Kaixiang Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kaixiang Yan has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Dongming Zhou
School of Information Science and Engineering, Yunnan University, Kunming, China
9 shared publications - Cong Bi
School of Information Science and Engineering, Yunnan University, Kunming, China
5 shared publications - Jinde Cao
School of Mathematics, Southeast University, Nanjing 210096, China
5 shared publications - Wenhua Qian
Yunnan University
4 shared publications - Changcheng Wang
School of Information and Engineering, Yunnan University, Kunming, China
3 shared publications - Yisong Liu
School of Information Science and Engineering, Yunnan University, Kunming, China
3 shared publications
Latest Publications
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Visual object tracking via integrating images of visible, thermal, and depth modalities
Multi-modal object tracking leverages the complementary attributes of different modalities, such as visible+ thermal (RGBT) or visible+depth (RGBD) data, to enhance tracking performance. However RGBT or RGBD image can not obtain reliable object features for limitations derived from dense or low-illumination scenarios, respectively. This work explores improving tracking reliability by integrating the advantages and complementarity of visible, depth, and thermal (RGBDT) data. To achieve this goal, a triple-modal object tracking dataset (VDT1k) and a triple-modal object tracking network (TOTrack) are proposed in this work. VDT1k includes 1,325 RGBDT image sequences (totaling 240k RGBDT image pairs) that cover 12 common scenarios of downtown streets. Meanwhile, 7 challenging attributes are annotated with binary labels to evaluate the detailed performance of the tested methods under these extreme scenarios. Considering the specific attributes of different modalities, TOTrack adopts asymmetric feature extraction and multi-stage feature fusion to fuse RGBDT information and complete the object tracking task. The asymmetric feature extraction treats the depth modality as a distance perception information that divides the visible and thermal images into three parts (object, background, and foreground). The multi-stage feature fusion employs different fusion strategies for the early, middle, and late fusion of visible and thermal modalities. Experimental results show that TOTrack outperforms current RGBD/RGBT methods on the test data of VDT1k. TOTrack demonstrates that integrating the complementary information of RGBDT data is a more effective approach to further improve tracking reliability and performance. Realted sources can be accessed at the link.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Visual object tracking via integrating images of visible, thermal, and depth modalities
Multi-modal object tracking leverages the complementary attributes of different modalities, such as visible+ thermal (RGBT) or visible+depth (RGBD) data, to enhance tracking performance. However RGBT or RGBD image can not obtain reliable object features for limitations derived from dense or low-illumination scenarios, respectively. This work explores improving tracking reliability by integrating the advantages and complementarity of visible, depth, and thermal (RGBDT) data. To achieve this goal, a triple-modal object tracking dataset (VDT1k) and a triple-modal object tracking network (TOTrack) are proposed in this work. VDT1k includes 1,325 RGBDT image sequences (totaling 240k RGBDT image pairs) that cover 12 common scenarios of downtown streets. Meanwhile, 7 challenging attributes are annotated with binary labels to evaluate the detailed performance of the tested methods under these extreme scenarios. Considering the specific attributes of different modalities, TOTrack adopts asymmetric feature extraction and multi-stage feature fusion to fuse RGBDT information and complete the object tracking task. The asymmetric feature extraction treats the depth modality as a distance perception information that divides the visible and thermal images into three parts (object, background, and foreground). The multi-stage feature fusion employs different fusion strategies for the early, middle, and late fusion of visible and thermal modalities. Experimental results show that TOTrack outperforms current RGBD/RGBT methods on the test data of VDT1k. TOTrack demonstrates that integrating the complementary information of RGBDT data is a more effective approach to further improve tracking reliability and performance. Realted sources can be accessed at the link.
- 18 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
UWRGBD1k: A large-scale RGBD dataset of underwater object tracking
- 18 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
UWRGBD1k: A large-scale RGBD dataset of underwater object tracking
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 1416-1425
AGVOT: Visual Object Tracking via Cooperation of Aerial and Ground Views
Visual object tracking (VOT) is a fundamental task in computer vision that underpins many higher-level tasks. Previous VOT methods have explored various approaches to improve the performance of VOT tasks and achieve predetermined goals. However, due to the limitations of a single view, issues such as visual blind spots and glitches in photographic devices present insurmountable challenges, often causing the visual features of the tracked object to vanish entirely or partially. Providing supplementary images from another view is an effective way to improve tracking performance by eliminating blind spots and enhancing the reliability of image sources. In this work, we propose a novel benchmark called the Aerial and Ground Cooperation Dataset for VOT (AGVOT). AGVOT consists of 643 sequences from aerial and ground views, comprising 119,859 image pairs. These image pairs were collected from 15 scenes and span 26 object categories. Every sequence is strictly time-aligned and annotated with 4-point bounding boxes. For comprehensive evaluation, AGVOT is further categorized into 12 challenging attributes, each labeled at the frame level. Moreover, we introduce an Aerial and Ground Cooperation Tracking Network (AGTrack) to demonstrate dual-view feature integration and cross-view tracking cooperation. Extensive experiments show that AGTrack outperforms 10 state-of-the-art (SOTA) methods in the computer vision community when tested on AGVOT’s dataset and its challenging attributes. These results demonstrate that implementing VOT tasks with cooperative views achieves more accurate and reliable tracking performance. The project source is available at the link.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 1416-1425
AGVOT: Visual Object Tracking via Cooperation of Aerial and Ground Views
Visual object tracking (VOT) is a fundamental task in computer vision that underpins many higher-level tasks. Previous VOT methods have explored various approaches to improve the performance of VOT tasks and achieve predetermined goals. However, due to the limitations of a single view, issues such as visual blind spots and glitches in photographic devices present insurmountable challenges, often causing the visual features of the tracked object to vanish entirely or partially. Providing supplementary images from another view is an effective way to improve tracking performance by eliminating blind spots and enhancing the reliability of image sources. In this work, we propose a novel benchmark called the Aerial and Ground Cooperation Dataset for VOT (AGVOT). AGVOT consists of 643 sequences from aerial and ground views, comprising 119,859 image pairs. These image pairs were collected from 15 scenes and span 26 object categories. Every sequence is strictly time-aligned and annotated with 4-point bounding boxes. For comprehensive evaluation, AGVOT is further categorized into 12 challenging attributes, each labeled at the frame level. Moreover, we introduce an Aerial and Ground Cooperation Tracking Network (AGTrack) to demonstrate dual-view feature integration and cross-view tracking cooperation. Extensive experiments show that AGTrack outperforms 10 state-of-the-art (SOTA) methods in the computer vision community when tested on AGVOT’s dataset and its challenging attributes. These results demonstrate that implementing VOT tasks with cooperative views achieves more accurate and reliable tracking performance. The project source is available at the link.
