Paper | Code | Accuracy | ModelName | ReleaseDate |
---|---|---|---|---|
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling | 93.4 | Structured Keypoint Pooling | 2023-03-27 | |
Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model | 90.4 | Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics dataset | 2022-02-04 | |
Human skeletons and change detection for efficient violence detection in surveillance videos | ✓ Link | 90.25 | Human Skeletons + Change Detection | 2023-05-20 |
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM | ✓ Link | 89.75 | Separable Convolutional LSTM | 2021-02-21 |
Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition | 89.3 | SPIL Convolution | ||
RWF-2000: An Open Large Scale Video Database for Violence Detection | ✓ Link | 87.25 | Flow Gated Network | 2019-11-14 |