Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915852538871808 |
|---|---|
| author | Li, Weize Du, Yunhao Yin, Qixiang Zhao, Zhicheng Su, Fei |
| author_facet | Li, Weize Du, Yunhao Yin, Qixiang Zhao, Zhicheng Su, Fei |
| contents | Referring Multi-Object Tracking (RMOT) aims to track multiple objects specified by natural language expressions in videos. With the recent significant progress of one-stage methods, the two-stage Referring-by-Tracking (RBT) paradigm has gradually lost its popularity. However, its lower training cost and flexible incremental deployment remain irreplaceable. Rethinking existing two-stage RBT frameworks, we identify two fundamental limitations: the overly heuristic feature construction and fragile correspondence modeling. To address these issues, we propose FlexHook, a novel two-stage RBT framework. In FlexHook, the proposed Conditioning Hook (C-Hook) redefines the feature construction by a sampling-based strategy and language-conditioned cue injection. Then, we introduce a Pairwise Correspondence Decoder (PCD) that replaces CLIP-based similarity matching with active correspondence modeling, yielding a more flexible and robust strategy. Extensive experiments on multiple benchmarks (Refer-KITTI/v2, Refer-Dance, and LaMOT) demonstrate that FlexHook becomes the first two-stage RBT approach to comprehensively outperform current state-of-the-art methods. Code can be found in the https://github.com/buptLwz/FlexHook. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07516 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again Li, Weize Du, Yunhao Yin, Qixiang Zhao, Zhicheng Su, Fei Computer Vision and Pattern Recognition Referring Multi-Object Tracking (RMOT) aims to track multiple objects specified by natural language expressions in videos. With the recent significant progress of one-stage methods, the two-stage Referring-by-Tracking (RBT) paradigm has gradually lost its popularity. However, its lower training cost and flexible incremental deployment remain irreplaceable. Rethinking existing two-stage RBT frameworks, we identify two fundamental limitations: the overly heuristic feature construction and fragile correspondence modeling. To address these issues, we propose FlexHook, a novel two-stage RBT framework. In FlexHook, the proposed Conditioning Hook (C-Hook) redefines the feature construction by a sampling-based strategy and language-conditioned cue injection. Then, we introduce a Pairwise Correspondence Decoder (PCD) that replaces CLIP-based similarity matching with active correspondence modeling, yielding a more flexible and robust strategy. Extensive experiments on multiple benchmarks (Refer-KITTI/v2, Refer-Dance, and LaMOT) demonstrate that FlexHook becomes the first two-stage RBT approach to comprehensively outperform current state-of-the-art methods. Code can be found in the https://github.com/buptLwz/FlexHook. |
| title | Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.07516 |