Efficient dual attention SlowFast networks for video action recognition

[CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization

Implementation for the paper "Unified Compositional Query Machine with Multimodal Consistency for Video-based Human Activity Recognition" (Tuyen et al., BMVC 2024)

Official repository for "Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition" [ICCV 2023]

[CVPR 2023] "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation" official implementation.

The project is an official implementation of our paper "3D Human Pose Estimation with Spatial and Temporal Transformers".

[ACMMM 2024] Implementation of the paper “Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition“.

[ECCV 2024] Official repository of SkateFormer

《The Way to Go》中文译本，中文正式名《Go 入门指南》

[CVPR 2023] Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition

[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"

[ICCV 2023] Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition

[ICCV'23] PAINet: Parallel Attention Interaction Network for Few-shot Skeleton-based Action Recognition

OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.

[CVPR 2023] STMixer: A One-Stage Sparse Action Detector