DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

By Pei Sun, Jinkun Cao, Yi Jiang, Zehuan Yuan, Song Bai, Kris M. Kitani, Ping Luo. Computer Vision and Pattern Recognition, 2021

422 citations recorded by the source corpus.

A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID)for object association. This pipeline is partially motivated by recent progress in both object detection and re- ID, and partially motivated by biases in existing tracking datasets, where most objects tend to have distin-guishing appearance and re-ID models are sufficient for es-tablishing associations. In response to such bias, we would like to re-emphasize that methods for multi-object tracking should also work when object appearance is not sufficiently discriminative. To this end, we propose a large-scale dataset for multi-human tracking, where humans have sim-ilar appearance, diverse motion and extreme articulation. As the dataset contains mostly group dancing videos, we name it “DanceTrack”. We expect DanceTrack to provide a better platform to develop more MOT algorithms that rely less on visual discrimination and depend more on motion analysis. We benchmark several state-of-the-art trackers on our dataset and observe a significant performance drop on DanceTrack when compared against existing benchmarks. The dataset, project code and competition is released at: https://github.com/DanceTrack.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8a349ff8222986274f302bf85c1f53a7ffafbf54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification (2023, methodology): “We conduct experiments on MOT17 [5], MOT20 [6], and DanceTrack [7].”
StrongSORT: Make DeepSORT Great Again (2022, methodology): “Camera movements exist in multiple benchmarks [31, 44, 19].”
MOTR: End-to-End Multiple-Object Tracking with TRansformer (2021, methodology): “Table 4: Performance comparison between MOTR and existing methods on the DanceTrack[28] dataset.”
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking (2022, methodology): “In this section, we provide experiments to demonstrate the efficiency of OC-SORT on multiple datasets, especially DanceTrack [59] where objects are in heavy occlusion, frequent crossover, and non-linear motion.”