Sponsors
Detailed Programme
|
Day 1 — Tuesday, June 16, 2026 |
|
|
09:00 – 12:15 |
Tutorial Session (Long #1) |
|
|
Title: From Static Representations to Animated (Digital) Humans: Motion Signals, Animation Streams, and Quality Assessment |
|
|
Presenters: Anthony Trioux (Xidian University); Giuseppe Valenzise (Université Paris-Saclay); Shiqi Wang (City University of Hong Kong) |
|
12:15 – 13:00 |
Lunch Break |
|
13:00 – 14:30 |
Tutorial Session (Short #1) |
|
|
Title: Perceptual Visual Signal Processing: Quality Assessment, Modeling, and Applications |
|
|
Presenters: Patrick Le Callet (Nantes Université); Wei Zhou (Cardiff University) |
|
14:30 – 14:45 |
Coffee Break |
|
14:45 – 18:00 |
Tutorial Session (Long #2) |
|
|
Title: Neural Spatial Computing: Geometric Modeling, Representation Learning, and 3D Compression |
|
|
Presenter: Junhui Hou (City University of Hong Kong) |
|
18:00 – 21:00 |
Welcome Reception |
|
|
|
|
Day 2 — Wednesday, June 17, 2026 |
|
|
08:30 - 09:00 |
Opening Ceremony |
|
09:00 - 10:00 |
Plenary Talk 1 |
|
|
Speaker: Zhengyou Zhang (Director of the AI Laboratory and Robotics X, Tencent) |
|
|
Title: Physical Agent: The Next Wave of Artificial Intelligence |
|
10:00 - 10:15 |
Coffee Break |
|
10:30 - 12:15 |
Oral Session 1 — Main Tracks |
|
10:30 - 10:45 |
Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters (Paper ID: 12) |
|
|
Authors: EL KHAYATI, Mohsine*; Elouahbi, Rachid; Semma, Abdelilah |
|
10:45 - 11:00 |
An Incremental Dual-Path Network for Robust Breast Ultrasound Image Segmentation (Paper ID: 16) |
|
|
Authors: Gaddala, Bhushan* |
|
11:00 - 11:15 |
Learning Selective Invariance for Augmentation-based Self-Supervised Learning to Improve Cross-User Human Activity Recognition (Paper ID: 26) |
|
|
Authors: Tong, Zixin; Abuhaija, Belal; Gao, Zhiqiang* |
|
11:15 - 11:30 |
Bayesian PET Reconstruction with Learned Flow Matching Priors via Langevin Sampling (Paper ID: 36) |
|
|
Authors: Ran, Hengjia ; Liu, Huafeng; Zhao , Bo* |
|
11:30 - 11:45 |
B-OmniNet: Patient-Centric Multimodal MRI Alignment for Breast Cancer Prognosis (Paper ID: 62) |
|
|
Authors: Zhang, Han*; Yang, Xinyu; Shang, Tongrui; Wang, Zehua; Yu, Yunfang; Li, Yang |
|
11:45 - 12:00 |
ActiveVideoAgent: Agent-Driven Spatio-Temporal Indexing for Long Video Reasoning (Paper ID: 64) |
|
|
Authors: Guo, Xi; Jia, Lili; Zhang, Jiawei; Li, Zijun; Qin, Jibo; Zhang, Liye; Di, Zhensheng; Wang, Guan* |
|
12:00 - 12:15 |
SurgiLink-MR: Bounded Planar Cutting and Bidirectional CT-Mesh Interaction for Surgical Mixed Reality Planning and Training (Paper ID: 29) |
|
|
Authors: TRIOUX, Anthony*; Zhou, Zikun ; Li, Yuzhe; Zhang, Xiaogang; Yang, Fuzheng |
|
12:15 - 13:30 |
Lunch Break |
|
13:30 - 15:00 |
Poster Session 1 — Main Tracks (incl. Industry Demo) |
|
|
Complete poster list: see the Poster Program section. |
|
15:00 - 15:15 |
Coffee Break |
|
15:30 - 18:00 |
Industry Session |
|
15:30 - 15:35 |
Session Opening |
|
15:35 - 15:55 |
Industry Keynote 1 |
|
|
Topic: Coming Soon |
|
|
Speaker: Dr. Qi Dai (Microsoft Research Asia, Principal Researcher) |
|
15:55 - 16:15 |
Industry Keynote 2 |
|
|
Topic: Coming Soon |
|
|
Speaker: Dr. Dinglong Huang (MALONG, Founder & CEO) |
|
16:15 - 16:35 |
