IEEE MIPR 2026

IEEE 9th International Conference on Multimedia Information Processing and Retrieval (MIPR 2026) IEEE MIPR 2026

August 9–11, 2026 | Chatrium Grand Bangkok Hotel, Thailand
Mahidol University
IEEE Computer Society
IEEE

Program Details

Day 1 Tracks

Track Chair Venue Time Note
Workshop 1 Luntian Mou Ballroom 09:00-10:00, Sun. 9 Aug. 4 Papers
Workshop 2 Wanwan Bu Komes 2 09:00-12:30, Sun. 9 Aug. https://www.ipmml.org/
Tutorial Iole Moccagatta Komes 1 10:30-12:30, Sun. 9 Aug.
Special Session 1 Song Wang Komes 1 13:30-14:00, Sun. 9 Aug. 2 Papers
Special Session 2 Teng-Wen Chang Ballroom 13:30-15:15, Sun. 9 Aug. 7 Papers
Special Session 3 Lei Gao Komes 1 14:00-15:00, Sun. 9 Aug. 4 Papers
Opening Iole Moccagatta Ballroom 15:45-16:15, Sun. 9 Aug.
Industry Talk Session Yukiko Yanagawa Ballroom 16:20-17:50, Sun. 9 Aug. Chenyang Lyu
Chiraphat Boonnag
Shiv Kumar Saini
Distinguished Plenary Talk Paisarn Muneesawang Ballroom 18:00-18:45, Sun. 9 Aug.
Demo Session Kim-Hui Yap Komes 2 13:30-15:15/16:15-18:00, Sun. 9 Aug.

Workshop Session WS-1: Healthcare Through Multimedia Analytics

Chair: Luntian Mou | Venue: Ballroom | Time: 09:00-10:00, Sunday, 9 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:15 WS-1-1 135 Explainable Fundus-Based AI Glaucoma Screening: Design and Evaluation of a Healthcare System Allan Pascual Erasmo (Yoobee Colleges); Jaya Tiwari (Waikato Hospital); Samaneh Chaharmiri Dokhaharani (Mae Fah Luang University); Mohammad Norouzifard (The University of Auckland)*
09:15-09:30 WS-1-2 162 RadLens: Radiology Report Generation Using a Vision Transformer and Retrieval-Augmented Generation Philip Niron Nithianandan (Yoobee College of Creative Innovation); Jaya Tiwari (Waikato Hospital); Seyedhashem Davarpanah (Agentic AI Hub); Mohammad Norouzifard (The University of Auckland)*
09:30-09:45 WS-1-3 171 Ethical Implications of AI-Assisted Digital Phenotyping in Clinical Psychiatry Deepa Shukla (IITJ)*; Nisha Daga (IITJ); George Kodimattam Joseph (IITJ)
09:45-10:00 WS-1-4 172 Neuro-Adaptive Virtual Reality for Spider Phobia: Integrating EEG and Heart Rate Biofeedback in Closed-Loop Exposure Therapy Rahul Kumar Ray (FLAME University); Rudra Krishna (FLAME University);
Chiranjoy Chattopadhyay (FLAME University)*

Tutorial Session

Time Title Speaker Venue
10:30-12:30, Sun. 9 Aug. Design and Optimization for Interactive Spatial-Temporal Multi-Modal Gaussian Splatting Dr. Guan-Ming Su
(Dolby Laboratories, USA)
 Komes  1

Special Session SS-1: Large Models for Embodied Multimedia Processing

Chair: Song Wang | Venue: Komes 1 | Time: 13:30-14:00, Sunday, 9 August 2026

Time Slot Paper ID Paper Title Authors
13:30-13:45 SS-1-1 124 Arbiter: Unifying Executable Verification and Semantic Assessment Yuhang Lu (Zhengzhou university)*; Yong Huang (Zhengzhou university); Ying Yu (The PLA Information Engineering University); Lei Li (The PLA Information Engineering University); Tao Yang (Zhengzhou university); Yun Tie (Zhengzhou university)
13:45-14:00 SS-1-2 129 A Diffusion-Based Data Augmentation Framework for Semantic Segmentation with Limited Data Zhiyan Wang (Henan University of Technology)*; Xinyu Li (Zhengzhou University); Chunhua Zhu (Henan University of Technology); Lin Qi (Zhengzhou University)

Special Session SS-2: Multimodal AI-Mediated Interaction for Cross-Disciplinary Design Collaboration

Chair: Teng-Wen Chang | Venue: Ballroom | Time: 13:30-15:15, Sunday, 9 August 2026

