg
Motion Reasoning for Goal-Based Imitation Learning
De-An Huang, Yu-Wei Chao, Chris Paxton, Xinke Deng, Li Fei-Fei, Juan Carlos Niebles, Animesh Garg, and Dieter Fox
In IEEE International Conference on Robotics and Automation (ICRA). Paris, France. May 2020
@inproceedings{Huang_ICRA_2020,author={Huang, De-An and Chao, Yu-Wei and Paxton, Chris and Deng, Xinke and Fei-Fei, Li and Niebles, Juan Carlos and Garg, Animesh and Fox, Dieter},title={Motion Reasoning for Goal-Based Imitation Learning},booktitle={IEEE International Conference on Robotics and Automation (ICRA)},address={Paris, France},month=may,year={2020},doi={10.1109/ICRA40945.2020.9197172},}
wacv2020.jpg
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
Karttikeya Mangalam, Ehsan Adeli, Kuan-Hui Lee, Adrien Gaidon, and Juan Carlos Niebles
In IEEE Winter Conference on Applications of Computer Vision (WACV). Colorado, USA. Mar 2020
@inproceedings{Mangalam_WACV_2020,author={Mangalam, Karttikeya and Adeli, Ehsan and Lee, Kuan-Hui and Gaidon, Adrien and Niebles, Juan Carlos},title={Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision},booktitle={IEEE Winter Conference on Applications of Computer Vision (WACV)},address={Colorado, USA},month=mar,year={2020},doi={10.1109/WACV45572.2020.9093350},}
Oral tcon-aaai20.png
Adversarial Cross-Domain Action Recognition with Co-Attention
Boxiao Pan, Zhangjie Cao, Ehsan Adeli, and Juan Carlos Niebles
In AAAI Conference on Artificial Intelligence (AAAI). New York. Feb 2020
@inproceedings{Pan_AAAI_2020,author={Pan, Boxiao and Cao, Zhangjie and Adeli, Ehsan and Niebles, Juan Carlos},title={Adversarial Cross-Domain Action Recognition with Co-Attention},booktitle={AAAI Conference on Artificial Intelligence (AAAI)},address={New York},month=feb,year={2020},doi={10.1609/aaai.v34i07.6854},}
2019
huang_iros19.jpg
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
De-An Huang, Danfei Xu, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei, and Juan Carlos Niebles
In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Macau, China. Nov 2019
@inproceedings{Huang_IROS_2019,author={Huang, De-An and Xu, Danfei and Zhu, Yuke and Garg, Animesh and Savarese, Silvio and Fei-Fei, Li and Niebles, Juan Carlos},title={Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning},booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},address={Macau, China},month=nov,year={2019},doi={10.1109/IROS40897.2019.8967761},}
jingwei_iccv19.png
Learning Temporal Action Proposals with Fewer Labels
@inproceedings{Ji_ICCV_2019,author={Ji, Jingwei and Cao, Kaidi and Niebles, Juan Carlos},title={Learning Temporal Action Proposals with Fewer Labels},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Seoul, South Korea},month=oct,year={2019},doi={10.1109/ICCV.2019.00717},}
wang-iccv19.png
Imitation Learning for Human Pose Prediction
Borui Wang, Ehsan Adeli, Hsu-kuang Chiu, De-An Huang, and Juan Carlos Niebles
In IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea. Oct 2019
@inproceedings{Wang_ICCV_2019,author={Wang, Borui and Adeli, Ehsan and Chiu, Hsu-kuang and Huang, De-An and Niebles, Juan Carlos},title={Imitation Learning for Human Pose Prediction},booktitle={IEEE/CVF International Conference on Computer Vision (ICCV)},address={Seoul, South Korea},month=oct,year={2019},doi={10.1109/ICCV.2019.00722},}
Oral cvpr19-ntg.png
Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
De-An Huang, Suraj Nair, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, California, USA. Jun 2019
@inproceedings{Huang_CVPR_2019,author={Huang, De-An and Nair, Suraj and Xu, Danfei and Zhu, Yuke and Garg, Animesh and Fei-Fei, Li and Savarese, Silvio and Niebles, Juan Carlos},title={Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Long Beach, California, USA},month=jun,year={2019},doi={10.1109/CVPR.2019.00876},}
cvpr19-d3tw.png
D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation
Chien-Yi Chang, De-An Huang, Yanan Sui, Li Fei-Fei, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, California, USA. Jun 2019