Industry Keynote 3 |
|
|
Topic: JoySim: Scaling Embodied Intelligence via Simulation and Physical World Models |
|
|
Speaker: Dr. Jiawei Li (JD Group) |
|
16:35 - 16:55 |
Industry Keynote 4 |
|
|
Topic: Toward Physical AI: Challenges and Opportunities in Real-World Industrial Systems |
|
|
Speaker: Dr. Long Chen (Jiangxing AI, CTO of Foundation Models) |
|
16:55 - 17:40 |
Industrial Panel (Roundtable) |
|
|
Topic: The Multimodal Multiplier — Bridging the Gap from Lab to Industry |
|
|
Moderator: Prof. Xiaoping Zhang |
|
17:45 - 18:10 |
Live performance |
|
|
Live performance by Italian researcher, musician and composer Leonello Tarabella |
|
|
|
|
Day 3 — Thursday, June 18, 2026 |
|
|
09:00 – 10:00 |
Plenary Talk 2 |
|
|
Speaker: Wen Gao (Boya Chair Professor and Dean of Electronics Engineering and Computer Science, Peking University) |
|
|
Title: Towards Next Generation AVS Video Coding Standards: Methods, Activities, and Beyond |
|
10:00 – 10:15 |
Coffee Break |
|
10:30 – 12:00 |
Panel Discussion (Roundtable) |
|
|
Theme: Generative AI for Visual Media: Beyond Diffusion Models |
|
|
Chair: Frederic Dufaux |
|
12:00 – 13:00 |
Lunch Break |
|
13:00 – 18:00 |
Company Visit |
|
18:00 – 21:00 |
Banquet and Night Cruise of Shenzhen Bay |
|
|
|
|
Day 4 — Friday, June 19, 2026 |
|
|
09:00 – 10:00 |
Plenary Talk 3 |
|
|
Speaker: Zhou Wang (Professor of Electrical and Computer Engineering, University of Waterloo) |
|
|
Title: Perceptual Quality Assessment in the Age of AI: 25 Years After SSIM |
|
10:00 – 10:15 |
Coffee Break |
|
10:45 – 12:15 |
Oral Session 2 — Special Session Tracks |
|
|
SS1: AI for Healthcare (Organizers: Prof. Xiaodan Zhang, Prof. Cheng Chen) |
|
|
SS2: Explainable Machine Learning (Organizer: Prof. Haoran Li) |
|
10:45 – 11:00 |
REFLEX-Med: Reinforcement with Label-Free Explainability for Unified Medical Reasoning (Paper ID: 10) |
|
|
Authors: Tang, Luyao*; Cai, Zheyuan; Tian, Qinong; Li, Zi; Liu, Quande; Bae, Kyongtae Tyler; Chen, Cheng |
|
11:00 – 11:15 |
Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet models (Paper ID: 20) |
|
|
Authors: EL KHAYATI, Mohsine*; Semma, Abdelillah; Cour, Abdelaziz; Elouahbi, Rachid |
|
11:15 – 11:30 |
ACD-Desmoke: Adaptive Constrained Diffusion for Generalizable Zero-Shot Surgical Smoke Removal in Laparoscopy (Paper ID: 58) |
|
|
Authors: Liu, Yunxun; Liu, Shuang; Liang, Chengjun; Meng, Qiushi; Hu, Ran; Liang, Mengmeng; Yan, Jixue; Lai, Jianyu; Zhu, Lei* |
|
11:30 – 11:45 |
A Filtering-Theoretic Interpretation of Transformers A State-Space Perspective (Paper ID: 59) |
|
|
Authors: Wang, Kecheng*; Xiao, Yigong |
|
11:45 – 12:00 |
Are Faithfulness Metrics Robust to Model and Machine Changes in Explainable Anomalous Sound Detection? (Paper ID: 9) |
|
|
Authors: Buck, Alexander*; Cosma, Georgina; Phillips, Iain; Conway, Paul; Baker, Patrick |
|
12:00 – 12:15 |
Tail-Aware Wavelet Graph Learning for Robust Spatio-Temporal Signal Forecasting: A Case Study on Traffic Flow (Paper ID: 42) |
|
|
Authors: Gao, Yeqi; Kuruoglu, Ercan Engin* |
|
|
|
|
12:15 – 13:30 |
Lunch Break |
|
13:30 – 15:00 |
Tutorial Session (Short #2) |
|
|
Title: Methodology and Evaluation for Generative Image Processing |
|
|
Presenters: Huiyu Duan (Shanghai Jiao Tong University); Chunyi Li (Shanghai Jiao Tong University); Wenhui Wu (Shenzhen University); Shishun Tian (Shenzhen University) |
|
15:00 – 15:15 |
Coffee Break |
|
15:15 – 16:45 |
Poster Session 2 — Special Session Tracks and Trustworthy AI |
|
|
Complete poster list: see the Poster Program section. |
|
16:45 – 17:45 |
Closing & Award Session |
|
|
|
|
Day 5 — Saturday, June 20, 2026 |
|
|
09:00 – 13:00 |
Optional Excursion |
|
|
Explore Shenzhen and surrounding area. |
Poster Program
Poster Session 1: Main Track | June 17, 2026 | 1:30–3:00 PM
|
Poster No. |
Paper ID |
Paper Title |
Authors |
Subject Area |
|
PS1-01 |
8 |
Green Tide Detection Based on Multi-Scale Spatial–Spectral Network with Multispectral Satellite Images |
Zhou, Yuqing*; Wang, Xueqian; Li, Gang; Zhang, Li |
Image and video sensing, modeling, and representation |
|
PS1-02 |
63 |
Pruning CNNs with Graph Random Walk and Random Matrix Theory |
Kuruoğlu, Ercan Engin; Xu, Chi* |
Image and video processing techniques |
|
PS1-03 |
5 |
Hybrid Variational Model for Unidirectional Disparity Map from Human Straight walk Video Scene |
Amur, Khuda Bux* |
Image and video processing techniques |
|
PS1-04 |
61 |
A Reconstruction System for Industrial Pipeline Inner Walls Using Panoramic Image Stitching with Endoscopic Imaging |
Ma, Rui; Wang, Yifeng; Yang , Ziteng; Guo, Jing; Okanda, Naomi Imali; Li, Xinghui* |
Image and video processing techniques |
|
PS1-05 |
34 |
Enhancing spectral images via Vision Transformers and vector optimization |
Achini, Federico*; Salvaggio, Isabella; Causin, Paola; Vanini, Sara; Scacchi, Simone |
Image and video analysis, synthesis, and retrieval |
|
PS1-06 |
64 |
ActiveVideoAgent: Agent-Driven Spatio-Temporal Indexing for Long Video Reasoning |
Guo, Xi; Jia, Lili; Zhang, Jiawei; Li, Zijun; Qin, Jibo; Zhang, Liye; Di, Zhensheng; Wang, Guan* |
Image and video analysis, synthesis, and retrieval |
|
PS1-07 |
66 |
Improved YOLOv8 real-time object detection algorithm |
Sun, Zhi; Jia, Lili; Lu, Zirui; Di, Zhensheng; Wang, Guan* |
Image and video analysis, synthesis, and retrieval |
|
PS1-08 |
31 |
Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors |
Dong, Xin; Teng, Yunzhi; Deng, Wenfeng; Tang, Yansong* |
Multimodality AI and vision-language action model |
|
PS1-09 |
47 |
WTranL: Multi-Resolution Wavelet-Transformer with Staged Cross-Attention for Multimodal Conversational Emotion Recognition |
Zhang, Hongkang*; Huang, Shao-Lun; Wang, Yanlong; Kuruoglu, Ercan Engin |
Multimodality AI and vision-language action model |
|
PS1-10 |
56 |
A Unified Framework of Strong and Weak Constraints for Robust Multimodal Learning |
Zhang, Hongkang*; Huang, Shao-Lun; Wang, Yanlong; Kuruoglu, Ercan Engin |
Multimodality AI and vision-language action model |
|
PS1-11 |
24 |
FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios |
Xu, Ruihao*; Liu, Yong; Tang, Yansong |
Applications and other topics in image, video and multidimensional signal processing |
|
PS1-12 |
12 |
Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters |
EL KHAYATI, Mohsine*; Elouahbi, Rachid; Semma, Abdelilah |
Machine learning model |
|
PS1-13 |
16 |
An Incremental Dual-Path Network for Robust Breast Ultrasound Image Segmentation |
Gaddala, Bhushan* |
Machine learning model |
|
PS1-14 |
17 |
Detecting Coordinated Fake View Campaigns on YouTube via Attribute-Disentangled Collaborative Graph Learning |
Gaddala, Bhushan* |
Machine learning model |
|
PS1-15 |
19 |
Explainable Multi Modal Ensemble Learning for Joint Cotton Disease Classification and Growth Milestone Prediction |
Narayana, Putturi* |
Machine learning model |
|
PS1-16 |
26 |
Learning Selective Invariance for Augmentation-based Self-Supervised Learning to Improve Cross-User Human Activity Recognition |
Tong, Zixin; Abuhaija, Belal; Gao, Zhiqiang* |
Applications and other topics of machine learning |
|
PS1-17 |
32 |
EBC-LLM: Expert-Bank Compression via Cluster-Shared Rotation and Runtime-Aligned Structured Payloads |
Kuzekov, Daniyar; Yang, Li; Kuruoğlu, Ercan Engin; Chan, Wai Kin (Victor)* |
Applications and other topics of machine learning |
|
PS1-18 |
33 |
Assessing Advertising Importance in Social Media–Driven Buying and Selling Decisions through Customer Satisfaction Prediction |
Bandi, Srinivas*; Suresh, M |
Applications and other topics of machine learning |
|
PS1-19 |
7 |
BlochShift: Physics-Guided Diffusion with Bloch-Based Drift for MRI Image Translation |
Wang, Zihao*; Gan, Yu; Wu, Ona |
Medical imaging |
|
PS1-20 |
51 |
DE-C3: Robust Kleihauer-Betke Test via Data-Efficient Contrastive Cell Classification |
Shen, Sheng; Jin, Austin; Wang, Jerry Kaizhong; Chadburn, Amy; Yuan, Junsogn; Brzostek, Sabrina Racine; Xi, Nan* |
Medical imaging |
|
PS1-21 |
52 |
Deep Dual-Path UNet with Cross-Attention for Medical Image Segmentation |
Zhang, Hongkang*; Huang, Shao-Lun; Kuruoglu, Ercan Engin |
Medical imaging |
|
PS1-22 |
53 |
YOLO-CSA: Channel–Spatial Enhanced YOLOv11 for Blood Cell Detection |
Deng, Yingqin* |
Medical imaging |
|
PS1-23 |
62 |
B-OmniNet: Patient-Centric Multimodal MRI Alignment for Breast Cancer Prognosis |
Zhang, Han*; Yang, Xinyu; Shang, Tongrui; Wang, Zehua; Yu, Yunfang; Li, Yang |
Medical imaging |
|
PS1-24 |
25 |
Robust Real-Time Heart Rate Measurement Using Adaptive SOBI Algorithm in Non-Stationary Environments |
Qin, Zihang*; Wang, Yiming ; Wu, Xiaopei |
Applications and emerging methods in biomedical image and signal processing |
|
PS1-25 |
29 |
SurgiLink-MR: Bounded Planar Cutting and Bidirectional CT-Mesh Interaction for Surgical Mixed Reality Planning and Training |
TRIOUX, Anthony*; Zhou, Zikun ; Li, Yuzhe; Zhang, Xiaogang; Yang, Fuzheng |
Applications and emerging methods in biomedical image and signal processing |
|
PS1-26 |
36 |
Bayesian PET Reconstruction with Learned Flow Matching Priors via Langevin Sampling |
Ran, Hengjia ; Liu, Huafeng; Zhao , Bo* |
Computational imaging methods and models |
|
PS1-27 |
39 |
Computation-Aware Event-to-Frame Reconstruction via Selective Attention |
Wu, Jingqian*; Jia, Yunbo; Lam, Edmund |
Computational imaging methods and models |
|
PS1-28 |
15 |
A Novel Architecture Enabled Graph-Based Authentication using CAG and API Driven Authentic News Verification Detection |
Singh Rayat, Simar*; Dahiya, Susheela; Anwarul, Shahina |
Multimedia forensics |
|
PS1-29 |
18 |
A Reproducible Benchmark for Quantum Machine Learning in Rainfall Anomaly Detection |
