- Submission Deadline: 30 May 2026
This special issue focuses on the convergence of large-scale video analytics and affective computing. With the rapid growth of live and on-demand video, new deep learning and multimodal models enable real-time understanding of events, actions, and emotional cues. By combining visual, audio, and language signals, AI can infer sentiment, engagement, trust and intent, enhancing decision-making in domains such as marketing, healthcare, finance, education, and smart environments. We invite research on scalable video understanding, multimodal fusion, streaming-native AI and MLOps, video-language models, real-time architectures, and responsible AI, aiming to build explainable, fair, and human-centered intelligent systems.
Journal: Information Systems Frontiers, Springer Nature
- Organizers: Andrea Generosi, Luigi Gallo, Valerio De Luca, Maura Mengoni (Marche Polytechnic University), Josef Spjut (NVIDIA)