@inproceedings{Chang_CVPR_2019,author={Chang, Chien-Yi and Huang, De-An and Sui, Yanan and Fei-Fei, Li and Niebles, Juan Carlos},title={{D3TW}: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Long Beach, California, USA},month=jun,year={2019},doi={10.1109/CVPR.2019.00366},}
peeking-cvpr19.png
Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, and Li Fei-Fei
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, California, USA. Jun 2019
@inproceedings{Liang_CVPR_2019,author={Liang, Junwei and Jiang, Lu and Niebles, Juan Carlos and Hauptmann, Alexander and Fei-Fei, Li},title={Peeking into the Future: Predicting Future Person Activities and Locations in Videos},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Long Beach, California, USA},month=jun,year={2019},doi={10.1109/CVPR.2019.00587},}
wacv2019-pose.png
Action-Agnostic Human Pose Forecasting
Hsu-Kuang Chiu, Ehsan Adeli, Borui Wang, De-An Huang, and Juan Carlos Niebles
In IEEE Winter Conference on Applications of Computer Vision (WACV). Hawaii, USA. Jan 2019
@inproceedings{Chiu_WACV_2019,author={Chiu, Hsu-Kuang and Adeli, Ehsan and Wang, Borui and Huang, De-An and Niebles, Juan Carlos},title={Action-Agnostic Human Pose Forecasting},booktitle={IEEE Winter Conference on Applications of Computer Vision (WACV)},address={Hawaii, USA},month=jan,year={2019},doi={10.1109/WACV.2019.00156},}
wacv2019-vqa.png
Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining
Yundong Zhang, Juan Carlos Niebles, and Alvaro Soto
In IEEE Winter Conference on Applications of Computer Vision (WACV). Hawaii, USA. Jan 2019
@inproceedings{Zhang_WACV_2019,author={Zhang, Yundong and Niebles, Juan Carlos and Soto, Alvaro},title={Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining},booktitle={IEEE Winter Conference on Applications of Computer Vision (WACV)},address={Hawaii, USA},month=jan,year={2019},doi={10.1109/WACV.2019.00043},}
2018
nips18-decomp.png
Learning to Decompose and Disentangle Representations for Video Prediction
Jun-Ting Hsieh, Bingbin Liu, De-An Huang, Li Fei-Fei, and Juan Carlos Niebles
In Conference on Neural Information Processing Systems (NeurIPS). Montreal, Canada. Dec 2018
@inproceedings{Hsieh_NeurIPS_2018,author={Hsieh, Jun-Ting and Liu, Bingbin and Huang, De-An and Fei-Fei, Li and Niebles, Juan Carlos},title={Learning to Decompose and Disentangle Representations for Video Prediction},booktitle={Conference on Neural Information Processing Systems (NeurIPS)},address={Montreal, Canada},month=dec,year={2018},}
zang2018emnlp.jpg
Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation
Xiaoxue Zang, Ashwini Pokle, Marynel Vázquez, Kevin Chen, Juan Carlos Niebles, Alvaro Soto, and Silvio Savarese
In Conference on Empirical Methods in Natural Language Processing (EMNLP). Brussels, Belgium. Nov 2018
@inproceedings{Zang_EMNLP_2018,author={Zang, Xiaoxue and Pokle, Ashwini and Vázquez, Marynel and Chen, Kevin and Niebles, Juan Carlos and Soto, Alvaro and Savarese, Silvio},title={Translating Navigation Instructions in Natural Language to a High-Level Plan for Behavioral Robot Navigation},booktitle={Conference on Empirical Methods in Natural Language Processing (EMNLP)},address={Brussels, Belgium},month=nov,year={2018},doi={10.18653/v1/D18-1286},}
Oral seg-eccv18.jpg
End-to-End Joint Semantic Segmentation of Actors and Actions in Video
@inproceedings{Ji_ECCV_2018,author={Ji, Jingwei and Buch, Shyamal and Soto, Alvaro and Niebles, Juan Carlos},title={End-to-End Joint Semantic Segmentation of Actors and Actions in Video},booktitle={European Conference on Computer Vision (ECCV)},address={Munich, Germany},month=sep,year={2018},doi={10.1007/978-3-030-01225-0_43},}
modular-eccv18.jpg
Temporal Modular Networks for Retrieving Complex Compositional Activities in Video
Bingbin Liu, Serena Yeung, Edward Chou, De-An Huang, Li Fei-Fei, and Juan Carlos Niebles
In European Conference on Computer Vision (ECCV). Munich, Germany. Sep 2018
@inproceedings{Liu_ECCV_2018,author={Liu, Bingbin and Yeung, Serena and Chou, Edward and Huang, De-An and Fei-Fei, Li and Niebles, Juan Carlos},title={Temporal Modular Networks for Retrieving Complex Compositional Activities in Video},booktitle={European Conference on Computer Vision (ECCV)},address={Munich, Germany},month=sep,year={2018},doi={10.1007/978-3-030-01219-9_34},}
graph-eccv18.jpg
Graph Distillation for Action Detection with Privileged Modalities
Zelun Luo, Lu Jiang, Jun-Ting Hsieh, Juan Carlos Niebles, and Li Fei-Fei
In European Conference on Computer Vision (ECCV). Munich, Germany. Sep 2018
@inproceedings{Luo_ECCV_2018,author={Luo, Zelun and Jiang, Lu and Hsieh, Jun-Ting and Niebles, Juan Carlos and Fei-Fei, Li},title={Graph Distillation for Action Detection with Privileged Modalities},booktitle={European Conference on Computer Vision (ECCV)},address={Munich, Germany},month=sep,year={2018},doi={10.1007/978-3-030-01264-9_11},}
monitor-eccv18.jpg
Liquid Pouring Monitoring via Rich Sensory Inputs
Tz-Ying Wu, Juan-Ting Lin, Tsun-Hsuang Wang, Chan-Wei Hu, Juan Carlos Niebles, and Min Sun
In European Conference on Computer Vision (ECCV). Munich, Germany. Sep 2018
@inproceedings{Wu_ECCV_2018,author={Wu, Tz-Ying and Lin, Juan-Ting and Wang, Tsun-Hsuang and Hu, Chan-Wei and Niebles, Juan Carlos and Sun, Min},title={Liquid Pouring Monitoring via Rich Sensory Inputs},booktitle={European Conference on Computer Vision (ECCV)},address={Munich, Germany},month=sep,year={2018},doi={10.1007/978-3-030-01252-6_21},}
Oral finding-it.png
Finding ’It’: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video
@inproceedings{Huang_CVPR_2018b,author={Huang, De-An and Buch, Shyamal and Dery, Lucio and Garg, Animesh and Fei-Fei, Li and Niebles, Juan Carlos},title={Finding 'It': Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Salt Lake City, Utah, USA},month=jun,year={2018},doi={10.1109/CVPR.2018.00623},}
Spotlight cvpr18-fb.gif
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
De-An Huang, Vignesh Ramanathan, Dhruv Mahajan, Lorenzo Torresani, Manohar Paluri, Li Fei-Fei, and Juan Carlos Niebles
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, Utah, USA. Jun 2018
@inproceedings{Huang_CVPR_2018a,author={Huang, De-An and Ramanathan, Vignesh and Mahajan, Dhruv and Torresani, Lorenzo and Paluri, Manohar and Fei-Fei, Li and Niebles, Juan Carlos},title={What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets},booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},address={Salt Lake City, Utah, USA},month=jun,year={2018},doi={10.1109/CVPR.2018.00769},}
icra2018.png
A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation
Gabriel Sepúlveda, Juan Carlos Niebles, and Alvaro Soto
In IEEE International Conference on Robotics and Automation (ICRA). Brisbane, Australia. May 2018
@inproceedings{Sepulveda_ICRA_2018,author={Sepúlveda, Gabriel and Niebles, Juan Carlos and Soto, Alvaro},title={A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation},booktitle={IEEE International Conference on Robotics and Automation (ICRA)},address={Brisbane, Australia},month=may,year={2018},doi={10.1109/ICRA.2018.8460646},}
Vision-Based Construction Activity Analysis in Long Video Sequences via Hidden Markov Models: Experiments on Earthmoving Operations
Dominic Roberts, Mani Golparvar-Fard, Juan Carlos Niebles, JunYoung Gwak, and Ruxiao Bao
In Construction Research Congress (CRC). New Orleans. Apr 2018
@inproceedings{Roberts_CRC_2018,author={Roberts, Dominic and Golparvar-Fard, Mani and Niebles, Juan Carlos and Gwak, JunYoung and Bao, Ruxiao},title={Vision-Based Construction Activity Analysis in Long Video Sequences via Hidden Markov Models: Experiments on Earthmoving Operations},booktitle={Construction Research Congress (CRC)},pages={164-173},doi={10.1061/9780784481288.017},month=apr,year={2018},address={New Orleans},}
lang-nav.png
Behavioral Indoor Navigation With Natural Language Directions
Xiaoxue Zang, Marynel Vázquez, Juan Carlos Niebles, Alvaro Soto, and Silvio Savarese
In ACM/IEEE International Conference on Human Robot Interaction - Late Breaking Reports (HRI LBR). Chicago, Illinois, USA. Mar 2018
