Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.13183 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909402893647872 |
|---|---|
| author | Wang, Kuiran Yu, Xuehui Yu, Wenwen Li, Guorong Lan, Xiangyuan Ye, Qixiang Jiao, Jianbin Han, Zhenjun |
| author_facet | Wang, Kuiran Yu, Xuehui Yu, Wenwen Li, Guorong Lan, Xiangyuan Ye, Qixiang Jiao, Jianbin Han, Zhenjun |
| contents | Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single object trackers and propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. Moreover, click as an input type inherently lack hierarchical information. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs, transforming the point into the bounding box expected by the operator. The bounding box will be used as input of single object trackers. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios. Furthermore, we explored the integration of GCR into the Segment Anything model(SAM), significantly reducing ambiguity issues when SAM receives point inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13183 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ClickTrack: Towards Real-time Interactive Single Object Tracking Wang, Kuiran Yu, Xuehui Yu, Wenwen Li, Guorong Lan, Xiangyuan Ye, Qixiang Jiao, Jianbin Han, Zhenjun Computer Vision and Pattern Recognition Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single object trackers and propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. Moreover, click as an input type inherently lack hierarchical information. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs, transforming the point into the bounding box expected by the operator. The bounding box will be used as input of single object trackers. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios. Furthermore, we explored the integration of GCR into the Segment Anything model(SAM), significantly reducing ambiguity issues when SAM receives point inputs. |
| title | ClickTrack: Towards Real-time Interactive Single Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.13183 |