Time Slot Paper ID Paper Title Authors
13:30-13:45 SS-2-1 131 The Domain-Specific Fidelity Gap: Trajectory-Based T2I Alignment in AI-Mediated Cross-Disciplinary Design Collaboration Chen-Syuan Lin (National Yunlin University of Science and Technology); Teng-Wen Chang (National Yunlin University of Science and Technology)*
13:45-14:00 SS-2-2 134 How Do Ideas Evolve Across HumanAI Co-Ideation Cycles? A Trajectory Analysis of Conversational AI in a Semester-Long Interactive-Installation Design Studio Chor-Kheng Lim (Yuan Ze University)*
14:00-14:15 SS-2-3 128 Surfacing Stress Subtypes through Cognitive-Variation-Conditioned Agentic LLM Co-Ideation: A Walkthrough Probe of Behavioral Trajectories Siao-Rou Jheng (National Yunlin University of Science and Technology); Ya-Chen Chang (National Yunlin University of Science and Technology); Teng-Wen Chang (National Yunlin University of Science and Technology)*
14:15-14:30 SS-2-4 125 Beyond Semantic Distance: Fusing Physiological and Linguistic Signals for Multimodal Coordination Assessment in Cross-Disciplinary Design Teng-Wen Chang (National Yunlin University of Science and Technology)*; Yi-Sheng (Ezra) Wu (National Yunlin University of Science and Technology); Ya-Chen Chang (National Yunlin University of Science and Technology); Jia-Rong (Lotus) Li (National Yunlin University of Science and Technology); Siao-Rou Jheng (National Yunlin University of Science and Technology); Wu-Haw Jue (National Formosa University)
14:30-14:45 SS-2-5 122 Toward AI-Mediated Attention Regulation: A Stability-Oriented Closed-Loop Architecture Using Consumer VR IMU as Wearable Behavioral Sensor Chia Hui Nico Lo (YuanZe University)*
14:45-15:00 SS-2-6 127 Structured Literary Knowledge as AI-Mediated Generative Mediation: From Cultural Interpretation to Immersive Scene Construction Tse Wei Hsu (YunTech)*
15:00-15:15 SS-2-7 123 Creatura Era: Multimodal Generative AI and Tangible AR for Cross-Disciplinary Design Collaboration Wingly Shih (NYUST)*; Kathryn Su (NYUST)

Special Session SS-3: From Macro & Micro Expression Analysis to Multimodal Affective Computing: Use Cases, Ethics, and Sector Applications

Chair: Lei Gao | Venue: Komes 1 | Time: 14:00-15:00, Sunday, 9 August 2026

Time Slot Paper ID Paper Title Authors
14:00-14:15 SS-3-1 113 Capturing Dynamics: The 4D Facial Expression Intensity Dataset Zesheng Wang (University of Nantes)*; Alexandre Bruckert (University of Nantes); Pierre Lebreton (University of Nantes); Patrick Le Callet (University of Nantes); Yante Li (University of Oulu); Guoying Zhao (University of Oulu)
14:15-14:30 SS-3-2 170 EmotionBench: Benchmarking Facial Emotion Understanding in Multimodal Large Language Models Linhan Xu (Shanghai Jiao Tong University); Baiyi Chen ( Shanghai Jiao Tong University); Yixuan Gao (Shanghai Jiao Tong University)*; Huiyu Duan ( Shanghai Jiao Tong University); Yuqin Cao (Shanghai Jiao Tong University); Sijing Wu (Shanghai Jiao Tong University); Yunhao Li (Shanghai Jiao Tong University); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)"
14:30-14:45 SS-3-3 140 Towards Emotion-Aware Wearables: Distilling PPG Foundation Models for Real-Time Affective and Physiological Monitoring Duc Hoang Long Nguyen (University of Engineering and Technology, Vietnam National Universit)*; Patrick Le Callet (Nantes Université, Ecole Centrale Nantes); Thanh Ha Le (University of Engineering and Technology, Vietnam National Universit); Thi Duyen Ngo (University of Engineering and Technology, Vietnam National Universit)
14:45-15:00 SS-3-4 159 Involuntary Leakage, Epistemic Harm, and Regulatory Arbitrage: A Cross-Jurisdictional Analysis of Micro-Expression Governance Jenjira Jaimunk (Department of Computer Engineering, Faculty of Engineering, Chiang Mai University)*; Patrick Le Callet (Équipe Image, Perception et Interaction, Laboratoire des Sciences du Numérique de Nantes, Université de Nantes); Pradorn Sureephong (College of Arts, Media and Technology, Chiang Mai University)

Distinguished Plenary Talk

Time Chair Title Speaker Venue
18:00-18:45, Sun. 9 Aug. Paisarn Muneesawang Learning beyond Deep Learning: Mathematics-Inspired Models for Multi-View Analysis Prof. Ling Guan
(Toronto Metropolitan University, Canada)
 Ballroom

