Kao Zhang received the Ph.D degrees at Lab. of Intelligent Information Processing (IIP) from Wuhan University, Wuhan, China, in 2020, under the supervision of Prof.Zhenzhong Chen. Formerly, he finished the B.Eng. and M.Eng degrees at Computer Vision & Remote Sensing Lab (CVRS) in 2014 and 2016 respectively, under the guidance of Prof.Jian Yao. He is now a lecturer at Nanjing University of Information Science and Technology, Nanjing, China. He was a postdoctoral fellow at Wuhan University, working on visual saliency pridection, a researcher at Tencent, Shenzhen, working on video processing, and a visiting student at PERCEPT team of INRIA, Rennes, France working on UAV video saliency prediction. He is currently a Lecturer with the Nanjing University of Information Science and Technology, Nanjing, China. His research interests include visual attention, image/video processing, remote sensing and metaverse.

中文主页; 英文主页; 谷歌学术; GitHub

We are looking for self-motivated undergraduate/graduate students. If you are interested in joining us, please feel free to contact me with your CV!

Main research fields：

Visual attention: Video/Image/RGBD/VR/UAV saliency prediction.

Remote sensing video analysis: Object detection, tracking and recognition in satellite/UAV videos.

Metaverse: Multimodal (text, image, video, and sound) Emotion analysis, Virtual Reality technology.

Dataset and benchmark: Visual saliency dataset, Object detection and tracking dataset.

1 Selected Publications：

1.1 Visual Saliency Modeling / Image Processing / Computer Vision

[1] Yanzhi Ding*, Kao Zhang*, Zhigeng Pan, Zhihua Hu, Ming Li and Tao Song. SphereU-Sal360: Spherical U-shaped Spatio-Temporal Transformer for 360◦ Video Saliency[C].  KSEM, 2026. (CCF C，co-first author)

[2] Kao Zhang, Tao Song, Zhihua Hu, Ming Li, Xin Ding. SGST-Transformer: A Spherical Geometry-Aware Spatio-Temporal Transformer for 360 Video Saliency Prediction[C]. Findings of the IEEE CVPR, 2026. 

[3] Cong Zhu, Yuhua Ge, Nenglun Chen, Kao Zhang, Peibei Cao, Zhigeng Pan. Sketch2HOI: Sketch-Based Modeling of 3D Hand-Object Interaction with Hierarchical Attentive Fusion[J]. IEEE Transactions on Visualization and Computer Graphics (TVCG). 2026.(CCF A, SCI Q1, IF: 6.80)

[4] Xin Ding, Yun Chen, Sen Zhang, Kao Zhang, Nenglun Chen, Peibei Cao, Yongwei Wang, Fei Wu. Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training[J]. IEEE Transactions on Multimedia (TMM). 2026.(CCF A, SCI Q1, IF: 9.90)

[5] Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang. CCDM: Continuous conditional diffusion models for image generation[J]. IEEE Transactions on Multimedia (TMM). 2026.(CCF A, SCI Q1, IF: 9.90)

[6] Chuangxin Cai, Kao Zhang, Zhihua Hu, Xianxuan Lin, Zhigeng Pan. Prompt-based hybrid supervised contrastive learning for emotion recognition in conversation. Neurocomputing, 2025, 130453. (CCF C, SCI Q1, IF: 6.50)

[7] Hao Cai*, Kao Zhang*, Zhao Chen, Chenxi Jiang, Zhenzhong Chen. Video saliency prediction for first-person view UAV videos: Dataset and benchmark[J]. Neurocomputing, 2024: 127876. (CCF C, SCI Q1, IF: 6.50, co-first author)

[8] Zhao Chen, Kao Zhang, Hao Cai, Xiaoying Ding, Chenxi Jiang, Zhenzhong Chen. Audio-visual saliency prediction for movie viewing in immersive environments: Dataset and benchmarks[J]. Journal of Visual Communication and Image Representation (JVCIR), 2024: 104095. (CCF C, SCI Q2, IF: 3.1)

[9] Kao Zhang, Yan Shang, Songnan Li, Shan Liu, Zhenzhong Chen. SalCrop: Spatio-temporal Saliency Based Video Cropping[C]. IEEE VCIP, 2022. (Demo, Oral, Poster, EI)