@inproceedings{Zang_HRILBR_2018,author={Zang, Xiaoxue and Vázquez, Marynel and Niebles, Juan Carlos and Soto, Alvaro and Savarese, Silvio},title={Behavioral Indoor Navigation With Natural Language Directions},booktitle={ACM/IEEE International Conference on Human Robot Interaction - Late Breaking Reports (HRI LBR)},address={Chicago, Illinois, USA},month=mar,year={2018},doi={10.1145/3173386.3177001},}
2017
Spotlight imitation.png
Visual Forecasting by Imitating Dynamics in Natural Sequences
Kuo-Hao Zeng, William B. Shen, De-An Huang, Min Sun, and Juan Carlos Niebles
In IEEE International Conference on Computer Vision (ICCV). Venice, Italy. Oct 2017
@inproceedings{Zeng_ICCV_2017,author={Zeng, Kuo-Hao and Shen, William B. and Huang, De-An and Sun, Min and Niebles, Juan Carlos},title={Visual Forecasting by Imitating Dynamics in Natural Sequences},booktitle={IEEE International Conference on Computer Vision (ICCV)},address={Venice, Italy},month=oct,year={2017},doi={10.1109/ICCV.2017.326},}
densevid.png
Dense-Captioning Events in Videos
Ranjay Krishna, Kenji Hata, Frederic Ren, Li Fei-Fei, and Juan Carlos Niebles
In IEEE International Conference on Computer Vision (ICCV). Venice, Italy. Oct 2017
@inproceedings{Krishna_ICCV_2017,author={Krishna, Ranjay and Hata, Kenji and Ren, Frederic and Fei-Fei, Li and Niebles, Juan Carlos},title={Dense-Captioning Events in Videos},booktitle={IEEE International Conference on Computer Vision (ICCV)},address={Venice, Italy},month=oct,year={2017},doi={10.1109/ICCV.2017.83},}
Oral sstad.png
End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos
@inproceedings{Buch_BMVC_2017,author={Buch, Shyamal and Escorcia, Victor and Ghanem, Bernard and Fei-Fei, Li and Niebles, Juan Carlos},title={End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos},booktitle={British Machine Vision Conference (BMVC)},address={London, UK},month=sep,year={2017},}
@inproceedings{Buch_CVPR_2017,author={Buch, Shyamal and Escorcia, Victor and Shen, Chuanqi and Ghanem, Bernard and Niebles, Juan Carlos},title={{SST}: Single-Stream Temporal Action Proposals},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Honolulu, Hawaii, USA},month=jun,year={2017},doi={10.1109/CVPR.2017.675},}
unsupervised_cvpr17.jpg
Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos
De-An Huang, Joseph Lim, Li Fei-Fei, and Juan Carlos Niebles
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Hawaii, USA. Jun 2017
@inproceedings{Huang_CVPR_2017,author={Huang, De-An and Lim, Joseph and Fei-Fei, Li and Niebles, Juan Carlos},title={Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Honolulu, Hawaii, USA},month=jun,year={2017},doi={10.1109/CVPR.2017.116},}
Spotlight agent_risk.jpg
Agent-centric Risk Assessment: Accident Anticipation and Risky Region Localization
Kuo-Hao Zeng, Shih-Han Chou, Fu-Hsiang Chan, Juan Carlos Niebles, and Min Sun
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, Hawaii, USA. Jun 2017
@inproceedings{Zeng_CVPR_2017,author={Zeng, Kuo-Hao and Chou, Shih-Han and Chan, Fu-Hsiang and Niebles, Juan Carlos and Sun, Min},title={Agent-centric Risk Assessment: Accident Anticipation and Risky Region Localization},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Honolulu, Hawaii, USA},month=jun,year={2017},doi={10.1109/CVPR.2017.146},}
sparse.jpg
Sparse composition of body poses and atomic actions for human activity recognition in RGB-D videos
@article{Lillo_IVC_2017,author={Lillo, Ivan and Niebles, Juan Carlos and Soto, Alvaro},title={Sparse composition of body poses and atomic actions for human activity recognition in {RGB-D} videos},journal={Image and Vision Computing},volume={59},month=mar,year={2017},doi={10.1016/j.imavis.201611004},}
AAAI17VideoQA.jpg
Leveraging Video Descriptions to Learn Video Question Answering
Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles Sun, and Min
In AAAI Conference on Artificial Intelligence (AAAI). San Francisco, USA. Feb 2017
