[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
[CVPR 2020] Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)
Video Graph Transformer for Video Question Answering (ECCV'22)
Official source code for "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems". In NeurIPS 2021.
Official source code for "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields". In NeurIPS 2023.
Code for "Ranking Causal Anomalies via Temporal and Dynamical Analysis on Vanishing Correlations" @ SIGKDD2016
A network model for studying the relation between temporal dynamics and connectivity structure
(CVPR 2020) Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)
A theoretical neural architecture where neurons autonomously learn temporal correlations. Enables continuous learning through binary processing of any input modality without preprocessing. Proposes pathway toward AGI via emergent self-organization and swarm intelligence principles.
LSTN is an experimental text generation engine that models language not as static probabilities, but as a dynamic and "liquid" neural network. Each trigram (3-character sequence) acts as an individual neuron within a continuous temporal dynamic system.
Revolutionary real-time control system for dynamic warp bubble stability, integrating seven advanced digital twin mathematical frameworks with enhanced uncertainty quantification, achieving 99.9% temporal coherence, ×ばつ metamaterial amplification, and sub-millisecond field transition control with complete causality preservation.
Comparative Analysis of LDR vs. HDR Imaging: Quantifying Luminosity Variability and Sky Dynamics through Image Processing Techniques
High-salience events slow the internal clock and reinforce memory. Quiet stretches accelerate the clock and let stale items decay. One model. One knob. Adaptive tempo.
A specification for unfinished regions: non-erasable, non-optimizable traces that remain referable at runtime.
Computational modeling pipeline for detecting near-term suicidality risk from reaction-time dynamics in the Death IAT. Latent temporal structure is extracted using PCA and autocorrelation analysis and used in a bilinear logistic regression classifier (77% balanced accuracy).
To associate your repository with the temporal-dynamics topic, visit your repo's landing page and select "manage topics."