Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission

The paper introduces a semantic‑aware multi‑level neural video codec designed for low‑latency, task‑oriented video transmission over unreliable channels. It builds on the real‑time DCVC‑RT codec by partitioning encoded representations into packets of varying semantic and feature importance, assigning them to priority streams, and employing an error‑resilient entropy model that removes inter‑packet dependencies. Experiments demonstrate that this framework improves robustness against packet erasures, achieving graceful degradation in less important regions while preserving task‑relevant visual content.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.