Zhongdao / UniTrack
[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).
☆344Updated 2 years ago
Alternatives and similar repositories for UniTrack:
Users that are interested in UniTrack are comparing it to the libraries listed below
- Global Tracking Transformers, CVPR 2022☆378Updated 2 years ago
- Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)☆389Updated 2 years ago
- Code for downloading and using the TAO dataset: http://taodataset.org/☆198Updated 2 months ago
- [CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion☆399Updated 4 months ago
- Multiple Object Tracking with Transformer☆644Updated last year
- [CVPR 2023] Unifying Short and Long-Term Tracking with Graph Hierarchies☆122Updated last month
- Official PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking" (CVPR 2020 Oral).☆351Updated 2 years ago
- Single object tracking and segmentation.☆491Updated 2 years ago
- Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object…☆273Updated 3 years ago
- ☆85Updated 2 years ago
- This is the official implementation of TransCenter (TPAMI). The code and pretrained models are now available here: https://gitlab.inria.…☆111Updated last year
- Implementation of "TrackFormer: Multi-Object Tracking with Transformers”. [Conference on Computer Vision and Pattern Recognition (CVPR), …☆544Updated last year
- Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral☆239Updated last year
- Track to Detect and Segment: An Online Multi-Object Tracker (CVPR 2021)☆558Updated 3 years ago
- PointTrack (ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation☆262Updated last year
- [ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer☆655Updated last year
- [CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors☆392Updated last year
- This project provides an official implementation of our recent work on real-time multi-object tracking in videos. The previous works cond…☆169Updated last year
- SiamMOT: Siamese Multi-Object Tracking☆480Updated 10 months ago
- D3S - Discriminative Single Shot Segmentation Tracker (CVPR 2020)☆267Updated 4 years ago
- [CVPR 2021] DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking☆82Updated 2 years ago
- ☆233Updated 4 years ago
- [ECCV 2020] Actions as Moving Points☆270Updated 4 years ago
- Object detection on multiple datasets with an automatically learned unified label space.☆500Updated 11 months ago
- Implementation of Tracking Every Thing in the Wild, ECCV 2022☆93Updated 4 months ago
- ☆257Updated 3 years ago
- [ECCV 2020] Codes and MultiviewX dataset for "Multiview Detection with Feature Perspective Transformation".☆175Updated 9 months ago
- ☆242Updated 2 years ago
- ☆56Updated last year
- Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight☆362Updated 2 years ago