Metraipolis › archive › dc_ca5a034efd89

TempCloze: Can Video-LLMs Identify the Missing Middle? — arXiv:2609.01515

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01515
License (as archived): CC0-1.0
Archived: 2026-10-17T06:34:24.678Z
SHA-256 of the archived text: 428473613411735de5ff04e22c8660d88527fe668c5c362d96ffdd73f5b13e0a
Stable URL of this page: https://metraipolis.com/documento/dc_ca5a034efd89

How to cite

TempCloze: Can Video-LLMs Identify the Missing Middle? — arXiv:2609.01515 — arXiv (en), https://arxiv.org/abs/2609.01515 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca5a034efd89 (Metraipolis archive dc_ca5a034efd89, sha256 428473613411735de5ff04e22c8660d88527fe668c5c362d96ffdd73f5b13e0a)

BibTeX

@misc{dcca5a034efd89,
  title = {TempCloze: Can Video-LLMs Identify the Missing Middle? — arXiv:2609.01515},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01515},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca5a034efd89; sha256 428473613411735de5ff04e22c8660d88527fe668c5c362d96ffdd73f5b13e0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01515. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01515 — 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 2026-10-17T06:15:12.907Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).