[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

A simple version for graphfpn

[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"

[CVPR 2022 Oral] Official implementation of DN-DETR

[NeurIPS 2021] You Only Look at One Sequence

Collect some papers about transformer for detection and segmentation. Awesome Detection Transformer for Computer Vision (CV)

🚀【CVPR 2024】Delving into the Trajectory Long-tail Distribution for Muti-object Tracking

Official code for NetTrack [CVPR 2024]

End-to-End Object Detection with Transformers

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

[IEEE TIP accepted] TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes

[CVPR 2024] iKUN: Speak to Trackers without Retraining

[AAAI2024]Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

[AAAI 2024] DiffusionTrack: Diffusion Model For Multi-Object Tracking. DiffusionTrack is the first work to employ the diffusion model for multi-object tracking by formulating it as a generative noi…

[NeurIPS 2023] Type-to-Track: Retrieve Any Object via Prompt-based Tracking

[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated camera parameters.

This repository is an official implementation of Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections

https://arxiv.org/abs/2302.11813

CO-MOT: Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking

Combining "segment-anything" with MOT, it create the era of "MOTS"

Official PyTorch implementation of SparseTrack

Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020