@inproceedings{Zeng_AAAI_2017,author={Zeng, Kuo-Hao and Chen, Tseng-Hung and Chuang, Ching-Yao and Liao, Yuan-Hong and Sun, Juan Carlos Niebles and Min},title={Leveraging Video Descriptions to Learn Video Question Answering},booktitle={AAAI Conference on Artificial Intelligence (AAAI)},address={San Francisco, USA},month=feb,year={2017},doi={10.1609/aaai.v31i1.11238},}
2016
ectc-1.png
Connectionist Temporal Modeling for Weakly Supervised Action Labeling
@inproceedings{Huang_ECCV_2016,author={Huang, De-An and Fei-Fei, Li and Niebles, Juan Carlos},title={Connectionist Temporal Modeling for Weakly Supervised Action Labeling},booktitle={European Conference on Computer Vision (ECCV)},address={Amsterdam, Netherlands},month=oct,year={2016},doi={10.1007/978-3-319-46493-0_9},}
eccv16.jpg
DAPs: Deep Action Proposals for Action Understanding
@inproceedings{Escorcia_ECCV_2016,author={Escorcia, Victor and Caba Heilbron, Fabian and Niebles, Juan Carlos and Ghanem, Bernard},title={{DAPs}: Deep Action Proposals for Action Understanding},booktitle={European Conference on Computer Vision (ECCV)},address={Amsterdam, Netherlands},month=oct,year={2016},doi={10.1007/978-3-319-46487-9_47},}
VTG.jpg
Title Generation for User Generated Videos
Kuo-Hao Zeng, Tseng-Hung Chen, Juan Carlos Niebles, and Min Sun
In European Conference on Computer Vision (ECCV). Amsterdam, Netherlands. Oct 2016
@inproceedings{Zeng_ECCV_2016,author={Zeng, Kuo-Hao and Chen, Tseng-Hung and Niebles, Juan Carlos and Sun, Min},title={Title Generation for User Generated Videos},booktitle={European Conference on Computer Vision (ECCV)},address={Amsterdam, Netherlands},month=oct,year={2016},doi={10.1007/978-3-319-46475-6_38},}
proposals.jpg
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos
@inproceedings{Heilbron_CVPR_2016,author={Caba Heilbron, Fabian and Niebles, Juan Carlos and Ghanem, Bernard},title={Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Las Vegas, USA},month=jun,year={2016},doi={10.1109/CVPR.2016.211},}
actionlets3.jpg
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets
Ivan Lillo, Juan Carlos Niebles, and Alvaro Soto
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA. Jun 2016
@inproceedings{Lillo_CVPR_2016,author={Lillo, Ivan and Niebles, Juan Carlos and Soto, Alvaro},title={A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Las Vegas, USA},month=jun,year={2016},doi={10.1109/CVPR.2016.218},}
2015
anet_cvpr15b.jpg
ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding
@inproceedings{Caba_CVPR_2015,author={Caba Heilbron, Fabian and Escorcia, Victor and Ghanem, Bernard and Niebles, Juan Carlos},title={{ActivityNet}: A Large-Scale Video Benchmark for Human Activity Understanding},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Boston, USA},month=jun,year={2015},doi={10.1109/CVPR.2015.7298698},}
cvpr15a.jpg
On the Relationship between Visual Attributes and Convolutional Networks
@inproceedings{Escorcia_CVPR_2015,author={Escorcia, Victor and Niebles, Juan Carlos and Ghanem, Bernard},title={On the Relationship between Visual Attributes and Convolutional Networks},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Boston, USA},month=jun,year={2015},doi={10.1109/CVPR.2015.7298730},}
manhattan.jpg
Robust Manhattan Frame Estimation from a Single RGB-D Image
@inproceedings{Ghanem_CVPR_2015,author={Ghanem, Bernard and Thabet, Ali and Niebles, Juan Carlos and Caba Heilbron, Fabian},title={Robust Manhattan Frame Estimation from a Single {RGB-D} Image},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Boston, USA},month=jun,year={2015},doi={10.1109/CVPR.2015.7299001},}
2014
actioncue.jpg
Camera Motion and Surrounding Scene Appearance as Context for Action Recognition
Fabian Caba Heilbron, Ali Thabet, Juan Carlos Niebles, and Bernard Ghanem
In Asian Conference on Computer Vision (ACCV). Singapore. Nov 2014
@inproceedings{Heilbron_ACCV_2014,author={Heilbron, Fabian Caba and Thabet, Ali and Niebles, Juan Carlos and Ghanem, Bernard},title={Camera Motion and Surrounding Scene Appearance as Context for Action Recognition},booktitle={Asian Conference on Computer Vision (ACCV)},address={Singapore},month=nov,year={2014},doi={10.1007/978-3-319-16817-3_38},}