[10] Kao Zhang, Zhenzhong Chen, Shan Liu. A Spatial-temporal Recurrent Neural Network for Video Saliency Prediction[J]. IEEE Transactions on Image Processing (TIP), 2021, 30: 572-587. (CCF A, SCI Q1, IF: 11.041)

[11] Di Liu, Kao Zhang, Zhenzhong Chen. Attentive Cross-Modal Fusion Network for RGB-D Saliency Detection[J]. IEEE Transactions on Multimedia (TMM), 2021, 23: 967-981. (CCF A, SCI Q1, IF: 8.182)

[12] Kao Zhang, Zhenzhong Chen. Video Saliency Prediction Based on Spatial-Temporal Two-Stream Network[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019, 29(12): 3544-3557. (CCF B, SCI Q1, IF: 4.133)

[13] Jing Ling, Kao Zhang, Yingxue Zhang, Daiqin Yang, Zhenzhong Chen. A saliency prediction model on 360 degree images using color dictionary based sparse representation[J]. Signal Processing: Image Communication (SPIC), 2018, 69: 60-68. (CCF C, SCI Q2, IF: 2.779)

1.2 Remote Sensing Information Processing

[1] Zhibin Liu, Yongjing Jiang, Kao Zhang*, Zhihua Hu, Ming Li, Yuxuan Liu, Xin Ding, Zhenglong Ding, Zhigeng Pan. Visible Nearshore Object Detection in Overhead Surveillance Imagery: A Large-Scale Dataset and Benchmark[J]. Remote Sensing, 2026, 18(17), 2982. (SCI Q1, IF: 4.3)

[2] Zhihua Hu, Kao Zhang, Yuxuan Liu. Edge constrained DSM refinement based on shading from high resolution multi-view satellite images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2025. (SCI Q1, IF: 5.3)

[3] Zhihua Hu, Wanjie Lu, Kao Zhang, Helong Yang, Yaoyang Wang, Nannan Qin, Yuxuan Liu, Sisi Zlatanova. Accurate room layout estimation from multi-view panoramas with multi-label graph cut[J]. International Journal of Applied Earth Observation and Geoinformation (JAG), 2025. (SCI Q1, IF: 8.6)

[4] Yang Li*, Kao Zhang*, Zhao Chen, Wanping Ouyang, Mingpeng Cui, Chenxi Jiang, Daiqin Yang and Zhenzhong Chen. Towards Object Tracking for Quadruped Robots[J]. Journal of Visual Communication and Image Representation (JVCIR), 2023, 97: 103958. (CCF C, SCI Q2, IF: 2.6, co-first author)

[5] Kao Zhang, Zhenzhong Chen, Songnan Li, Shan Liu. An Efficient Saliency Prediction Model for Unmanned Aerial Vehicle Video[J]. ISPRS Journal of Photogrammetry and Remote Sensing (ISPRS JPRS), 2022, 194: 152-166. (SCI Q1, IF: 12.7)

[6] Zhaopeng Hu, Daiqin Yang, Kao Zhang, Zhenzhong Chen. Object Tracking in Satellite Videos Based on Convolutional Regression Network with Appearance and Motion Features[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2020, 13: 783-793. (SCI Q1, IF: 3.827)

[7] Ruiqian Zhang, Jian Yao, Kao Zhang, Chen Feng and Jiadong Zhang. S-CNN-Based Ship Detection from High-Resolution Remote Sensing Images[C]. ISPRS Congress, 2016. (Best Poster Award, EI).

[8] Tong He, Jian Yao, Kao Zhang, Yaolin Hou, Shiyao Han. Accurate Multi-Scale License Plate Localization Via Image Saliency[C]. IEEE ITSC, 2014. (Oral, EI).

1.3 Metaverse/ VR (Book)

[1] Industry and Technology Roadmap for Metaverse. China Society of Image and Graphics, ISBN：9787523607367, 2024.11.(Responsible for the organization and compilation of the book)

[2] Virtual Reality Technology. Publishing House of Electronics Industry, ISBN 9787121529672, 2026.07. (Editors-in-Chief).

