mlsanityData to 14 Oct 2026

The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge

arXiv 2210.15281 ↗First posted 27 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present our 1st place solution to the Group Dance Multiple People Tracking Challenge. Based on MOTR: End-to-End Multiple-Object Tracking with Transformer, we explore: 1) detect queries as anchors, 2) tracking as query denoising, 3) joint training on pseudo video clips generated from CrowdHuman dataset, and 4) using the YOLOX detection proposals for the anchor initialization of detect queries. Our method achieves 73.4% HOTA on the DanceTrack test set, surpassing the second-place solution by +6.8% HOTA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 15 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

13 of 15 references.

References · 13

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  3. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  4. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  5. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  6. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  7. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  8. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  9. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  10. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 346
  11. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  12. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
1 more
  1. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133

Built on by

Not cited yet.