weidafeng / Efficient-SlowFast
Efficient dual attention SlowFast networks for video action recognition
☆23Updated 2 years ago
Alternatives and similar repositories for Efficient-SlowFast:
Users that are interested in Efficient-SlowFast are comparing it to the libraries listed below
- pytorch☆60Updated 4 years ago
- Contains code for C3D, LCN and TSM for action recognition models.☆10Updated 4 years ago
- ☆46Updated 4 years ago
- Custom ava dataset, Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions☆122Updated 2 years ago
- download AVA dataset☆20Updated last year
- You Only Watch One Frame for Online Spatio-Temporal Action Detection☆33Updated last year
- Tiny Kinetics-400 for test☆90Updated last year
- ☆102Updated 2 years ago
- Implementation of brand new video augmentation strategy for video action recognition with 3D CNN☆27Updated 3 years ago
- A re-trainable version version of i3d. It is a superset of kinetics_i3d_pytorch repo from hassony2. You can train on your own dataset, an…☆9Updated 5 years ago
- ☆15Updated 2 years ago
- Official codes of CVPR21 paper: Learning Normal Dynamics in Videos with Meta Prototype Network☆133Updated 2 years ago
- Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020☆112Updated 10 months ago
- TAM: Temporal Adaptive Module for Video Recognition☆201Updated 2 years ago
- [Codes of paper]: Busy-Quiet Video Disentangling for Video Classification☆13Updated 3 years ago
- ☆59Updated 2 years ago
- Code for the paper: "Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM"☆59Updated last year
- Action_Recognition_Surveillance, for huamn fall down action recognition, helmet、smoke、cell-phone detection.☆16Updated 2 years ago
- [CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few…☆100Updated 2 years ago
- The Pytorch code of the TEA module (Temporal Excitation and Aggregation for Action Recognition)☆193Updated 3 years ago
- A simple but efficient transformer model for video action recognition☆58Updated 2 years ago
- fourierer / Video_Classification_ResNet3D_R2plus1D_ip-CSN_train-UCF101-HMDB51-Kinetics400-from-scratchUsing ResNet3D-50,R(2+1)D-50, and ip_CSN-50 to train UCD-101,HMDB-51 and Kinetics-400 from scratch.☆28Updated 4 years ago
- Official PyTorch implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21)☆203Updated 3 years ago
- Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"☆175Updated 3 years ago
- task: pose estimation/ action recognition/ object track => kapao/ yolo-pose/ sort / bot-sort/ oc-sort☆12Updated 2 years ago
- Official codes for CVPR2021 paper "MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection"☆131Updated 2 years ago
- YOLO-POSE was used for key point detection, Bytetrack for tracking, and STGCN for fall and other behavior recognition☆44Updated 2 years ago
- [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding☆21Updated 4 years ago
- Video Transformer Network☆40Updated 3 years ago
- C3D-LSTM implementation in PyTorch [WACV 2019]☆39Updated 4 years ago