automation2014.png
Vision-based workface assessment using depth images for activity analysis of interior construction operations
Ardalan Khosrowpour, Juan Carlos Niebles, and Mani Golparvar-Fard
@article{Khosrowpour_AutCon_2014,author={Khosrowpour, Ardalan and Niebles, Juan Carlos and Golparvar-Fard, Mani},title={Vision-based workface assessment using depth images for activity analysis of interior construction operations},journal={Automation in Construction},volume={48},month=dec,year={2014},doi={10.1016/j.autcon.201408003},}
cvpr2014.png
Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities
Ivan Lillo, Alvaro Soto, and Juan Carlos Niebles
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colombus, USA. Jun 2014
@inproceedings{Lillo_CVPR_2014,author={Lillo, Ivan and Soto, Alvaro and Niebles, Juan Carlos},title={Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Colombus, USA},month=jun,year={2014},doi={10.1109/CVPR.2014.109},}
indoor.png
Automated Worker Activity Analysis in Indoor Environments for Direct-Work Rate Improvement from long sequences of RGB-D Images
Ardalan Khosrowpour, Igor Fedorov, Aleksander Holynski, Juan Carlos Niebles, and Mani Golparvar-Fard
In Construction Research Congress (CRC). Atlanta, USA. May 2014
@inproceedings{Khosrowpour_CRC_2014,author={Khosrowpour, Ardalan and Fedorov, Igor and Holynski, Aleksander and Niebles, Juan Carlos and Golparvar-Fard, Mani},title={Automated Worker Activity Analysis in Indoor Environments for Direct-Work Rate Improvement from long sequences of {RGB-D} Images},booktitle={Construction Research Congress (CRC)},month=may,year={2014},address={Atlanta, USA},doi={10.1061/9780784413517.075},}
crowd.jpg
Collecting and Annotating Human Activities in Web Videos
@inproceedings{Heilbron_ICMR_2014,author={Caba Heilbron, Fabian and Niebles, Juan Carlos},title={Collecting and Annotating Human Activities in Web Videos},booktitle={ACM International Conference on Multimedia Retrieval (ICMR)},address={Glasgow, UK},month=apr,year={2014},doi={10.1145/2578726.2578775},}
2013
iccvw13.jpg
Spatio-Temporal Human-Object Interactions for Action Recognition in Videos
@inproceedings{Escorcia_ICCVW_2013,author={Escorcia, Victor and Niebles, Juan Carlos},title={Spatio-Temporal Human-Object Interactions for Action Recognition in Videos},booktitle={IEEE International Conference on Computer Vision Workshops (ICCVW)},address={Sydney, Australia},month=dec,year={2013},doi={10.1109/ICCVW.2013.72},}
earthmoving.jpg
Vision-based action recognition of earthmoving equipment using spatio-temporal features and support vector machine classifiers
Mani Golparvar-Fard, Arsalan Heydarian, and Juan Carlos Niebles
@article{GolparvarFard_AEI_2013,author={Golparvar-Fard, Mani and Heydarian, Arsalan and Niebles, Juan Carlos},title={Vision-based action recognition of earthmoving equipment using spatio-temporal features and support vector machine classifiers},journal={Advanced Engineering Informatics},volume={27},number={4},month=oct,year={2013},doi={10.1016/j.aei.201309001},}
hogc.jpg
Automated 2D detection of construction equipment and workers from site video streams using histograms of oriented gradients and colors
Milad Memarzadeh, Mani Golparvar-Fard, and Juan Carlos Niebles
@article{Memarzadeh_AutCon_2013,author={Memarzadeh, Milad and Golparvar-Fard, Mani and Niebles, Juan Carlos},title={Automated 2D detection of construction equipment and workers from site video streams using histograms of oriented gradients and colors},journal={Automation in Construction},volume={32},month=jul,year={2013},doi={10.1016/j.autcon.201212002},}
2012
crc2012.jpg
Automated Vision-based Recognition of Construction Worker Actions for Building Interior Construction Operations Using RGBD Cameras
Victor Escorcia, Maria A. Dávila, Mani Golparvar-Fard, and Juan Carlos Niebles
In Construction Research Congress (CRC). West Lafayette, Indiana, USA. May 2012