Demo Session

Chair: Kim-Hui Yap | Venue: Komes 2 | Time: 13:30-15:15/16:15-18:00, Sunday, 9 August 2026

Time Slot Paper ID Paper Title Authors
13:30-15:15
16:15-18:00
 DS-1-1 110 Multi Agent LLMs for Diversified Large Scale Spatial Consistent 3D Scene Data Synthesis Sandeep Bangalore (Dolby Labs)*; Lakshmi Priya Muraleedharan (Dolby Labs); Arpitha Nagaraj Hegde (Dolby Labs); Guan-Ming Su (Dolby Labs)
13:30-15:15
16:15-18:00
 DS-1-2 111 AuthentiQ: Real-Time On-Device Deepfake Detection for the Internet of Multimedia Things Raghu Iyengar (pi-labs)*; Kapardi Mallampalli (pi-labs); Hitesh Sanghvi (Directorate of Forensic Sciences)
13:30-15:15
16:15-18:00
 DS-1-3 148 Real-Time Clinical Decision Support in the Trauma Room: An Edge-Native Two-Agent System for Structured Information Processing Niklas Beck (Fraunhofer IAIS)*; Johann Jasper Schulze Buschhoff (Fraunhofer IAIS); Emmy Lai (Fraunhofer IAIS); Najmeh Mousavi (Fraunhofer IAIS); Julian Maluck (T-Systems International); Teh-Hai Julian Zheng (T-Systems International); Stefan Swoboda (T-Systems International); Benny Jörg Stein (Fraunhofer IAIS)
13:30-15:15
16:15-18:00
 DS-1-4 151 Personalized Federated Fine-Tuning for Distributed Image-Text Retrieval Yifan Zhou (shanghai university); Mengxin Yang (shanghai university); Hongmei Shi (shanghai university); Yixiao Gu (shanghai university)*
13:30-15:15
16:15-18:00
 DS-1-5 152 BETA-Cap: An Interactive System for Bilingual English-Turkish Audio Captioning Best Demo Paper Candidate Melek Tanyeri Yener (Baskent University)*; Mustafa Sert (Baskent University)
13:30-15:15
16:15-18:00
 DS-1-6 169 Harness Engineering for Multi-Agent Data Visualization with Small Language Models Xinxiao Li (Shonan Institute of Technology); Peilin Wang (Shonan Institute of Technology); Eisei Nakahara (Nihon University)*
13:30-15:15
16:15-18:00
 DS-1-7 178 Designing an Intelligent Multimedia Vending Interface for Ethical-Choice Interaction Wing Yan Jasman PANG (Technological and Higher Education Institute of Hong Kong)*; Yan Chi Wan (Technological and Higher Education Institute of Hong Kong)

Day 2 Tracks

Keynote Sessions

Time Chair Title Speaker Venue
11:30-12:30, Mon. 10 Aug. Albert Ali Salah Towards Trustworthy Multimodal Models Prof. Mohan Kankanhalli
(National University of Singapore, Singapore)
 Ballroom
14:00-15:00, Mon. 10 Aug. Supavadee Aramvith Stable Components in High-Dimensional Data: Joint Decomposition Across Datasets Prof. Tülay Adalı
(University of Maryland, Baltimore County, USA)
 Ballroom

Regular Sessions

Session Chair Venue Time Note
RO-1 Toshihiko Yamasaki Ballroom 09:00-10:30, Mon. 10 Aug. 6 Papers
RO-2 Albert Ali Salah Ballroom 15:30-17:15, Mon. 10 Aug. 7 Papers
RP-1 Shanshan Yao Komes 1 15:30-17:45, Mon. 10 Aug. 24 Papers

Regular Oral Session RO-1: Multimodal Perception, Reasoning, and Intelligent Agents

