Multi-Object Tracking by Hierarchical Visual Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929256484831232 |
|---|---|
| author | Cao, Jinkun Pang, Jiangmiao Kitani, Kris |
| author_facet | Cao, Jinkun Pang, Jiangmiao Kitani, Kris |
| contents | We propose a new visual hierarchical representation paradigm for multi-object tracking. It is more effective to discriminate between objects by attending to objects' compositional visual regions and contrasting with the background contextual information instead of sticking to only the semantic visual cue such as bounding boxes. This compositional-semantic-contextual hierarchy is flexible to be integrated in different appearance-based multi-object tracking methods. We also propose an attention-based visual feature module to fuse the hierarchical visual representations. The proposed method achieves state-of-the-art accuracy and time efficiency among query-based methods on multiple multi-object tracking benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15895 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Object Tracking by Hierarchical Visual Representations Cao, Jinkun Pang, Jiangmiao Kitani, Kris Computer Vision and Pattern Recognition We propose a new visual hierarchical representation paradigm for multi-object tracking. It is more effective to discriminate between objects by attending to objects' compositional visual regions and contrasting with the background contextual information instead of sticking to only the semantic visual cue such as bounding boxes. This compositional-semantic-contextual hierarchy is flexible to be integrated in different appearance-based multi-object tracking methods. We also propose an attention-based visual feature module to fuse the hierarchical visual representations. The proposed method achieves state-of-the-art accuracy and time efficiency among query-based methods on multiple multi-object tracking benchmarks. |
| title | Multi-Object Tracking by Hierarchical Visual Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.15895 |