@inproceedings{Escorcia_CRC_2012,author={Escorcia, Victor and Dávila, Maria A. and Golparvar-Fard, Mani and Niebles, Juan Carlos},title={Automated Vision-based Recognition of Construction Worker Actions for Building Interior Construction Operations Using {RGBD} Cameras},booktitle={Construction Research Congress (CRC)},address={West Lafayette, Indiana, USA},month=may,year={2012},doi={10.1061/9780784412329.089},}
equipment_actions.jpg
Automated visual recognition of construction equipment actions using spatio-temporal features and multiple binary support vector machines
Arsalan Heydarian, Mani Golparvar-Fard, and Juan Carlos Niebles
In Construction Research Congress (CRC). West Lafayette, Indiana, USA. May 2012
@inproceedings{Heydarian_CRC_2012,author={Heydarian, Arsalan and Golparvar-Fard, Mani and Niebles, Juan Carlos},title={Automated visual recognition of construction equipment actions using spatio-temporal features and multiple binary support vector machines},booktitle={Construction Research Congress (CRC)},address={West Lafayette, Indiana, USA},month=may,year={2012},doi={10.1061/9780784412329.090},}
equipment_tracking.jpg
Real-time and automated recognition and 2D tracking of Construction workers and equipment from Site video streams
Milad Memarzadeh, Arsalan Heydarian, Mani Golparvar-Fard, and Juan Carlos Niebles
In ASCE International Conference on Computing in Civil Engineering (i3CE). Clearwater Beach, Florida, USA. Jun 2012
@inproceedings{Memarzadeh_i3CE_2012,author={Memarzadeh, Milad and Heydarian, Arsalan and Golparvar-Fard, Mani and Niebles, Juan Carlos},title={Real-time and automated recognition and {2D} tracking of Construction workers and equipment from Site video streams},booktitle={ASCE International Conference on Computing in Civil Engineering (i3CE)},address={Clearwater Beach, Florida, USA},month=jun,year={2012},doi={10.1061/9780784412343.0054},}
2010
Oral NieblesChenFei-Fei_ECCV2010_icon.jpg
Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification
Juan Carlos Niebles, Chih-Wei Chen, and Li Fei-Fei
In European Conference on Computer Vision (ECCV). Hersonissos, Crete, Greece. Sep 2010
@inproceedings{Niebles_ECCV_2010,author={Niebles, Juan Carlos and Chen, Chih-Wei and Fei-Fei, Li},title={Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification},booktitle={European Conference on Computer Vision (ECCV)},address={Hersonissos, Crete, Greece},month=sep,year={2010},doi={10.1007/978-3-642-15552-9_29},}
efficient_moving_people.jpg
Efficient Extraction of Human Motion Volumes by Tracking
Juan Carlos Niebles, Bohyung Han, and Li Fei-Fei
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, USA. Jun 2010
@inproceedings{Niebles_CVPR_2010,author={Niebles, Juan Carlos and Han, Bohyung and Fei-Fei, Li},title={Efficient Extraction of Human Motion Volumes by Tracking},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={San Francisco, USA},month=jun,year={2010},doi={10.1109/CVPR.2010.5540152},}
2009
mining.jpg
Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition
Bangpeng Yao, Juan Carlos Niebles, and Li Fei-Fei
In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Miami, USA. Jun 2009
@inproceedings{Yao_CVPRW_2009,author={Yao, Bangpeng and Niebles, Juan Carlos and Fei-Fei, Li},title={Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition},booktitle={IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},address={Miami, USA},month=jun,year={2009},doi={10.1109/CVPRW.2009.5204222}}
2008
eccv08.jpg
Extracting Moving People from Internet Videos
Juan Carlos Niebles, Bohyung Han, Andras Ferencz, and Li Fei-Fei
In European Conference on Computer Vision (ECCV). Marseilles, France. Oct 2008
@inproceedings{Niebles_ECCV_2008,author={Niebles, Juan Carlos and Han, Bohyung and Ferencz, Andras and Fei-Fei, Li},title={Extracting Moving People from Internet Videos},booktitle={European Conference on Computer Vision (ECCV)},address={Marseilles, France},month=oct,year={2008},doi={10.1007/978-3-540-88693-8_39},}
ijcv.jpg
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
Juan Carlos Niebles, Hongcheng Wang, and Li Fei-Fei
