Abstract
<jats:p>This volume focuses on computational learning techniques and adaptive processing models for real-time image and video interpretation, visual perception, and motion intelligence. Key areas include spatiotemporal feature modeling, gesture recognition, scene understanding, attention based video reasoning, immersive visual experience generation, and streaming optimization. The volume encourages contributions related to object tracking, event detection, structured video representation, real-time encoding efficiency, augmented visual environments, and scalable surveillance analytics. The objective is to enable intelligent visual systems capable of perception, interpretation, and dynamic interaction in real-time expressive environments.</jats:p>