File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Dancetrack: Multi-object tracking in uniform appearance and diverse motion
Title | Dancetrack: Multi-object tracking in uniform appearance and diverse motion |
---|---|
Authors | |
Issue Date | 2022 |
Publisher | IEEE Computer Society. |
Citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, New Orleans, Louisiana, USA, 19-24 June, 2022. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, p. 20993-21002 How to Cite? |
Abstract | 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 distinguishing appearance and re-ID models are sufficient for establishing 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 similar 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. |
Persistent Identifier | http://hdl.handle.net/10722/315858 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | SUN, P | - |
dc.contributor.author | JIANG, Y | - |
dc.contributor.author | YUAN, Z | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2022-08-19T09:05:43Z | - |
dc.date.available | 2022-08-19T09:05:43Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, New Orleans, Louisiana, USA, 19-24 June, 2022. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, p. 20993-21002 | - |
dc.identifier.uri | http://hdl.handle.net/10722/315858 | - |
dc.description.abstract | 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 distinguishing appearance and re-ID models are sufficient for establishing 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 similar 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. | - |
dc.language | eng | - |
dc.publisher | IEEE Computer Society. | - |
dc.relation.ispartof | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 | - |
dc.rights | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Copyright © IEEE Computer Society. | - |
dc.title | Dancetrack: Multi-object tracking in uniform appearance and diverse motion | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.hkuros | 335575 | - |
dc.identifier.spage | 20993 | - |
dc.identifier.epage | 21002 | - |
dc.publisher.place | United States | - |