open-mmlab / mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
☆4,574Updated 8 months ago
Alternatives and similar repositories for mmaction2:
Users that are interested in mmaction2 are comparing it to the libraries listed below
- PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.☆6,918Updated 5 months ago
- OpenMMLab Computer Vision Foundation☆6,113Updated last week
- A deep learning library for video understanding research.☆3,429Updated 3 months ago
- OpenMMLab Pre-training Toolbox and Benchmark☆3,642Updated 6 months ago
- [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding☆2,115Updated 9 months ago
- A toolbox for skeleton-based action recognition.☆1,074Updated last month
- OpenMMLab Semantic Segmentation Toolbox and Benchmark.☆8,859Updated 8 months ago
- This is an official implementation for "Video Swin Transformers".☆1,543Updated 2 years ago
- An open-source toolbox for action understanding based on PyTorch☆1,871Updated 3 years ago
- AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.☆3,431Updated 8 months ago
- Deformable DETR: Deformable Transformers for End-to-End Object Detection.☆3,508Updated 11 months ago
- OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT…☆3,713Updated last year
- ☆847Updated 11 months ago
- The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"☆1,679Updated last year
- Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.☆4,203Updated last month
- End-to-End Object Detection with Transformers☆14,292Updated last year
- YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta…☆9,812Updated 5 months ago
- You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization☆877Updated 6 months ago
- This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and …☆1,873Updated 2 years ago
- OpenMMLab Detection Toolbox and Benchmark☆30,932Updated 8 months ago
- OpenMMLab Self-Supervised Learning Toolbox and Benchmark☆3,254Updated last year
- The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.☆5,245Updated 3 years ago
- BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models☆7,277Updated this week
- An efficient video loader for deep learning with smart shuffling that's super easy to digest☆2,132Updated 9 months ago
- RepVGG: Making VGG-style ConvNets Great Again☆3,387Updated 2 years ago
- [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box☆5,246Updated 10 months ago
- Code release for ConvNeXt model☆5,989Updated 2 years ago
- OpenMMLab Pose Estimation Toolbox and Benchmark.☆6,389Updated 9 months ago
- [NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training☆1,490Updated last year
- This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".☆14,729Updated 9 months ago