- 20 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Cross-modality masked autoencoder for infrared and visible image fusion
- 20 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Cross-modality masked autoencoder for infrared and visible image fusion
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
VT2V: A benchmark of object tracking with aerial & ground cooperation and multi-modal images
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
VT2V: A benchmark of object tracking with aerial & ground cooperation and multi-modal images
- 6 November 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 113
IHC-IS4BC: A supervised dataset for pathological image segmentation based on IHC-staining slides of breast cancer
- 6 November 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 113
IHC-IS4BC: A supervised dataset for pathological image segmentation based on IHC-staining slides of breast cancer
- 27 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108037
PathTGSeg: The pathologic image segmentation of breast cancer via template matching and graphic calculation
- 27 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108037
PathTGSeg: The pathologic image segmentation of breast cancer via template matching and graphic calculation
- 25 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
TIPTrack: Time-series information prompt network for RGBT tracking
- 25 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
TIPTrack: Time-series information prompt network for RGBT tracking
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (11) , 8374-8384
Pathological Image Segmentation of Breast Cancer via Template Matching
Accurate pathological image segmentation is crucial for the clinical diagnosis of breast cancer. However, existing methods of pathological segmentation face challenges due to the variability and complexity of breast cancer on pathological images. To address these issues, we propose a novel segmentaion network called templatematching pathological segmentation network. Our method incorporates an innovative template matching strategy inspired by the diagnostic process of pathologists. The template matching strategy is to utilize visual transformer to establish a correlative relationship between cancer lesions and corresponding templates. To improve feature utilization of pathological images, PSVTNet introduces detailed information attention and information entropy attention. Detailed information attention aims to exploit detailed information by serving as the path connecting shallow-layer and deep-layer features. Meanwhile, information entropy attention can redistribute feature weights to high-entropy regions according to the information-entropy attention map. Additionally, this work releases a comprehensive pathological dataset that comprises labeled pathological images. These images are collected from breast and stomach cancers with hematoxylin&eosin and human epidermal growth factor receptor-2 staining. Extensive experiments demonstrate that PSVTNet significantly outperforms state-of-theart methods on pathologic images of breast cancer, but can also process pathologic images of stomach cancer carrying with same diagnosed features as the breast cancer
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (11) , 8374-8384
Pathological Image Segmentation of Breast Cancer via Template Matching
Accurate pathological image segmentation is crucial for the clinical diagnosis of breast cancer. However, existing methods of pathological segmentation face challenges due to the variability and complexity of breast cancer on pathological images. To address these issues, we propose a novel segmentaion network called templatematching pathological segmentation network. Our method incorporates an innovative template matching strategy inspired by the diagnostic process of pathologists. The template matching strategy is to utilize visual transformer to establish a correlative relationship between cancer lesions and corresponding templates. To improve feature utilization of pathological images, PSVTNet introduces detailed information attention and information entropy attention. Detailed information attention aims to exploit detailed information by serving as the path connecting shallow-layer and deep-layer features. Meanwhile, information entropy attention can redistribute feature weights to high-entropy regions according to the information-entropy attention map. Additionally, this work releases a comprehensive pathological dataset that comprises labeled pathological images. These images are collected from breast and stomach cancers with hematoxylin&eosin and human epidermal growth factor receptor-2 staining. Extensive experiments demonstrate that PSVTNet significantly outperforms state-of-theart methods on pathologic images of breast cancer, but can also process pathologic images of stomach cancer carrying with same diagnosed features as the breast cancer
- 2 June 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 180
A multi-branch and multi-scale feature fusion underwater image enhancement algorithm for diverse water environments
- 2 June 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 180
A multi-branch and multi-scale feature fusion underwater image enhancement algorithm for diverse water environments