{
  "abstract": "Emerging physical AI systems require low-latency, task-oriented video communication over unreliable channels. We propose a semantic-aware multi-level neural video coding method for robust low-latency video transmission over unreliable channels that are abstracted as multi-level packet erasure channels. Built upon the real-time DCVC-RT neural video codec, the proposed framework introduces a semantic- and feature-aware coding strategy that partitions encoded representations into packets carrying different levels of semantic and latent-feature importance and assigns these packets to different streams, each associated with a priority level when transmitted over unreliable communication channels. We also developed an error-resilient entropy model that removes inter-packet dependencies, allowing each packet to be decoded independently under packet losses. The complete system is trained end-to-end over the abstracted multi-level packet erasure channels, enabling learning of channel-aware representations together with importance-aware packet assignment while facilitating the network for differentiated packet prioritization. Experiments show that the proposed framework significantly improves robustness over baseline DCVC-RT under packet erasures, achieving graceful degradation in less important regions while better preserving task-relevant visual content.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.16279",
  "author_total": 4,
  "authors": [
    {
      "name": "Matin Mortaheb"
    },
    {
      "name": "Homa Esfahanizadeh"
    },
    {
      "name": "Jinfeng Du"
    },
    {
      "name": "Harish Viswanathan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3vj08gprphc0r.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.16279",
  "fulltext_url": null,
  "id": "3vj08gprphc0r",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.16279",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.MM"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1711|Video Coding and Compression Technologies"
    ]
  ],
  "openalex": "W7213407119",
  "pdf_url": "https://arxiv.org/pdf/2609.16279",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3vj08gprphc0r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:45Z",
      "native_id": "2609.16279",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.16279"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission",
  "title_text": "Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:45Z",
  "url": "https://research.draconitic.com/paper/3vj08gprphc0r",
  "venue": "arXiv",
  "versions": []
}