Xin Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xin Zhao has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Kaiqi Huang
University of Chinese Academy of Sciences
17 shared publications - Shiyu Hu
Nanyang Technological University
16 shared publications - Xu-Cheng Yin
University of Science and Technology Beijing, Beijing, China
10 shared publications - Yin Li
University of Wisconsin–Madison
5 shared publications - Lianghua Huang
Wan Team, Alibaba Group, Beijing, China
3 shared publications - Naiyu Gao
Center for Research on Intelligent System and Engineering (CRISE), Institute of Automation, the Chinese Academy of Sciences (CASIA), Beijing, China
3 shared publications
Latest Publications
- 18 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 123
B$^{3}$CT: Three-Branch Learning with Unlabeled Target Signals for Domain-Robust Semantic Segmentation- 18 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 123
B$^{3}$CT: Three-Branch Learning with Unlabeled Target Signals for Domain-Robust Semantic Segmentation- Open Access
Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking
Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking
Open AccessDecoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking
Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking
- Open Access
- 26 December 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (1) , 19
Guest Editorial: Special Issue on Visual Datasets
- 26 December 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (1) , 19
Open AccessGuest Editorial: Special Issue on Visual Datasets
- 2 July 2025
- Published by Springer Nature
- p. 159-175
More Realistic Data Environment
- 2 July 2025
- Published by Springer Nature
- p. 191-199
More Intelligent Evaluation
- 2 July 2025
- Published by Springer Nature
- p. 177-189
More Human-Like Executors
- 2 July 2025
- Published by Springer Nature
- p. 25-52
Experimental Environment
- 2 July 2025
- Published by Springer Nature
- p. 147-157
More Human-Like Task Design