[CVPR 2022] Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection

OpenMMLab FewShot Learning Toolbox and Benchmark

Improving Calibration for Long-Tailed Recognition (CVPR2021)

[BMVC 2021] A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark

Fast CUDA implementation of (differentiable) otam for PyTorch using Numba

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Context-aware RCNN: a Baseline for Action Detection in Videos

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Code and pretrained models for LIP: Local Importance-based Pooling (ICCV 19)

[ECCV 2020] Actions as Moving Points

[CVIU] Fully Convolutional Online Tracking

Learning Spatiotemporal Features via Video and Text Pair Discrimination

De novo analysis for cryo-electron tomography

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

3D extension of a Gabor filter

AI for tomography

Code and pretrained models for LIP: Local Importance-based Pooling (ICCV 19)