Shubo Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shubo Lin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Liang Li
Beijing Institute of Basic Medical Sciences, Beijing, China
2 shared publications - Weiming Hu
CASIA
2 shared publications Bing Li
State Key Laboratory of Multimodal Artificial Intelligence System, Institute of Automation, Chinese Academy of Science
1 shared publication- Congxuan Zhang
Nanchang Hangkong University
1 shared publication Jin Gao
State Key Laboratory of Multimodal Artificial Intelligence System, Institute of Automation, Chinese Academy of Science
1 shared publication- Jin Gao
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) CASIA
1 shared publication
Latest Publications
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1314-1322
SSTrack: Sample-interval Scheduling for Lightweight Visual Object Tracking
In recent years, CPU real-time object tracking has gained significant attention due to its broad applications such as UAV-tracking. To maintain computational efficiency, most existing CPU real-time object trackers rely on lightweight backbones and employ a single initial template image without intermediate online templates. Although the appearance variance between the template and the search is larger under this single template setting, the representation ability of lightweight backbones is weaker which poses a challenge when training lightweight object trackers. To address this issue, we propose SSTrack, a new easier-to-harder training schedule for the lightweight object tracker. From the data perspective, our method designed a success-aware sample scheduler that gradually increases difficult training samples with longer template-search time intervals and reduces the amount of the easier samples so the training cost remains unchanged. From the optimization perspective, we utilized a gradient scaling strategy that retains the original training objective of easier samples despite the reduction in their quantities. With the collective effort from both perspectives, our method achieves State-of-the-Art CPU-real-time accuracy on 5 UAV-tracking benchmarks and 5 general object tracking benchmarks. Codes and models will be available at https://github.com/Kou-99/SSTrack.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1314-1322
Open AccessSSTrack: Sample-interval Scheduling for Lightweight Visual Object Tracking
In recent years, CPU real-time object tracking has gained significant attention due to its broad applications such as UAV-tracking. To maintain computational efficiency, most existing CPU real-time object trackers rely on lightweight backbones and employ a single initial template image without intermediate online templates. Although the appearance variance between the template and the search is larger under this single template setting, the representation ability of lightweight backbones is weaker which poses a challenge when training lightweight object trackers. To address this issue, we propose SSTrack, a new easier-to-harder training schedule for the lightweight object tracker. From the data perspective, our method designed a success-aware sample scheduler that gradually increases difficult training samples with longer template-search time intervals and reduces the amount of the easier samples so the training cost remains unchanged. From the optimization perspective, we utilized a gradient scaling strategy that retains the original training objective of easier samples despite the reduction in their quantities. With the collective effort from both perspectives, our method achieves State-of-the-Art CPU-real-time accuracy on 5 UAV-tracking benchmarks and 5 general object tracking benchmarks. Codes and models will be available at https://github.com/Kou-99/SSTrack.
- Open Access
- 13 February 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 3918-3950
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training
- 13 February 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 3918-3950
Open AccessAn Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training