Action Recognition
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
Subtasks
Greatest papers with code
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
CVPR 2018
• tensorflow/models
• 
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
CVPR 2018
• kenshohara/3D-ResNets-PyTorch
• 
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels.
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• yysijie/st-gcn
•
Dynamics of human body skeletons convey significant information for human action recognition.
Temporal Segment Networks for Action Recognition in Videos
• yjxiong/temporal-segment-networks
•
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
• yjxiong/temporal-segment-networks
•
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
CVPR 2017
• deepmind/kinetics-i3d
•
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks.
SOTA for Action Recognition on HMDB51 (using extra training data)
Sparse 3D convolutional neural networks
• facebookresearch/SparseConvNet
• 
We have implemented a convolutional neural network designed for processing sparse three-dimensional input data.
Real-time Action Recognition with Enhanced Motion Vector CNNs
The deep two-stream architecture exhibited excellent performance on video based action recognition.
Towards Good Practices for Very Deep Two-Stream ConvNets
However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.
A Closer Look at Spatiotemporal Convolutions for Action Recognition
CVPR 2018 • facebookresearch/R2Plus1D
In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition.