3D-IP Group Chinese profile

RESEARCH & TEACHING

This homepage was
generated with ChatGPT.

Kao Zhang

Kao Zhang is a Lecturer and Master’s Supervisor at Nanjing University of Information Science and Technology (NUIST), where he serves as Head of the Department of Artificial Intelligence.

His research focuses on visual attention, image and video processing, remote sensing, and virtual reality. His work explores how machines can understand human attention, interpret complex visual scenes, and learn from multimodal information.

He received his Ph.D. from Wuhan University in 2020, supervised by Prof. Zhenzhong Chen. He also earned his B.Eng. (2014) and M.Eng. (2016) at Wuhan University under Prof. Jian Yao. Previously, he was a postdoctoral fellow at Wuhan University, a visiting researcher at Tencent, and a visiting student with the PERCEPT team at INRIA, Rennes.

Research group

Zhihua Hu Ming Li
JOIN US

Undergraduate and graduate students are welcome.

→

01 / RESEARCH

Research interests

From visual attention to intelligent perception

Visual attention

Saliency prediction for images, video, RGB-D, 360° content and first-person UAV video.

Visual saliency modeling

Remote sensing

Object detection, tracking and recognition in satellite, UAV and coastal surveillance imagery.

Remote sensing video analysis

Multimodal intelligence

Visual grounding, text-to-image generation, multimodal emotion recognition and virtual reality.

Multimodal understanding & generation

Datasets & benchmarks

Building datasets and evaluation protocols for visual saliency, object detection and tracking.

Datasets & evaluation benchmarks
EXPLORE THE CODENearshore detection ↗360° saliency ↗UAV saliency ↗

02 / PUBLICATIONS

Selected publications

Google Scholar ↗

Recent work and earlier contributions. * Corresponding author. Co-first authorship is noted in the publication details.

2026Remote Sensing

Visible Nearshore Object Detection in Overhead Surveillance Imagery: A Large-Scale Dataset and Benchmark

Zhibin Liu, Yongjing Jiang, Kao Zhang*, Zhihua Hu, Ming Li, Yuxuan Liu, Xin Ding, Zhenglong Ding, Zhigeng Pan.

Remote Sensing, 2026.

Project
2026TVCG

Sketch2HOI: Sketch-Based Modeling of 3D Hand-Object Interaction with Hierarchical Attentive Fusion

Cong Zhu, Yuhua Ge, Nenglun Chen, Kao Zhang, Peibei Cao, Zhigeng Pan.

IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026.

2026TMM

Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training

Xin Ding, Yun Chen, Sen Zhang, Kao Zhang, Nenglun Chen, Peibei Cao, Yongwei Wang, Fei Wu.

IEEE Transactions on Multimedia (TMM), 2026.

Code
2026Remote Sensing

Shading and Geometric Constraint Neural Radiance Field for DSM Reconstruction from Multi-View Satellite Images

Zhihua Hu, Zhiwen Chen, Yushun Li, Yuxuan Liu, Kao Zhang, Chenguang Zhao, Yongxian Zhang.

Remote Sensing, 2026.

2026CVPR

SGST-Transformer: A Spherical Geometry-Aware Spatio-Temporal Transformer for 360 Video Saliency Prediction

Kao Zhang, Tao Song, Zhihua Hu, Ming Li, Xin Ding.

Findings of IEEE CVPR, 2026.

Code
2026KSEM

SphereU-Sal360: Spherical U-shaped Spatio-Temporal Transformer for 360◦ Video Saliency

Yanzhi Ding, Kao Zhang, Zhigeng Pan, Zhihua Hu, Ming Li and Tao Song.

KSEM, 2026, (co-first author).

Code
2025TMM

CCDM: Continuous conditional diffusion models for image generation

Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang.

IEEE Transactions on Multimedia (TMM), 2025.

Code
2025Neurocomputing

Prompt-based hybrid supervised contrastive learning for emotion recognition in conversation

Chuangxin Cai, Kao Zhang, Zhihua Hu, Xianxuan Lin, Zhigeng Pan.

Neurocomputing, 2025.

2025JSTARS

Edge constrained DSM refinement based on shading from high resolution multi-view satellite images

Zhihua Hu, Kao Zhang, Yuxuan Liu.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2025.

2025JAG

Accurate room layout estimation from multi-view panoramas with multi-label graph cut

Zhihua Hu, Wanjie Lu, Kao Zhang, Helong Yang, Yaoyang Wang, Nannan Qin, Yuxuan Liu, Sisi Zlatanova.

International Journal of Applied Earth Observation and Geoinformation (JAG), 2025.

2024Neurocomputing

Video saliency prediction for first-person view UAV videos: Dataset and benchmark

Hao Cai, Kao Zhang, Zhao Chen, Chenxi Jiang, Zhenzhong Chen.

Neurocomputing, 2024. (co-first author)

2024JVCI

Audio-visual saliency prediction for movie viewing in immersive environments: Dataset and benchmarks

Zhao Chen, Kao Zhang, Hao Cai, Xiaoying Ding, Chenxi Jiang, Zhenzhong Chen.

Journal of Visual Communication and Image Representation (JVCI), 2024.

2024Sensors Journal

Attentive Fusion for Efficient Wrist-worn Gesture Recognition based on Dual-view Cameras

Pengyuan Quan, Zihao Mao, Nenglun Chen, Yang Zhang, Kao Zhang, Zhigeng Pan.

IEEE Sensors Journal, 2024.

2023JVCI

Towards Object Tracking for Quadruped Robots

Yang Li, Kao Zhang, Zhao Chen, Wanping Ouyang, Mingpeng Cui, Chenxi Jiang, Daiqin Yang and Zhenzhong Chen.

Journal of Visual Communication and Image Representation (JVCI), 2023. (co-first author)

2022ISPRS JPRS

An Efficient Saliency Prediction Model for Unmanned Aerial Vehicle Video

Kao Zhang, Zhenzhong Chen, Songnan Li, Shan Liu.

ISPRS Journal of Photogrammetry and Remote Sensing, 2022.

Code
2022VCIP

SalCrop: Spatio-temporal Saliency Based Video Cropping

Kao Zhang, Yan Shang, Songnan Li, Shan Liu, Zhenzhong Chen.

IEEE VCIP, 2022, (Demo, Oral, Poster).

Project
2021TIP

A Spatial-Temporal Recurrent Neural Network for Video Saliency Prediction

Kao Zhang, Zhenzhong Chen, Shan Liu.

IEEE Transactions on Image Processing (TIP), 2021.

Code
2021TMM

Attentive Cross-Modal Fusion Network for RGB-D Saliency Detection

Di Liu, Kao Zhang, Zhenzhong Chen.

IEEE Transactions on Multimedia (TMM), 2021.

2020JSTARS

Object Tracking in Satellite Videos Based on Convolutional Regression Network with Appearance and Motion Features

Zhaopeng Hu, Daiqin Yang, Kao Zhang, Zhenzhong Chen.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2020.

2019TCSVT

Video Saliency Prediction Based on Spatial-Temporal Two-Stream Network

Kao Zhang, Zhenzhong Chen.

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019.

Code
2019ICIP

Two-stream refinement network for RGB-D saliency detection

Di Liu, Yaosi Hu, Kao Zhang, Zhenzhong Chen.

IEEE ICIP, 2019. (Poster)

2018SPIC

A saliency prediction model on 360 degree images using color dictionary based sparse representation

Jing Ling, Kao Zhang, Yingxue Zhang, Daiqin Yang, Zhenzhong Chen.

Signal Processing: Image Communication (SPIC), 2018.

2017ACM MMAsia

Layout-Driven Top-Down Saliency Detection for Webpage

Xixi Li, Di Liu, Kao Zhang, Zhenzhong Chen.

PCM (ACM MMAsia), 2017. (Poster)

2016ISPRS Congress

S-CNN-Based Ship Detection from High-Resolution Remote Sensing Images

Ruiqian Zhang, Jian Yao, Kao Zhang, Chen Feng and Jiadong Zhang.

ISPRS Congress, 2016. (Best Poster Award).

Books2 books
2026Book

Virtual Reality Technology

Kao Zhang, Zhigeng Pan, Zhihua Hu, Feng Kong, Ming Li, Huiling Wang, Wenyan Wang (Editors-in-Chief).

Publishing House of Electronics Industry, July 2026. ISBN 9787121529672.

2024Book

Industry and Technology Roadmap for Metaverse

China Society of Image and Graphics.

China Science and Technology Press, November 2024. ISBN 9787523607367.

Kao Zhang: contributing author; responsible for compilation and organization of the volume.

03 / BACKGROUND

Experience & education

2023.03 — Present

Nanjing University of Information Science and Technology

Lecturer · School of Artificial Intelligence / School of Future Technology

2020.12 — 2023.02

Wuhan University

Postdoctoral Fellow · School of Remote Sensing and Information Engineering

2020.07 — 2020.12

Tencent, Shenzhen

Visiting Researcher · Intelligent Media Team, Media Lab, CSIG

2019.10

INRIA / IRISA, Rennes, France

Visiting Student · PERCEPT team

2010.09 — 2020.06

Wuhan University

Ph.D., Photogrammetry and Remote Sensing · 2016–2020
M.Eng., Surveying and Mapping Engineering · 2014–2016
B.Eng., Remote Sensing Science and Technology · 2010–2014

Honors & awardsView honors
  • 2026, Outstanding Collective in Teacher Ethics, NUIST; Department of Artificial Intelligence (Department Head).
  • 2025, Bronze Award, China International College Students’ Innovation Competition (Co-supervisor).
  • 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!.
  • 2016, Best Poster Award on ISPRS Congresses.
  • 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.

04 / PROJECTS & INNOVATION

Research & innovation

Research supported by the National Natural Science Foundation of China, postdoctoral research programs and industry collaborations.

Research funding12 projects

2024

  • Industry-sponsored research: ** Optical-video target detection and early-warning analysis. Principal Investigator. Dec. 2024–Nov. 2025.
  • Industry-sponsored research: ** Infrared-video target detection and early-warning analysis. Principal Investigator. Aug. 2024–July 2025.
  • NUIST Research Start-up Fund: Multi-source UAV video saliency detection. Principal Investigator; completed. Jan. 2024–Oct. 2026.

2023

  • National Social Science Fund of China, Youth Program: Strengthening strategic initiative and capabilities in preventing online ideological risks. Participant. Jan. 2024–Dec. 2026.
  • National Modern Industry College of Artificial Intelligence, industry–education integration textbook development program: Virtual Reality Technology. Principal Investigator; completed. Oct. 2023–Aug. 2025.
  • Industry-sponsored research: Image-based object detection and scene understanding for virtual reality. Principal Investigator; completed. June 2023–May 2024.

2022

  • Young Scientists Fund, National Natural Science Foundation of China: Efficient video saliency prediction based on weakly supervised learning. Principal Investigator; completed. Jan. 2023–Dec. 2025.

2021

  • China Postdoctoral Science Foundation, General Program: Key technologies for saliency prediction in remote sensing videos. Principal Investigator; completed. July 2021–Feb. 2023.
  • Hubei Postdoctoral Innovation Research Position Program: Key technologies for saliency prediction in UAV videos. Principal Investigator; completed. July 2021–Feb. 2023.
  • Exploratory Research Grant, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing: Salient object detection in remote sensing videos. Principal Investigator; completed. Jan.–Dec. 2021.

2018

  • National Key R&D Program of China, research task: Key technologies for integrated collaborative monitoring for public security. Participant. May 2018–Apr. 2021.

2017

  • National Key R&D Program of China, research task: Mechanisms and methods for human-like intelligent perception integrating multi-channel contextual information. Core team member. Oct. 2017–Sept. 2021.
Student research projects8 projects

2026

  • Jiangsu Graduate Research and Practice Innovation Program: Stereo matching with semantic information. Co-supervisor. May 2026–Apr. 2027.
  • Jiangsu Graduate Research and Practice Innovation Program: Panoramic video saliency prediction based on a spherical Transformer. Supervisor. May 2026–Apr. 2027.
  • Jiangsu Graduate Research and Practice Innovation Program: Multimodal emotion recognition through cross-modal semantic alignment and adaptive fusion. Supervisor. May 2026–Apr. 2027.
  • University-level Undergraduate Innovation and Entrepreneurship Training Program: Lightweight object detection and an edge–cloud collaborative system for UAV platforms. Supervisor. May 2026–Apr. 2027.

2025

  • Jiangsu Graduate Research and Practice Innovation Program: Attention-based audio-visual saliency prediction. Supervisor; completed. May 2025–Apr. 2026.
  • Jiangsu Undergraduate Innovation and Entrepreneurship Training Program: Multi-scale infrared ship detection based on YOLOv12. Supervisor; completed. May 2025–Apr. 2026.
  • University-level Undergraduate Innovation and Entrepreneurship Training Program: Object detection in UAV imagery. Supervisor; completed. May 2025–Apr. 2026.

2024

  • National Undergraduate Innovation and Entrepreneurship Training Program: “AI Video Highlights”—an intelligent video editing system based on visual saliency. Supervisor; completed. June 2024–May 2025.
Patents19 entries

Grouped by application year.

2026

  • Zhenglong Ding, Wenyan Wang, Xin Ding, Zheyu Shen, Kao Zhang, Zhihua Hu, Ming Li, Nenglun Chen, Feng Jiang, Junwen Zhu, Yiwen Qian. A lightweight adaptive-center method and system for multimodal sentiment analysis. Application No. CN202611149972.6. Granted.
  • Linfang Wang, Ming Li, Kao Zhang, Zhihua Hu, Xin Ding, Zhenglong Ding, Nenglun Chen, Feng Jiang. A stereo depth estimation method combining scene-structure enhancement with joint monocular and binocular optimization. Application No. CN202611126530.X. Granted.
  • Yuebing Liu, Zhihua Hu, Zhigeng Pan, Zhiwen Chen, Kao Zhang, Ming Li. Indoor layout prediction from multi-view panoramic imagery by combining semantics and planarity. Application No. CN202610253650.X. Under substantive examination.
  • Kao Zhang, Tao Song, Zhihua Hu, Ming Li, Xin Ding, Nenglun Chen, Ruiyang Huang, Feng Jiang. Spherical geometry-aware panoramic video saliency prediction and video compression. Application No. CN202610180308.1. Granted.
  • 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. Application No. CN202610167799.6. Under substantive examination.
  • 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. Application No. CN202610011013.1. Granted.

2025

  • Yutong Guo, Zhihua Hu, Yifan Zhang, Kao Zhang, Ming Li. A resolution-adaptive end-to-end method for subpixel feature matching. Application No. CN202511236228.5. Granted.
  • 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. Application No. CN202511016292.2. Granted.
  • Kao Zhang, Tao Song, Zhihua Hu, Ming Li, et al. A fast method for panoramic video saliency prediction. Application No. CN202510708582.7. Granted.
  • Helong Yang, Zhihua Hu, Kao Zhang, Ming Li, et al. A room layout estimation method, apparatus, device and storage medium based on multi-view panoramas and multi-label graph cuts. Application No. CN202510208123.2. Granted.

2024

  • Yangyang Luo, Kao Zhang, Tao Song, Zhihua Hu, et al. A video cropping method and a method for evaluating cropped-video quality. Application No. CN202411886091.3. Granted.
  • Chuangxin Cai, Zhigeng Pan, Kao Zhang, Zhihua Hu, et al. A progressive relaxation training method based on facial and body behavior perception. Application No. CN202411003151.2. Granted.
  • Chuangxin Cai, Zhigeng Pan, Kao Zhang, Zhihua Hu, et al. Emotion recognition integrating interactive conversational context and speaker identity attributes. Application No. CN202411328293.6. Granted.
  • Chuangxin Cai, Zhigeng Pan, Yu Zou, Xianxuan Lin, Xianliang Xia, Kao Zhang, et al. A multimodal conversational emotion recognition method. Application No. CN202411833608.2. Granted.
  • Changli Li, Shiyu Zhang, Xianxuan Lin, Kao Zhang, et al. A keyframe extraction method, apparatus and storage medium. Application No. CN202411314338.4. Granted.
  • Yushun Li, Zhihua Hu, Zhigeng Pan, Kao Zhang, et al. A digital terrain 3D reconstruction method, apparatus, device and storage medium based on neural radiance fields and bidirectional reflectance distribution functions. Application No. CN202411757299.5. Granted.