International Journal of Computer Vision (IJCV). Sep 2008
@article{Niebles_IJCV_2008,author={Niebles, Juan Carlos and Wang, Hongcheng and Fei-Fei, Li},title={Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words},journal={International Journal of Computer Vision (IJCV)},volume={79},month=sep,year={2008},doi={10.1007/s11263-007-0122-4},}
correlatons.jpg
Spatial-Temporal Correlatons for Unsupervised Action Classification
Silvio Savarese, Andrey Del Pozo, Juan Carlos Niebles, and Li Fei-Fei
In IEEE Workshop on Motion and Video Computing (WMVC). Copper Mountain, Colorado, USA. Jan 2008
@inproceedings{Savarese_WMVC_2008,author={Savarese, Silvio and Pozo, Andrey Del and Niebles, Juan Carlos and Fei-Fei, Li},title={Spatial-Temporal Correlatons for Unsupervised Action Classification},booktitle={IEEE Workshop on Motion and Video Computing (WMVC)},address={Copper Mountain, Colorado, USA},month=jan,year={2008},doi={10.1109/WMVC.2008.4544068},}
2007
optimol.png
OPTIMOL: a framework for Online Picture collecTion via Incremental MOdel Learning
Li-Jia Li, Juan Carlos Niebles, and Li Fei-Fei
In Association for the Advancement of Artificial Intelligence (AAAI) 2007 Robot Competition and Exhibition. Vancouver, Canada. Jul 2007
@inproceedings{Li_AAAI_2007,author={Li, Li-Jia and Niebles, Juan Carlos and Fei-Fei, Li},title={{OPTIMOL}: a framework for Online Picture collecTion via Incremental MOdel Learning},booktitle={Association for the Advancement of Artificial Intelligence (AAAI) 2007 Robot Competition and Exhibition},address={Vancouver, Canada},month=jul,year={2007},}
NieblesFei-Fei_CVPR2007.jpg
A Hierarchical Model of Shape and Appearance for Human Action Classification
Juan Carlos Niebles, and Li Fei-Fei
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Minneapolis, USA. Jun 2007
@inproceedings{Niebles_CVPR_2007,author={Niebles, Juan Carlos and Fei-Fei, Li},title={A Hierarchical Model of Shape and Appearance for Human Action Classification},booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},address={Minneapolis, USA},month=jun,year={2007},doi={10.1109/CVPR.2007.383132},}
2006
Oral NieblesWangFei-Fei_BMVC2006.jpg
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
Juan Carlos Niebles, Hongcheng Wang, and Li Fei-Fei
In British Machine Vision Conference (BMVC). Edinburgh, UK. Sep 2006
@inproceedings{Niebles_BMVC_2006,author={Niebles, Juan Carlos and Wang, Hongcheng and Fei-Fei, Li},title={Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words},booktitle={British Machine Vision Conference (BMVC)},address={Edinburgh, UK},month=sep,year={2006},doi={10.5244/C.20.127},}
2004
tugboat.png
Signal Processing Unit for River Tugboat Telemetry System
Humberto Campanella, Mauricio Pardo, Victor Manotas, Javier Páez, Juan Carlos Niebles, and David Angulo
In Conference on Design of Circuits and Integrated Systems (DCIS). Bordeaux, France. Nov 2004
@inproceedings{Campanella_DCIS_2004,author={Campanella, Humberto and Pardo, Mauricio and Manotas, Victor and P\'{a}ez, Javier and Niebles, Juan Carlos and Angulo, David},title={Signal Processing Unit for River Tugboat Telemetry System},booktitle={Conference on Design of Circuits and Integrated Systems (DCIS)},address={Bordeaux, France},month=nov,year={2004},}
2001
robots.png
Dispositivos automatas para navegacion, deteccion y recoleccion de pelotas de tenis en ambientes conocidos
Carlos Cubas, Marcos Consuegra, Royman Lopez, Alexis Sierra, Jorge Leon, Fernando Mendez, Carlos Ochoa, Fabian Panesso, Edgar Sotter, Fabian Manotas, and 4 more authors
@article{Cubas_IyD_2001,author={Cubas, Carlos and Consuegra, Marcos and Lopez, Royman and Sierra, Alexis and Leon, Jorge and Mendez, Fernando and Ochoa, Carlos and Panesso, Fabian and Sotter, Edgar and Manotas, Fabian and Manotas, Victor and Niebles, Juan Carlos and Pardo, Mauricio and Vallejo, Eric},title={Dispositivos automatas para navegacion, deteccion y recoleccion de pelotas de tenis en ambientes conocidos},journal={Revista Ingenieria y Desarrollo (IyD)},month=jan,year={2001},}
