Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.07758 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912954178338816 |
|---|---|
| author | Yan, Teng Liu, Yihan Chen, Jiongxu Wang, Teng Li, Jiaqi Zhong, Bingzhuo |
| author_facet | Yan, Teng Liu, Yihan Chen, Jiongxu Wang, Teng Li, Jiaqi Zhong, Bingzhuo |
| contents | Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07758 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos Yan, Teng Liu, Yihan Chen, Jiongxu Wang, Teng Li, Jiaqi Zhong, Bingzhuo Computer Vision and Pattern Recognition Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating. |
| title | AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07758 |