2023

  • Zhenzhong Chen, Yang Li, Kao Zhang. A Siamese-network-based method for object tracking with quadruped robots. Application No. CN202310399358.5. Granted.
  • Zhenzhong Chen, Zhao Chen, Kao Zhang. A method and system for video saliency prediction based on audio-visual features. Application No. CN202310247030.1. Granted.

2014

  • Jian Yao, Kao Zhang, Tong He, Sa Zhu. Accurate multi-scale license plate localization based on affine rectification. Application No. CN201410077985.8. Granted.

05 / TEACHING & MENTORING

Learning, together.

Undergraduate courses

  • Digital Image Processing
  • Neural Networks and Deep Learning
  • Machine Learning Course Design
  • Introduction to AI / Virtual Reality
  • Programming Fundamentals (C / Python)
  • Digital Twin Technology
  • AI in Everyday Life / DeepSeek and AI Large Models

Graduate courses

  • Deep Learning
  • General Education in AI
  • Frontiers of Artificial Intelligence
  • Frontiers of the Discipline

Selected courses are taught entirely in English. Students from interdisciplinary backgrounds are welcome to learn and exchange ideas.

Student destinations18 alumni · 2022–2026
Graduate alumni
ClassNameDestinationNotes
2026Zhibin LiuPh.D. studies, Beihang University—
2026Tao SongZhejiang Rural Commercial Digital Technology—
2026Bhattarai AditApplying for Ph.D. programsInternational student
2025Saidhumoyunkhon AnvarkhonovEmploymentInternational student
2024Hao CaiBaiduCo-supervised; Wuhan University
2023Zhao ChenChangjiang River Scientific Research InstituteCo-supervised; Wuhan University
2023Yang LiDEEP RoboticsCo-supervised; Wuhan University
2022Yiming ZhangZhongdaohangCo-supervised; Wuhan University
Undergraduate alumni
ClassNameDestination
2026Ye YuGraduate studies, NUIST
2026Wenpo ZhuGraduate studies, NUIST
2026Yu LiuDirect-entry Ph.D., University of Science and Technology of China
2026Jingxi HouGraduate studies, Institute of Information Engineering, Chinese Academy of Sciences
2026Liang ZhangGraduate studies, Soochow University
2026Yuchen ZhiEmployment
2025Xiaoxuan YuanGraduate studies, NUIST
2025Hao WangGraduate studies, NUIST
2025Peijia XieGraduate studies, South China Normal University
2025He YuanGraduate studies, Southwest Institute of Automation

Source: NUIST faculty profile .

06 / ACADEMIC COMMUNITY

Academic service

Journal reviewer
IEEE TIP, TMM, TCSVT, TGRS, JSTARS, GRSL; JAG, CVIU, PR, Neurocomputing
Conference reviewer
CVPR, ECCV, ACM MM, NeurIPS, ICME, ICASSP, ICIP
Editorial & community
Guest Editor, Remote Sensing
Deputy Secretary-General, Metaverse Technology and Application Innovation Platform of China, CIUR
Publicity Co-chair, ICGIP 2023–2025
Member, Integrated Research Platform for Aerospace Information Intelligent Services, Ministry of Education of China (2022–2025)

PROSPECTIVE STUDENTS

Join the group

Students interested in visual saliency, remote sensing or multimodal intelligence are welcome to contact Kao Zhang with a CV.

Email your CV

GET IN TOUCH

Contact

↑

Email

kaozhang@nuist.edu.cn

Office

Room A1911, Linjiang Building
219 Ningliu Road, Nanjing, China