简体中文 | English

Introduction

We implemented video classification model and action localization model in this repo.

Model list

Field	Model	Config	Dataset	Metrics	ACC%	Download
action recgonition	ppTSM	pptsm_k400.yaml	Kinetics-400	Top-1	73.5	ppTSM.pdparams
action recgonition	SlowFast	slowfast.yaml	Kinetics-400	Top-1	74.35	SlowFast.pdparams
action recgonition	TSM	tsm.yaml	Kinetics-400	Top-1	70.0	TODO
action recgonition	TSN	tsn.yaml	Kinetics-400	Top-1	67.0	TODO
action recgonition	Attention LSTM	attention_lstm.yaml	Youtube-8M	Hit@1	89.0	AttentionLstm.pdparams
action detection	BMN	bmn.yaml	ActivityNet	AUC	67.0	BMN.pdparams

Reference

• Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification, Xiang Long, Chuang Gan, Gerard de Melo, Jiajun Wu, Xiao Liu, Shilei Wen

• BMN: Boundary-Matching Network for Temporal Action Proposal Generation, Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen.

• SlowFast Networks for Video Recognition, Feichtenhofer C, Fan H, Malik J, et al.

• Temporal Segment Networks: Towards Good Practices for Deep Action Recognition, Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc Van Gool

• Temporal Shift Module for Efficient Video Understanding, Ji Lin, Chuang Gan, Song Han