Alternatives and similar repositories for mmaction2:

Users that are interested in mmaction2 are comparing it to the libraries listed below

• facebookresearch / SlowFast
  PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
  ☆6,744Updated last month
• open-mmlab / mmpose
  OpenMMLab Pose Estimation Toolbox and Benchmark.
  ☆6,036Updated 5 months ago
• open-mmlab / mmpretrain
  OpenMMLab Pre-training Toolbox and Benchmark
  ☆3,532Updated 2 months ago
• kennymckormick / pyskl
  A toolbox for skeleton-based action recognition.
  ☆1,018Updated 10 months ago
• open-mmlab / mmcv
  OpenMMLab Computer Vision Foundation
  ☆5,970Updated 3 weeks ago
• SwinTransformer / Video-Swin-Transformer
  This is an official implementation for "Video Swin Transformers".
  ☆1,478Updated last year
• facebookresearch / TimeSformer
  The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
  ☆1,601Updated 9 months ago
• facebookresearch / pytorchvideo
  A deep learning library for video understanding research.
  ☆3,365Updated last month
• mit-han-lab / temporal-shift-module
  [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
  ☆2,085Updated 6 months ago
• open-mmlab / mmaction
  An open-source toolbox for action understanding based on PyTorch
  ☆1,865Updated 2 years ago
• cvdfoundation / kinetics-dataset
  ☆801Updated 8 months ago
• leoxiaobin / deep-high-resolution-net.pytorch
  The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
  ☆4,364Updated 4 months ago
• open-mmlab / mmskeleton
  A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
  ☆2,960Updated 2 years ago
• DingXiaoH / RepVGG
  RepVGG: Making VGG-style ConvNets Great Again
  ☆3,360Updated last year
• MCG-NJU / VideoMAE
  [NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
  ☆1,421Updated last year
• open-mmlab / mmsegmentation
  OpenMMLab Semantic Segmentation Toolbox and Benchmark.
  ☆8,481Updated 5 months ago
• open-mmlab / mmyolo
  OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
  ☆3,073Updated 6 months ago
• fundamentalvision / Deformable-DETR
  Deformable DETR: Deformable Transformers for End-to-End Object Detection.
  ☆3,360Updated 8 months ago
• dmlc / decord
  An efficient video loader for deep learning with smart shuffling that's super easy to digest
  ☆1,972Updated 6 months ago
• open-mmlab / mmtracking
  OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT…
  ☆3,625Updated last year
• ifzhang / ByteTrack
  [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
  ☆4,969Updated 6 months ago
• huawei-noah / Efficient-AI-Backbones
  Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
  ☆4,115Updated last month
• kenshohara / 3D-ResNets-PyTorch
  3D ResNets for Action Recognition (CVPR 2018)
  ☆3,934Updated 3 years ago
• jinwchoi / awesome-action-recognition
  A curated list of action recognition and related area resources
  ☆3,846Updated last year
• SwinTransformer / Swin-Transformer-Object-Detection
  This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and …
  ☆1,830Updated last year
• lucasjinreal / yolov7_d2
  🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
  ☆3,127Updated last year
• PaddlePaddle / PaddleVideo
  Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based a…
  ☆1,555Updated this week
• biubug6 / Pytorch_Retinaface
  Retinaface get 80.99% in widerface hard val using mobilenet0.25.
  ☆2,685Updated last year
• IDEA-Research / DINO
  [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
  ☆2,337Updated 5 months ago
• wei-tim / YOWO
  You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
  ☆854Updated 2 months ago