Metraipolis › archive › dc_3d2ee3fe3979

Emotion Understanding in Streaming Video with Trajectory-Aware Reliability — arXiv:2608.26786

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26786
License (as archived)
CC0-1.0
Archived
2026-10-17T18:55:44.929Z
SHA-256 of the archived text
ca90cbcdd6340f1418e90abc793d9afac20d4196b64e6fc7458a0ba65fed6375
Stable URL of this page
https://metraipolis.com/documento/dc_3d2ee3fe3979

How to cite

Emotion Understanding in Streaming Video with Trajectory-Aware Reliability — arXiv:2608.26786 — arXiv (en), https://arxiv.org/abs/2608.26786 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d2ee3fe3979 (Metraipolis archive dc_3d2ee3fe3979, sha256 ca90cbcdd6340f1418e90abc793d9afac20d4196b64e6fc7458a0ba65fed6375)
BibTeX
@misc{dc3d2ee3fe3979,
  title = {Emotion Understanding in Streaming Video with Trajectory-Aware Reliability — arXiv:2608.26786},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26786},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d2ee3fe3979; sha256 ca90cbcdd6340f1418e90abc793d9afac20d4196b64e6fc7458a0ba65fed6375},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26786. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video emotion understanding is commonly studied as an offline classification problem, where the complete video segment is available before prediction. Real-time interaction, however, requires emotion decisions from incomplete and evolving evidence. This paper studies streaming video emotion understanding as a reliability-aware decision process over evolving emotion beliefs. In this setting, a single confident prefix prediction can still be unreliable when the underlying belief trajectory is unstable or repeatedly switches across emotion classes. We propose TRACE, a trajectory-aware reliability framework that forms low-latency emotion beliefs from streaming audio prefixes, estimates reliability from confidence, entropy, stability, and class-switching patterns, and selectively invokes contextual belief reinterpretation with visual, textual, and neighboring-utterance evidence. TRACE keeps stable cases in the low-latency online pathway while allocating stronger multimodal reasoning to uncertain cases that remain ambiguous. Experiments on StreamMER, MELD, and MER2024 show that TRACE improves the accuracy-cost trade-off, retaining most full-context gains while reducing unnecessary contextual reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.MM).
Categorie arXiv: Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.26786 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T18:31:14.481Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).