Chair: Toshihiko Yamasaki | Venue: Ballroom | Time: 09:00-10:30, Monday, 10 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:15 RO-1-1 17 Single-View Biomechanical State Estimation for Maize Architecture Recovery Yue Zhuo (Cornell University); Fengqi You (Cornell University)*
09:15-09:30 RO-1-2 18 3D Object Recovery for Data Tampering Attack on In-vehicle Networks Gangtao Han (Zhengzhou University); Yurui Chen (Zhengzhou University); Song Wang (Zhengzhou University)*; Enqing Chen (Zhengzhou University); Lingling Li (Zhengzhou University of Aeronautics); Gaofeng Pan (Beijing Institute of Technology)
09:30-09:45 RO-1-3 45 Boosting Vision-Language Model for Cross-Device GUI Agent Grounding and Navigation Best Student Paper Candidate Bo-Yu Chen (National Chung Cheng University); Liang-Han Shih (National Chung Cheng University); Chen-Kuo Chiang (National Chung Cheng University)*
09:45-10:00 RO-1-4 47 SpatialAgent: Spatial Question Answering with LLM Agent and Perception Models 🏆 Best Student Paper Award Hsiang-Wei Huang (University of Washington)*; Junbin Lu (University of Washington); Jianxu Shangguan (University of Washington); Jen-Hao Cheng (University of Washington); Kuang-Ming Chen (University of Washington); Cheng-Yen Yang (University of Washington); Bahaa Alattar (University of Washington); Yi-Ru Lin (University of Washington); Pyongkun Kim (Electronics and Telecommunications Research Institute); Sangwon Kim (Electronics and Telecommunications Research Institute); Kwangju Kim (Electronics and Telecommunications Research Institute); Chung-I Huang (National Chung Hsing University); Jenq-Neng Hwang (University of Washington)
10:00-10:15 RO-1-5 63 Document-Grounded Coaching Agent for Video Skill Assessment Best Paper Candidate Masaya Fujiwaka (NEC)*; Takuro Kawada (Hosei University); Xiaotong Ji (NEC); Jianquan Liu (NEC)
10:15-10:30 RO-1-6 84 Trajectory-Centered Reasoning for Counterfactual Driving Question Answering Best Paper Candidate Xiaotong Ji (NEC Corporation)*; Masaya Fujiwaka (NEC Corporation); Jianquan Liu (NEC Corporation)

Regular Oral Session RO-2: Multimedia Intelligence and Learning for Domain-Specific Applications

Chair: Albert Ali Salah | Venue: Ballroom | Time: 15:30-17:15, Monday, 10 August 2026

Time Slot Paper ID Paper Title Authors
15:30-15:45 RO-2-1 3 Bridging Design and Quality: A Technical Overview of FMs in Manufacturing Chih-Fan Hsu (Inventec Corp.)*; Yung-Huei Chiou (Inventec Corp.); Po-Han Huang (Inventec Corp.); Yu-chi Liao (Inventec Corp.); Shu Huei Yang (Inventec Corp.); Jyun-Ze Tang (Inventec Corp.); Yu-Lun Chang (Inventec Corp.); Ming-Ching Chang (University at Albany)
15:45-16:00 RO-2-2 24 QuranRTT: Real-Time Domain-Specific Translation of Classical Arabic Quranic Recitation Nagendhra Madishetti (University at Albany, State University of New York); Md Monjurul Ahsan Prodhan (University at Albany, State University of New York); Md Nour Hossain (University at Albany, State University of New York)*
16:00-16:15 RO-2-3 36 Hard-Decision Bottleneck in Belief Propagation for Speaker Diarization: A Factor Graph Analysis Snit Sanghlao (Faculty of Information and Communication Technology, Mahidol University)*; Jantarat Saenghlao (Department of Computer Engineering, KMUTT); Threrawee Sanglaow (Department of Physics, KMUTT)
16:15-16:30 RO-2-4 53 Continual Learning with Support Boundary Experience Blending 🏆 Best Paper Award Chih-Fan Hsu*; Yung-Huei Chiou (Inventec Corp.); Ming-Ching Chang (University at Albany, State University of New York); Wei-Chao Chen (Inventec Corp.)
16:30-16:45 RO-2-5 62 Modeling Video Ads with Structured Semantics for CTR Prediction Best Student Paper Candidate Yoshiaki Tanabe (The university of Tokyo)*; Shuntaro Masuda (The university of Tokyo); Gakumatsu Ryu (Septeni Japan, Inc.); Ryoichi Katsuya (Septeni Japan, Inc.); Toshihiko Yamasaki (The university of Tokyo)
16:45-17:00 RO-2-6 100 VCE-DINO: Robust Video Capsule Endoscopy Anatomy Recognition via DINO Pretraining and Imbalance-Aware Learning Chayapon Sasnarukkit (Chulalongkorn university); Natawut Nupairoj (Chulalongkorn university); Peerapon Vateekul (Chulalongkorn university)*
16:45-17:15 RO-2-7 40 Bi-projection Fusion for 360 Depth Estimation Based on Coordinate Attention Lei Li (Information Engineering University);Chenyang He (Zhengzhou University);Ying Yu (Information Engineering University);Tao Yang (Zhengzhou University);Yuhang Lu (Zhengzhou University);Yun Tie (Zhengzhou University)*

