Industrial Physical AI

More workshops at ACM International Conference on Multimedia 2026

• Agentic Multimodal Intelligence — Explores agent-based multimodal systems that can perceive, reason, and act across diverse real-world tasks using...
• Deepfake Forensics — Covers detection, attribution, and forensic analysis of AI-generated synthetic media including deepfake video and audio....
• Efficient Representation Learning for Multimodal Retrieval — Focuses on lightweight and efficient representation learning approaches for cross-modal and multimodal retrieval at scale....
• Efficient AI Systems for Sustainability — Examines energy-efficient multimedia processing and AI systems designed to reduce the environmental impact of large-scale...
• Human-centric Multimedia Analysis — Addresses multimedia understanding of human behavior, emotion, gesture, and social interaction using multimodal signals. Human-centred...
• Multimodal Persuasive Analysis and Contextual Trust — Studies multimodal analysis of persuasive content in media and online platforms, with emphasis on measuring...
• Joint Audio-Video Comprehension and Generation — Explores unified models for understanding and generating synchronized audio and video content across diverse multimedia...
• Multimedia Computing for Health and Medicine — Applies multimedia computing, computer vision, and multimodal learning to clinical imaging, patient monitoring, and health...
• Multimedia Content Analysis in Sports — Covers computer vision and multimedia analysis techniques applied to sports video, player tracking, and performance...
• Multimodal and Responsible Affective Computing — Covers affective computing using multimodal signals and generative AI, with attention to ethical and responsible...
• Multi-Sensorial Media and Applications — Investigates multimedia systems that extend beyond audiovisual content to incorporate olfactory, gustatory, and haptic sensory...
• Multimodal Human Understanding for Web and Social Media — Explores multimodal analysis of user-generated web and social media content to understand human intent, sentiment,...
• Neurophysiological Intelligence for Multimedia — Investigates the use of neurophysiological signals such as EEG and eye tracking to build multimedia...
• Quality of Experience in Visual Multimedia — Investigates perceptual quality metrics, subjective evaluation methods, and QoE optimization for streaming and interactive visual...
• Rich Media with Generative AI — Examines generative AI methods for creating, editing, and enhancing rich multimedia content including video, audio,...
• Analysis and Promotion of Heritage Contents — Applies multimedia analysis, recognition, and retrieval techniques to digitize, preserve, and promote cultural heritage artifacts...
• UAVs in Multimedia — Covers multimedia capture, processing, and understanding using unmanned aerial vehicles, with applications in surveillance, mapping,...