An open-source toolbox for action understanding based on PyTorch

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

R-C3D pytorch implementation

Awesome papers & datasets specifically focused on long-term videos.

temporal action detection: benchmark results, features download etc.

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

A curated publication list on weakly-supervised temporal action localization

[TIP 2022] End-to-end Temporal Action Detection with Transformer

[ECCV 2022] Official Pytorch Implementation of the paper : " Zero-Shot Temporal Action Detection via Vision-Language Prompting "

[CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection

[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark

A single stage temporal action detection toolbox based on PyTorch

[NeurIPS 2022] PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points

End to End Streaming Video Temporal Segmentation

[ECCV 2022] Official Pytorch Implementation of the paper : " Semi-Supervised Temporal Action Detection with Proposal-Free Masking "

【AAAI 2022】Temporal Action Proposal Generation with Background Constraint

[ECCV 2022] Official Pytorch Implementation of paper : " Proposal-Free Temporal Action Detection with Global Segmentation Mask Learning "

[AAAI 2022] DCAN: Improving Temporal Action Detection via Dual Context Aggregation

[CVPR 2024] Asymmetric Masked Distillation for Pre-Training Small Foundation Models