Regular Poster Session

Chair: Shanshan Yao | Venue: Komes 1 | Time: 15:30-17:45, Monday, 10 August 2026

Time Slot Paper ID Paper Title Authors
15:30-17:45 RP-1-1 5 Optimized Smart Home Energy Management Systems Based on Hybrid Method Alexander N. Ndife (Chalmers University of Technology)*; Arinze Ijeoma (Institut für Kernphysik University of Münster); Paisarn Muneesawang (Department of Computer Engineering Mahidol University)
15:30-17:45 RP-1-2 16 A Rotation-Guided and Feature-Refined Framework for Robust Nuclei Segmentation in Histopathology Arbab Sufyan Wadood (Multimedia University)*; Mohammad Faizal Ahmad Fauzi (KPJU Healthcare University); Lai Kuan Wong (Multimedia University); Md Serajun Nabi (KPJU Healthcare University)
15:30-17:45 RP-1-3 20 Hierarchical Federated Class-Incremental Learning with Client-Local Replay for Industrial IoT Intrusion Detection Waiteng CHING (University of Aizu)*; Xiuheng LIAO (University of Aizu); Jingcheng SONG (Linyi University); Weiyu Wang (Hosei University); Zhiwei Si (University of Aizu); Chunhua SU (University of Aizu)
15:30-17:45 RP-1-4 25 Multi Local Modeling: Toward Structured Symbolic Music Generation Via Local Learning Van Hoang Bao Bach (University of Central Florida)*; Sansiri Tarnpradab (King Mongkut's University of Technology Thonburi); Kien Hua (University of Central Florida)
15:30-17:45 RP-1-5 28 DeepVisionSafety: An intelligent CCTV Monitoring System for Multi-class Anomaly Recognition Napasrapee Satittham (Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand.)*; Purin Pongpanich (Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand.); Kunanont Vutiprasertwong (Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand.); Narit Hnoohom (Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand.)
15:30-17:45 RP-1-6 32 A Distributed Learning Approach for Controlled Grammar Transfer using Structure-Timbre Disentangled Audio Synthesis Sridhar Varma Kalidindi (National Institute of Technology Andhra Pradesh); Karthick S (National Institute of Technology Tiruchirappalli)*
15:30-17:45 RP-1-7 33 Attention-Enhanced EfficientNet with Anatomy-Aware Test-Time Augmentation for Robust Dental Caries Detection Phubase Sangliamthong (Faculty of Information and Communication Technology, Mahidol University ); Aroonrat Choochue (Faculty of Information and Communication Technology, Mahidol Universit); Siriwan Suebnukarn (Faculty of Dentistry, Thammasat University ); Kanoksak Wattanachote (Mahidol University )*
15:30-17:45 RP-1-8 41 Language-Conditioned Geographic Localization of Indic Speech Raghu Iyengar (pi-labs)*; Hitesh Sanghvi (Directorate of Forensic Science )
15:30-17:45 RP-1-9 46 Detection-based Spatial Token Selection for Long Video Understanding with MLLMs Yuta Goto (NEC Corporation)*; Kengo Ishida (NEC Corporation); Satoshi Yamazaki (NEC Corporation); Junichi Funada (NEC Corporation); Jianquan Liu (NEC Corporation)
15:30-17:45 RP-1-10 57 Extreme Learning Machine Ensemble for Deep Learning-based List Decoding in Error-prone Video Transmission Systems Anton Louise De Ocampo (Batangas State University)*; Francois-Xavier Coudoux (Institut d’Électronique de Microélectronique et de Nanotechnologie (IEMN)); Stéphane Coulombe (École de technologie supérieure (Université du Québec)); Patrick Corlay (Université Polytechnique Hauts-de-France)
15:30-17:45 RP-1-11 61 Convolution and Transformer Integration for Glaucoma Classification on Enhanced Fundus Images Chayawat Nilsumrit (Mahidol University); Narit Hnoohom (Mahidol University)*
15:30-17:45 RP-1-12 66 An Empirical Study of Model-Specific Preprocessing and Focal Loss for Thai Depression Text Classification Rawipas Samoondee (Chiang Mai University)*; Dussadee Praserttitipong (Chiang Mai University)
15:30-17:45 RP-1-13 70 Real-Time Video Anomaly Detection Using YOLO Pose Estimation and CLIP-Based Semantic Scoring Vanodhya Warnasooriya (Chulalongkorn University); Amir Hajian (Chulalongkorn University); Watchara Ruangsang (King Mongkut’s University of Technology Thonburi); Supavadee Aramvith (Chulalongkorn University)*
15:30-17:45 RP-1-14 71 CARRE: Comprehensive Automated Refinement for Real Estate Using Large Language Models Yuta Takatsuji (The University of Tokyo)*; Tatsuya Iwanari (estie, inc.); Ryosuke Katsuta (estie, inc.); Shuntaro Masuda (The University of Tokyo); Shengzhou Yi (The University of Tokyo); Toshihiko Yamasaki (The University of Tokyo)
15:30-17:45 RP-1-15 73 Discriminative Correlation Perceptron-Style Neural Network for Multi-View Glaucoma Image Classification Chakkrit Termritthikun (Naresuan University)*; Yirga Belay Muna (Naresuan University); Paisarn Muneesawang (Mahidol University); Patchara Suwanbordin (Mahidol University); Lei Gao (Wilfrid Laurier University); Kai Liu (Toronto Metropolitan University); Ling Guan (Toronto Metropolitan University)
15:30-17:45 RP-1-16 77 SAM3 Adaptation for Root CT Image Segmentation Hurriyatul Fitriyah (Adelaide University)*; Huafei Huang (University of South Australia); Ivan Lee (University of South Australia)
15:30-17:45 RP-1-17 82 Beyond Global and Local: A Stacked Ensemble Approach to Symbolic Music Emotion Recognition Hema Kanoujia (University of Central Florida)*; Hemant Kanoujia (University of Central Florida); Kien Hua (University of Central Florida)
15:30-17:45 RP-1-18 83 Depth-Aware Pothole Detection Using YOLO and RT-DETR at the Edge Md Monjurul Prodhan (University at Albany, State University of New York); Md Nour Hossain (University at Albany, State University of New York)*
15:30-17:45 RP-1-19 87 Evaluating Diffusion Models for Single-Image 3D Gaussian Splatting Scene Reconstruction Max Eskandari (York University); Xingbang Tang (York University)*; Matthew J. Kyan (York University)
15:30-17:45 RP-1-20 88 A Harmless Owner-Specific Verification Scheme for DNN Copyright Protection Jiangnan Zhu (Kyushu University)*; Yuzhang Chen (Kyushu University); Yujie Gu (Kyushu University); Minoru Kuribayashi (Tohoku University); Kouichi Sakurai (Kyushu University)
15:30-17:45 RP-1-21 98 Exploring LMM-as-a-Judge for Image Harmonization Evaluation Jeonghun Baek (The University of Tokyo)*; Eunchung Noh (Samsung Electronics)
15:30-17:45 RP-1-22 101 Evaluating Symptom Fidelity in LLM-Driven Simulated Patients Using PHQ-9 and GAD-7 Pathanin Opachalearn (Mahidol University)*; Konlakorn Wongpatikaseree (Mahidol University); Natthawut Kertkeidkachorn (Japan Advanced Institute of Science and Technology)
15:30-17:45 RP-1-23 105 Characterizing Spatial Interface Metaphors for Exploratory 360° Video Retrieval in VR Mike Knoop (Utrecht University); Wolfgang Hürst (Utrecht University)*
15:30-17:45 RP-1-24 107 Improving GPT-Based Subjective Floor Plan Evaluation with Structural Cue Correction Taro Narahara (New Jersey Institute of Technology)*; Toshihiko Yamasaki (The University of Tokyo)

Workshop Sessions

Track Chair Venue Time Note
Workshop 3 Luntian Mou and Zichun Guo Komes 2 09:00-11:05, Mon. 10 Aug. 3 Keynotes and 5 Papers
Workshop 4 Komes 2 15:30-16:15, Mon. 10 Aug.

Workshop Session WS-3: AI for Culture, Art, and Design

Chair: Luntian Mou | Venue: Komes 2 | Time:09:00-11:05, Monday, 10 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:25 WS-3-1 Keynote 1 Provenance Computation of Historical and Cultural Data Xiaoru Yuan (Peking University)
09:25-09:35 WS-3-2 144 A Value-Aligned Multimodal Agent for Culturally Grounded Textbook Illustration Generation and Evaluation Chenrui Qin (East China University of Science and Technology); Yumiao Chen (East China University of Science and Technology)*; Yifan Yan (East China University of Science and Technology)
09:35-09:45 WS-3-3 145 SensiPillow: An Embodied Multimodal Agent for Bedtime Smartphone Intervention Qi Fang (Southern University of Science and Technology); Qianwen Tan (Southern University of Science and Technology); Kai Lin (Southern University of Science and Technology); Ziqian Bai (Southern University of Science and Technology)*
09:45-10:10 WS-3-4 Keynote 2 Music Large Model Shao 1.0 Jiafeng Liu (Central Conservatory of Music)
10:10-10:20 WS-3-5 175 Phygital Symbiosis and Innovation Dynamics of Location-Based Entertainment in China Jie Pang (Peking University)*; Jiaxin Li (Peking University)
10:20-10:30 WS-3-6 176 EAC2-Curation:Embodied Attention Capture and Curatorial Reconstruction Jiaxin Li(Peking University )*; Jie Pang(Peking university); Xinyi Wang(Zhejiang University)
10:30-10:55 WS-3-7 Keynote 3 Jewelry and Theater: Design and Artistic Practice Spanning Physical and Digital Realities Ting Song (Ting Museum)
10:55-11:05 WS-3-8 180 From Viewing to Experiencing: An Embodied Narrative Study of Dunhuang Mural Content Xianning Meng (Daegu University)*; Zichun Guo (Beijing University of Chemical Technology); Qiang Hao (Tsinghua University); Chang Pan (Daegu University)