2 Patent (Translated by AI)

[1] Zhenglong Ding, Wenyan Wang, Xin Ding, Zheyu Shen, Kao Zhang, Zhihua Hu, Ming Li, Nenglun Chen, Feng Jiang, Junwen Zhu, Yiwen Qian. A Multimodal Sentiment Analysis Method and System Based on Lightweight Adaptive Centers. Chinese Patent Application No. CN202611149972.6. (Granted; Project Lead)

[2] Linfang Wang, Ming Li, Kao Zhang, Zhihua Hu, Xin Ding, Zhenglong Ding, Nenglun Chen, Feng Jiang. A Stereo Depth Estimation Method Based on Scene Structural Information Enhancement and Joint Monocular–Stereo Optimization. Chinese Patent Application No. CN202611126530.X. (Granted)

[3] Yuebing Liu, Zhihua Hu, Zhigeng Pan, Zhiwen Chen, Kao Zhang, Ming Li. An Indoor Layout Prediction Method for Multi-View Panoramic Images Integrating Semantic and Planarity Information. Chinese Patent Application No. CN202610253650.X. (Under Substantive Examination)

[4] Kao Zhang, Tao Song, Zhihua Hu, Ming Li, Xin Ding, Nenglun Chen, Ruiyang Huang, Feng Jiang. A Panoramic Video Saliency Prediction Method and Video Compression Method Based on Spherical Geometry Awareness. Chinese Patent Application No. CN202610180308.1. (Granted)

[5] Kao Zhang, Ruiyang Huang, Zhihua Hu, Ming Li, Xin Ding, Nenglun Chen, Tao Song, Feng Jiang. A UAV Video Saliency Prediction Method and Intelligent Visualization System Based on Multi-Scale Attention Fusion. Chinese Patent Application No. CN202610167799.6. (Under Substantive Examination)

[6] Yanzhi Ding, Kao Zhang, Zhigeng Pan, Zhihua Hu, Ming Li, Tao Song, Xin Ding, Nenglun Chen. A Viewport Preloading Method, System, and Device Based on Panoramic Video Saliency Prediction. Chinese Patent Application No. CN202610011013.1. (Granted)

[7] Yutong Guo, Zhihua Hu, Yifan Zhang, Kao Zhang, Ming Li. A Resolution-Adaptive End-to-End Subpixel-Level Feature Matching Method. Chinese Patent Application No. CN202511236228.5. (Granted)

[8] Kao Zhang, Zhibin Liu, Zhigeng Pan, Zhihua Hu, et al. An Early Warning and Storage Method, System, Device, and Medium Based on Infrared Video Surveillance. Chinese Patent Application No. CN202511016292.2. (Granted)

[9] Kao Zhang, Tao Song, Zhihua Hu, Ming Li, et al. A Fast Panoramic Video Saliency Prediction Method. Chinese Patent Application No. CN202510708582.7. (Granted)

[10] Helong Yang, Zhihua Hu, Kao Zhang, Ming Li, et al. A Room Spatial Layout Estimation Method, Apparatus, Device, and Storage Medium Based on Multi-View Panoramas and Multi-Label Graph Cuts. Chinese Patent Application No. CN202510208123.2. (Granted)

[11] Yangyang Luo, Kao Zhang, Tao Song, Zhihua Hu, et al. A Video Cropping Method and a Quality Evaluation Method for Cropped Videos. Chinese Patent Application No. CN202411886091.3. (Granted)

[12] Chuangxin Cai, Zhigeng Pan, Kao Zhang, Zhihua Hu, et al. A Progressive Relaxation Training Method Based on Facial and Postural Behavior Perception. Chinese Patent Application No. CN202411003151.2. (Granted)

[13] Chuangxin Cai, Zhigeng Pan, Kao Zhang, Zhihua Hu, et al. An Emotion Recognition Method Integrating Interactive Conversational Context and Speaker Identity Attributes. Chinese Patent Application No. CN202411328293.6. (Granted)

[14] Chuangxin Cai, Zhigeng Pan, Yu Zou, Xianxuan Lin, Xianliang Xia, Kao Zhang, et al. A Multimodal Conversational Emotion Recognition Method. Chinese Patent Application No. CN202411833608.2. (Granted)

