Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer
| Date | Stars |
|---|---|
| 2026-07-30 | 809 |
| 2026-08-07 | 810 |
| 2026-08-15 | 809 |
| 2026-08-20 | 810 |
| 2026-08-21 | 809 |
| 2026-09-03 | 810 |
| 2026-09-10 | 811 |
| 2026-09-20 | 810 |
| 2026-09-30 | 811 |
| 2026-10-04 | 812 |
| 2026-10-05 | 811 |
| 2026-10-08 | 812 |
| 2026-10-16 | 811 |
| 2026-10-24 | 812 |
| 2026-10-29 | 813 |
| 2026-11-04 | 813 |
Today
— stars today
This week
+1 stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.12%/day
# MOTR: End-to-End Multiple-Object Tracking with TRansformer </div> [](https://paperswithcode.com/sota/multi-object-tracking-on-mot17?p=motr-end-to-end-multiple-object-tracking-with) [](https://paperswithcode.com/sota/multi-object-tracking-on-mot16?p=motr-end-to-end-multiple-object-tracking-with) </div> This repository is an official implementation of the paper [MOTR: End-to-End Multiple-Object Tracking with TRansformer](https://arxiv.org/pdf/2105.03247.pdf). ## Introduction **TL; DR.** MOTR is a fully end-to-end multiple-object tracking framework based on Transformer. It directly outputs the tracks within the video sequences without any association procedures. <div style="align: center"> <img src=./figs/motr.png/> </div> **Abstract.** The key challenge in multiple-object tracking task is temporal modeling of the object under track. Existing tracking-by-detection methods adopt simple heuristics, such as spatial or appearance similarity. Such methods, in spite of their commonality, are overly simple and lack the ability to learn temporal variations from data in an end-to-end manner.In this paper, we present MOTR, a fully end-to-end multiple-object tracking framework. It learns to model the long-range temporal variation of the objects. It performs temporal association implicitly and avoids previous explicit heuristics. Built upon DETR, MOTR introduces the concept of "track query". Each track query models the entire track of an object. It is transferred and updated frame-by-frame to perform iterative predictions in a seamless manner. Tracklet-aware label assignment is proposed for one-to-one assignment between track queries and object tracks. Temporal aggregation network together with collective average loss is further proposed to enhance the long-range temporal relation. Experimental results show that MOTR achieves competitive performance and can serve as a strong Transformer-based baseline for future research. ## Updates - (2021/09/23) Report BDD100K results and release corresponding codes [motr_bdd100k](https://github.com/megvii-model/MOTR/tree/motr_bdd100k). - (2022/02/09) Higher performance achieved by not clipping the bounding boxes inside the image. - (2022/02/11) Add checkpoint support for training on RTX 2080ti. - (2022/02/11) Report [DanceTrack](https://github.com/DanceTrack/DanceTrack) results and [scripts](configs/r50_motr_train_dance.sh). - (2022/05/12) Higher performance achieved by removing the public detection filtering (filter_pub_det) trick. - (2022/07/04) MOTR is accepted by ECCV 2022. ## Main Results ### MOT17 | **Method** | **Dataset** | **Train Data** | **HOTA** | **DetA** | **AssA** | **MOTA** | **IDF1** | **IDS** | **URL** | | :--------: | :---------: | :------------------: | :------: | :------: | :------: | :------: | :------: | :-----: | :-----------------------------------------------------------------------------------------: | | MOTR | MOT17 | MOT17+CrowdHuman Val | 57.8 | 60.3 | 55.7 | 73.4 | 68.6 | 2439 | [model](https://drive.google.com/file/d/1K9AbtzTCBNsOD8LYA1k16kf4X0uJi8PC/view?usp=sharing) | ### DanceTrack | **Method** | **Dataset** | **Train Data** | **HOTA** | **DetA** | **AssA** | **MOTA** | **IDF1** | **URL** | | :--------: | :---------: | :------------: | :------: | :------: | :------: | :------: | :------: | :-----------------------------------------------------------------------------------------: | | MOTR | DanceTrack | DanceTrack | 54.2 |
Excerpt of 8,824 characters
Read on GitHub
23
6
4
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6f2db243f67cf1b3, topic:pytorch
matched fp:6f2db243f67cf1b3, topic:transformer