Workshop Session WS-4: AWS AI-Driven Development Lifecycle (AI-DLC)

Chair: | Venue: Komes 2 | Time: 15:30-16:15, Monday, 10 August 2026

Day 3 Tracks

Keynote Sessions

Time Chair Title Speaker Venue
10:30-11:30, Tue. 11 Aug. Iole Moccagatta Journey to the Next Era: AI-driven Multi-view Analysis and the Future of Spatial Intelligence Prof. Hideo Saito
(Keio University, Japan)
 Ballroom

Invited Paper Sessions

Session Chair Venue Time Note
IP-1 Mei-Chen Yeh Ballroom 09:00–10:00 / 11:30–12:15, Tue. 11 Aug. 4/3 papers
IP-2 Guan-Ming Su Komes 1 09:00–10:00 / 11:30–12:15, Tue. 11 Aug. 4/3 papers
IP-3 Chih-Fan Hsu Komes 2 09:00–10:00 / 11:30–12:15, Tue. 11 Aug. 4/3 Papers

Invited Paper Session IP-1: Applications

Chair: Mei-Chen Yeh | Venue: Ballroom | Time: 09:00-10:00, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:15 IP-1-1 158 Designing Storyboards for Immersive Video Retrieval: A Comparative Study of 360-Degree Video Visualizations Marloes van der Haagen (Utrecht University); Wolfgang Hürst (Utrecht University)*
09:15-09:30 IP-1-2 109 Self-Supervised Representation Learning Using Object-Aware Data Augmentation Yong-Hong Lin (National Taiwan Normal University); Mei-Chen Yeh (National Taiwan Normal University)*
09:30-09:45 IP-1-3 173 Force-Responsive Virtual Makeup Ning Xu (Adeia Inc.)*; Aldis Sipolins (Adeia Inc.); Mareeta Mathai (Adeia Inc.); Mathew Adams (Adeia Inc.); Serhad Doken (Adeia Inc.)
09:45-10:00 IP-1-4 117 Transformer-Based Local Path Planning for Quadruped Robots Using Multi-View Semantic Perception Ju Wang (Virginia State University)*; Wei-Bang Chen (Virginia State University); Qian Qu (Virginia State University); Xuanchen Xiang (Virginia State University); Ahmed Mohammed (Virginia State University)

Chair: Mei-Chen Yeh | Venue: Ballroom | Time: 11:30-12:15, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
11:30-11:45 IP-1-5 133 Super-Resolution Preprocessing for Small Object Detection: An Empirical Study on VisDrone-Det at ×2 and ×4 Scales Musa Yahaya (Chulalongkorn University)*; Amir Hajian (Chulalongkorn University); Kanapoj Ngambenjavichaikul (Chulalongkorn University); Watchara Ruangsang (King Mongkut's University of Technology Thonburi); Supavadee Aramvith (Chulalongkorn University)
11:45-12:00 IP-1-6 155 A Lightweight Speaker Recognition Method with Multi-Layer Self-Distillation Shanshan Yao (Shanxi University); Jing You (Shanxi University); Yaozhang Zhu (Shanxi Lu'an Mining (Group) Co., Ltd.); Baoning Niu (Taiyuan University of Technology)*
12:00-12:15 IP-1-7 149 Physics-Guided Cascade Classification for Multi-Granularity Liquid Recognition in Dual-Energy X-ray Security Inspection Hongping Zhi (Tsinghua University)*; Lifeng Sun (Tsinghua University); Xiaoyun Su (Suzhou ZMore Technology Co., Ltd.); Weiwei Zheng (Suzhou ZMore Technology Co., Ltd.)