[15] Changli Li, Shiyu Zhang, Xianxuan Lin, Kao Zhang, et al. A Keyframe Extraction Method, Apparatus, and Storage Medium. Chinese Patent Application No. CN202411314338.4. (Granted)

[16] Yushun Li, Zhihua Hu, Zhigeng Pan, Kao Zhang, et al. A 3D Digital Ground Surface Reconstruction Method, Apparatus, Device, and Storage Medium Based on Neural Radiance Fields and Bidirectional Reflectance Distribution Functions. Chinese Patent Application No. CN202411757299.5. (Granted)

[17] Jian Yao, Kao Zhang, Tong He, Sa Zhu. An Accurate Multi-Scale License Plate Localization Method Based on Affine Correction. Chinese Patent Application No. CN201410077985.8. (Granted)

[18] Zhenzhong Chen, Yang Li, Kao Zhang. An Object Tracking Method for Quadruped Robots Based on Siamese Networks. Chinese Patent Application No. CN202310399358.5. (Granted)

[19] Zhenzhong Chen, Zhao Chen, Kao Zhang. A Video Saliency Prediction Method and System Based on Audio-Visual Features. Chinese Patent Application No. CN202310247030.1. (Granted)

3 Funding (Translated by AI)

3.1 Principal Investigator

[1] Industry-Commissioned Research Project, Detection and Early Warning Analysis of Typical Targets in Infrared Videos. (PI, Ongoing), Aug. 2024 – Jul. 2025.

[2] Industry-Commissioned Research Project, Detection and Early Warning Analysis of Typical Targets in Optical Videos. (PI, Ongoing), Dec. 2024 – Nov. 2025.

[3] National Natural Science Foundation of China (NSFC), Young Scientists Fund, Research on Efficient Video Saliency Prediction Methods Based on Weakly Supervised Learning. (PI, Completed), Jan. 2023 – Dec. 2025.

[4] National-Level Modern Industrial College of Artificial Intelligence, Industry–Education Integration Textbook Development Project, Virtual Reality Technology. (PI, Ongoing), Oct. 2023 – Aug. 2025.

[5] Research Start-up Fund of Nanjing University of Information Science and Technology, Saliency Detection in Multi-Source UAV Videos. (PI, Ongoing), Mar. 2024 – Oct. 2026.

[6] Industry-Commissioned Research Project, Research on Object Detection and Scene Understanding Technologies for Virtual Reality Images. (PI, Completed), Jun. 2023 – May 2024.

[7] China Postdoctoral Science Foundation, General Program, Research on Key Technologies for Saliency Prediction in Remote Sensing Videos. (PI, Completed), Jul. 2021 – Feb. 2023.

[8] Hubei Provincial Postdoctoral Innovative Research Program, Research on Key Technologies for UAV Video Saliency Prediction. (PI, Completed), Jul. 2021 – Feb. 2023.

[9] State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Exploratory Research Project, Salient Object Detection in Remote Sensing Videos. (PI, Completed), Jan. 2021 – Dec. 2021.

3.2 Participant/Collaborator

[1] National Social Science Fund of China, Youth Project, Research on Enhancing Strategic Initiative and Capabilities for Preventing Ideological Risks in Cyberspace. (Participant, Ongoing), Jan. 2024 – Dec. 2026.

[2] National Key Research and Development Program of China, Key Technologies for Multi-Dimensional Collaborative Monitoring of Public Safety. (Participant, Completed), May 2018 – Apr. 2021.

[3] National Key Research and Development Program of China, Human-Like Intelligent Perception Mechanisms and Methods Integrating Multi-Channel Contextual Information. (Key Research Member, Completed), Oct. 2017 – Sep. 2021.

[4] National Natural Science Foundation of China (NSFC), Key Program, Research on Vision-Inspired Machine Learning Methods for Remote Sensing Imagery. (Participant), Jan. 2021 – Dec. 2025.

[5] National Natural Science Foundation of China (NSFC), General Program, Visual Perception Analysis and Video Coding Optimization Based on Visual Characteristics. (Participant, Completed), Jan. 2018 – Dec. 2021.