Thota, Naga Manikanta* |
Machine learning for information forensics and security |
|
PS1-30 |
37 |
SynergyAI: An AI-Driven Predictive Valuation and Risk Assessment Framework for Private Equity Investments |
Gaikwad, Pranav*; Sonawane, Moulik ; Kadam, Priyanshu Kadam; Shende, Yash; Futane, Pravin |
Machine learning for information forensics and security |
Poster Session 2: Special Session Tracks and Trustworthy AI | June 19, 2026 | 3:15–4:45 PM
|
Poster No. |
Paper ID |
Paper Title |
Authors |
Primary Subject Area |
|
PS2-01 |
13 |
A Bayesian LSTM Framework for Uncertainty-Aware Traffic Forecasting and Risk-Based Congestion Alarms |
Gollapati, Sai Krishna*; Lakshmi Nadh, k |
Trustworthy and reliable machine learning |
|
PS2-02 |
20 |
Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet models |
El Khayati, Mohsine*; Semma, Abdelillah; Cour, Abdelaziz; Elouahbi, Rachid |
Trustworthy and reliable machine learning |
|
PS2-03 |
42 |
Tail-Aware Wavelet Graph Learning for Robust Spatio-Temporal Signal Forecasting: A Case Study on Traffic Flow |
Gao, Yeqi; Kuruoglu, Ercan Engin* |
Trustworthy and reliable machine learning |
|
PS2-04 |
6 |
Semantic Bias-Aware Medical Report Generation for Brain CT Imaging |
Xiang, Xinrui*; Yao, Xinyi; Chen, Peng |
Special Session: AI for Healthcare |
|
PS2-05 |
10 |
REFLEX-Med: Reinforcement with Label-Free Explainability for Unified Medical Reasoning |
Tang, Luyao*; Cai, Zheyuan; Tian, Qinong; Li, Zi; Liu, Quande; Bae, Kyongtae Tyler; Chen, Cheng |
Special Session: AI for Healthcare |
|
PS2-06 |
11 |
MM-FM: Multi-Modal Flow Matching for Brain MRI Missing Modality Synthesis |
Lin, Bin*; Cheng, Zhiming; Zhao, Jianxiang; Li, Yu; Miao, Zheng; Ma, Bingtao; Wang, Shuai |
Special Session: AI for Healthcare |
|
PS2-07 |
28 |
Beyond Static Retrieval: A Multi-Layer Cognitive Architecture for Evidence-Based Medical Reasoning |
Xu, Jiacheng* |
Special Session: AI for Healthcare |
|
PS2-08 |
30 |
Diffusion-Based Longitudinal Representation Learning for OCT Prognosis |
Zhang, Wanyu; Zheng, Chengxin; Zhang, Xiaodan* |
Special Session: AI for Healthcare |
|
PS2-09 |
58 |
ACD-Desmoke: Adaptive Constrained Diffusion for Generalizable Zero-Shot Surgical Smoke Removal in Laparoscopy |
Liu, Yunxun; Liu, Shuang; Liang, Chengjun; Meng, Qiushi; Hu, Ran; Liang, Mengmeng; Yan, Jixue; Lai, Jianyu; Zhu, Lei* |
Special Session: AI for Healthcare |
|
PS2-10 |
60 |
Mucosa-Aware Localization Refinement for Robust Endoscopic Polyp Detection |
Shao, Junhao*; Zhao, Jianxiang; Yue, Changpeng; Ma, Bingtao; Wang, Shuai |
Special Session: AI for Healthcare |
|
PS2-11 |
9 |
Are Faithfulness Metrics Robust to Model and Machine Changes in Explainable Anomalous Sound Detection? |
Buck, Alexander*; Cosma, Georgina; Phillips, Iain; Conway, Paul; Baker, Patrick |
Special Session: Explainable Machine Learning |
|
PS2-12 |
43 |
The Mechanics of Explainability: How Exponential Attention Enables Sparse and Interpretable In-Context Learning |
Gao, Yeqi; Kuruoglu, Ercan Engin* |
Special Session: Explainable Machine Learning |
|
PS2-13 |
59 |
A Filtering-Theoretic Interpretation of Transformers A State-Space Perspective |
Wang, Kecheng*; Xiao, Yigong |
Special Session: Explainable Machine Learning |