{"ID":5937066,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T13:44:59.978947637Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05093","arxiv_id":"2607.05093","title":"Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing","abstract":"The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generative AI-enabled framework for semantic video communication addressing two critical challenges: efficient hierarchical temporal modeling for bandwidth-constrained transmission and robust semantic alignment between video content and natural language queries at network edge devices. Our approach introduces a multi-scale temporal convolutional encoder that captures motion patterns across different temporal granularities with O(T) complexity suitable for resource-constrained IoT deployments. We further propose a capsule-based dynamic routing mechanism that iteratively refines segment-query associations, enabling flexible modeling of non-monotonic semantic alignments essential for goal-oriented communication. These components are unified through a multi-task learning objective optimizing temporal boundary regression, cross-modal alignment, and capsule diversity. Experiments on ActivityNet Captions demonstrate significant improvements, achieving 42.9% Recall@0.5 and 41.1% mean IoU while maintaining computational efficiency critical for edge deployment.","short_abstract":"The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generative AI-enabled framework for semantic video communication addressing two critical challenges: efficient hierarchical temporal modeling for bandwidth-constrained transmis...","url_abs":"https://arxiv.org/abs/2607.05093","url_pdf":"https://arxiv.org/pdf/2607.05093v1","authors":"[\"Gengtian Shi\",\"Jinze Yu\",\"Chenhao Wu\",\"Shaofei Wang\",\"Eiji Fukuzawa\",\"Junjie Tang\",\"Hiroshi Onoda\",\"Jiang Liu\"]","published":"2026-07-06T13:52:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}