[6] National Natural Science Foundation of China (NSFC), General Program, Research on Efficient Video Coding Based on Global Visual Redundancy Analysis. (Participant, Completed), Jan. 2015 – Dec. 2018.

3.3 Student Project Supervision/Mentorship

[1] 2026 Jiangsu Provincial Postgraduate Research and Practice Innovation Program, Research on Stereo Matching Algorithms Integrating Semantic Information. (Co-supervisor; Total Funding: CNY 15,000), May 2026 – Apr. 2027.

[2] 2026 Jiangsu Provincial Postgraduate Research and Practice Innovation Program, Research on Panoramic Video Saliency Prediction Based on Spherical Transformers. (Supervisor; Total Funding: CNY 15,000), May 2026 – Apr. 2027.

[3] 2026 Jiangsu Provincial Postgraduate Research and Practice Innovation Program, Research on Multimodal Emotion Recognition Based on Cross-Modal Semantic Alignment and Adaptive Fusion. (Supervisor; Total Funding: CNY 15,000), May 2026 – Apr. 2027.

[4] 2026 University-Level Undergraduate Innovation and Entrepreneurship Training Program, Research on Lightweight Object Detection Algorithms and Edge–Cloud Collaborative Systems for UAV Platforms. (Supervisor; Total Funding: CNY 500), May 2026 – Apr. 2027.

[5] 2025 Jiangsu Provincial Postgraduate Research and Practice Innovation Program, Research on Audio-Visual Saliency Prediction Based on Attention Mechanisms. (Supervisor, Completed; Total Funding: CNY 15,000), May 2025 – Apr. 2026.

[6] 2025 Jiangsu Provincial Undergraduate Innovation and Entrepreneurship Training Program, A Multi-Scale Infrared Ship Detection Algorithm Based on YOLOv12. (Supervisor, Completed; Total Funding: CNY 2,500), May 2025 – Apr. 2026.

[7] 2025 University-Level Undergraduate Innovation and Entrepreneurship Training Program, Research on Object Detection in UAV Imagery. (Supervisor, Completed; Total Funding: CNY 500), May 2025 – Apr. 2026.

[8] 2024 National Undergraduate Innovation and Entrepreneurship Training Program, "AI Video Highlights": An Intelligent Video Editing System Based on Visual Saliency. (Supervisor, Completed; Total Funding: CNY 9,000), Jun. 2024 – May 2025.

4 Selected Awards (Translated by AI)

2025, Outstanding Class Teacher Award, NUIST.

2024, Outstanding Faculty Member Award, NUIST.

2021, Second-Class Prize of Graduate Academic Innovation Award, Wuhan University.

2018, Grand Winner Prize on Images in ICME2018 Grand Challenge (GC) – Salient360!.

2018, 1st place on track: Prediction of Head Saliency for Images in ICME2018 GC–Salient360!.

2018, 1st place on track: Prediction of Head+Eye Saliency for Videos in ICME2018 GC–Salient360!.

2017, Best Head Movement Prediction Student Prize in ICME2017 GC–Salient360!.

2014, Second-Class Prize of the National Graduate Contest on Smart-City Technology and Creative Design, Video Challenge--Face Detection Section.

2014, Excellent Bachelor’s Degree Thesis of Hubei Province.

2014-2016, Excellent Graduate Students of Wuhan University.

2010-2012, Excellent Undergraduate Students of Wuhan University.

2014-2016, First Class Scholarship of Wuhan University.

5 Teaching

5.1 Undergraduate Courses

Digital Image Processing; Digital Twin Technology (Laboratory Sessions)

Neural Networks and Deep Learning (Chinese and English); Machine Learning Course Design (English-Taught)

Introduction to Artificial Intelligence (English-Taught); Introduction to Virtual Reality (Laboratory Sessions)

Fundamentals of Programming (C Language); Fundamentals of Programming (Python)

Artificial Intelligence in Everyday Life (University-Wide General Education Elective); DeepSeek and AI Large Language Models (University-Wide General Education Elective)

5.2 Graduate Courses

Deep Learning

General Introduction to Artificial Intelligence

Frontiers of Artificial Intelligence

Frontiers of the Discipline