Metraipolis › archive › dc_4f1648044203

Interpretable Temporal Video Reasoning with EventGraph and EventField — arXiv:2609.13258

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13258
License (as archived)
CC0-1.0
Archived
2026-10-15T23:16:41.830Z
SHA-256 of the archived text
f102396400c049cb17ce83f51c8ff3370b0c6b58a5d45f4957fe1530c0aa6d7c
Stable URL of this page
https://metraipolis.com/documento/dc_4f1648044203

How to cite

Interpretable Temporal Video Reasoning with EventGraph and EventField — arXiv:2609.13258 — arXiv (en), https://arxiv.org/abs/2609.13258 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f1648044203 (Metraipolis archive dc_4f1648044203, sha256 f102396400c049cb17ce83f51c8ff3370b0c6b58a5d45f4957fe1530c0aa6d7c)
BibTeX
@misc{dc4f1648044203,
  title = {Interpretable Temporal Video Reasoning with EventGraph and EventField — arXiv:2609.13258},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13258},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f1648044203; sha256 f102396400c049cb17ce83f51c8ff3370b0c6b58a5d45f4957fe1530c0aa6d7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13258. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 \times 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.13258 — 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 2026-10-15T22:51:09.997Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).