Bo Ke
Research Subjects
Bo Ke has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ruizhi Qiao
Tencent Youtu Lab
3 shared publications - Bo Ren
Tencent Youtu Lab
2 shared publications - Mengtian Li
East China Normal University
1 shared publication - Wei Wen
Beijing National Laboratory for Molecular Sciences, Key Laboratory of Organic Solids, Institute of Chemistry, Chinese Academy of Sciences, Beijing, PR China
1 shared publication - Xing Sun
Tencent Youtu Lab, Shanghai, China
1 shared publication - Xiujun Shu
Peng Cheng Laboratory, Shenzhen, China
1 shared publication
Latest Publications
- 30 January 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (7) , 2443-2449
Multi-dataset Detection with Transformers
- 30 January 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (7) , 2443-2449
Multi-dataset Detection with Transformers
- 20 October 2022
- Published by Springer Nature
- p. 38-55
Hyperspherical Learning in Multi-Label Classification
- 20 October 2022
- Published by Springer Nature
- p. 38-55
Hyperspherical Learning in Multi-Label Classification
- Open Access
Head and Body: Unified Detector and Graph Network for Person Search in Media
Person search in media has seen increasing potential in Internet applications, such as video clipping and character collection. This task is common but overlooked by previous person search works which focus on surveillance scenes. The media scenarios have some different challenges from surveillance scenes. For example, a person may change his clothes frequently. To alleviate this issue, this paper proposes a Unified Detector and Graph Network (UDGNet) for person search in media. UDGNet is the first person search framework to detect and re-identify the human body and head simultaneously. Specifically, it first builds two branches based on a unified network to detect the human body and head, then the detected body and head are used for re-identification. This dual-task approach can significantly enhance discriminative learning. To tackle the cloth-changing issue, UDGNet builds two graphs to explore reliable links among cloth-changing samples and utilizes a graph network to learn better embeddings. This design effectively enhances the robustness of person search to cloth-changing challenges. Besides, we demonstrate that UDGNet can be implemented with both anchor-based and anchor-free person search frameworks and further achieve performance improvement. This paper also contributes a large-scale dataset for Person Search in Media (PSM), which provides both body and head annotations. It is by far the largest dataset for person search in media. Experiments show that UDGNet improves the anchor-free model AlignPS by 12.1% in mAP. Meanwhile, it shows good generalization across surveillance and longterm scenarios. The dataset and code will be available at: https://github.com/shuxjweb/PSM.git.
Open AccessHead and Body: Unified Detector and Graph Network for Person Search in Media
Person search in media has seen increasing potential in Internet applications, such as video clipping and character collection. This task is common but overlooked by previous person search works which focus on surveillance scenes. The media scenarios have some different challenges from surveillance scenes. For example, a person may change his clothes frequently. To alleviate this issue, this paper proposes a Unified Detector and Graph Network (UDGNet) for person search in media. UDGNet is the first person search framework to detect and re-identify the human body and head simultaneously. Specifically, it first builds two branches based on a unified network to detect the human body and head, then the detected body and head are used for re-identification. This dual-task approach can significantly enhance discriminative learning. To tackle the cloth-changing issue, UDGNet builds two graphs to explore reliable links among cloth-changing samples and utilizes a graph network to learn better embeddings. This design effectively enhances the robustness of person search to cloth-changing challenges. Besides, we demonstrate that UDGNet can be implemented with both anchor-based and anchor-free person search frameworks and further achieve performance improvement. This paper also contributes a large-scale dataset for Person Search in Media (PSM), which provides both body and head annotations. It is by far the largest dataset for person search in media. Experiments show that UDGNet improves the anchor-free model AlignPS by 12.1% in mAP. Meanwhile, it shows good generalization across surveillance and longterm scenarios. The dataset and code will be available at: https://github.com/shuxjweb/PSM.git.