cv benchmarks / cv baselines
This repository aims to provide readers with the current benchmarks for the most common Computer Vision (CV) tasks, including Object Detection, Pose Estimation, Scene Text Recognition, Video Classification, Visual Question Answering, image text retrieval and so on.
| object_detection | pose_estimation | scene_text_recognition |
| object_det | pose_estimation | STR |
| video_classification | visual_question_answering | image_text_retrieval |
| video_cls | vqa | image_text_retrieval |
- benchmark of text-sentence retrieval
- benchmark of face recognition
- benchmark of visual segmentation
- benchmark of image classification
- benchmark of visual caption