Invited Paper Session IP-2: Content Understanding

Chair: Guan-Ming Su| Venue: Komes 1 | Time: 09:00-10:00, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:15 IP-2-1 86 Global Attribution Meets Local Representation: A Hybrid Pipeline for Binary Composer Classification Hemant Kanoujia (University of Central Florida)*; Hema Kanoujia (University of Central Florida); Kien Hua (University of Central Florida)
09:15-09:30 IP-2-2 116 Anchor Tracking and Prediction with Triplane Channel-to-Spatial Mapping for Dynamic Gaussian Splatting Compression Birendra Kathariya (Dolby)*; Tsung-Wei Huang (Dolby Laboratories Inc.); Dae Yeol Lee (Dolby Laboratories Inc.); Fangjun Pu (Dolby Laboratories Inc.); Guan-Ming Su (Dolby Laboratories Inc.); Peng Yin (Dolby Laboratories Inc.); Gary J. Sullivan (Dolby Laboratories Inc.)
09:30-09:45 IP-2-3 160 Capture-Stage Multi-Camera Placement Recommendation System for Improved 3D Scene Coverage Dae Yeol Lee (Dolby Laboratories)*; Sandeep Bangalore Venkatesh (Dolby Laboratories); Anshul Rai (Dolby Laboratories); Tsung-Wei Huang (Dolby Laboratories); Guan-Ming Su (Dolby Laboratories)
09:45-10:00 IP-2-4 174 Dynamic Range Reshaping for Gaussian Splatting Tsung-Wei Huang (Dolby Laboratories)*; Dae Yeol Lee (Dolby Laboratories); Birendra Kathariya (Dolby Laboratories); Guan-Ming Su (Dolby Laboratories); Peng Yin (Dolby Laboratories)

Chair: Guan-Ming Su| Venue: Komes 1 | Time: 11:30-12:15, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
11:30-11:45 IP-2-5 163 Origin–Destination Proportion Analysis Using Machine Learning on Non-Overlapping Camera Videos Sajan Kumar (Purdue University); Stanley Chien (Purdue University)*; Shail Desai (Purdue University); Yaobin Chen (Purdue University); Nathan Shellhamer (Indiana Department of Transportation)
11:45-12:00 IP-2-6 164 Open-set Visual Template Discovery in Large-Scale Propaganda Image Collections Minh Tu Nguyen (National Chung Cheng University); Yu-Yao Tseng (National Chung Cheng University); Ming-Hung Wang (National Chung Cheng University)*
12:00-12:15 IP-2-7 154 Emotional Plants: When Artificial Agents Report Their Internal Affective States Vito Vekic (Utrecht University); Albert Ali Salah (Utrecht University)*; Almila Akdag (Utrecht University)

Invited Paper Session IP-3: Machine Learning, Deep Learning, Foundation Model, and Trustworthy AI

Chair: Chih-Fan Hsu | Venue: Komes 2 | Time: 09:00-10:00, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
09:00-09:15 IP-3-1 91 Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis Weidong Zhang (Northeastern University); Yongchan Jung (Fairleigh Dickinson University); Shafayat Mowla Anik (University of Colorado - Colorado Springs); Furen Xiao (National Taiwan University); Vasudevan Janarthanan (Fairleigh Dickinson University); Enkhzaya Chuluunbaatar (University of British Columbia); Marco Ho (British Columbia Institute of Technology); Byeong Kil Lee (University of Colorado - Colorado Springs); Jeeho Ryoo (Fairleigh Dickinson University)*
09:15-09:30 IP-3-2 156 DESNet: A Multimodal Collaborative Network for Joint Driver Emotion and Stress Recognition Luntian Mou (Beijing University of Technology)*; Wenyan Zhao (Beijing University of Technology); Shasha Mao (Xidian University); Nan Ma (Beijing University of Technology)
09:30-09:45 IP-3-3 167 Edge Computing with Green Super-Resolution Li-Heng Wang (USC)*; Yixing Wu (USC); Wei Wang (USC); C.-C. Jay Kuo (USC)
09:45-10:00 IP-3-4 76 A Discriminant Multi-view Correlation Analysis Platform for Multimedia Computing Lei Gao (Wilfrid Laurier University)*; Kai Liu (Toronto Metropolitan University); Ling Guan (Toronto Metropolitan University)

Chair: Chih-Fan Hsu | Venue: Komes 2 | Time: 11:30-12:15, Tuesday, 11 August 2026

Time Slot Paper ID Paper Title Authors
11:30-11:45 IP-3-5 161 A Multi-Source Ultrasound Benchmark Revealing the Limits of Contemporary Self-Supervised Anomaly Detection Methods Marco Riedenauer (University of Augsburg)*; Daniel Kienzle (University of Augsburg); Pratik Mayekar (University of Augsburg); Rainer Lienhart (University of Augsburg)
11:45-12:00 IP-3-6 139 Comparison of multimodal LLM embedding models in the task of cross-modal recipe retrieval Keisuke Gomi (The University of Electro-Communications)*; Keiji Yanai (The University of Electro-Communications)
12:00-12:15 IP-3-7 115 Differentiable Proxy Learning for Adaptive Quantization Control in H.264 Video Coding Qihan Xu (Simon Fraser University)*; Ivan Bajic (Simon Fraser University)