English(EN) LF-VideoQA: Evaluating Long-Video Understanding with Long-Form Theory-of-Mind Questions

新数据集LF-VideoQA挑战AI模型进行长篇视频理解

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员推出了LF-VideoQA，这是一个旨在评估视觉-语言模型（VLMs）在叙事视频上的长篇理解能力的新数据集。该数据集侧重于心理理论问题，这些问题需要综合分布在长时间内的信息，平均每个问题时长为23分钟。对最先进VLMs的初步评估显示出显著的挑战，即使是oracle模型也未能给出完整答案，而当前的非oracle模型仅达到oracle模型一半的召回率。结果表明，视觉证据至关重要，召回率是这些模型的主要瓶颈。 AI

影响该数据集将推动AI模型在更深层次、更具上下文理解能力的长篇视频内容方面的发展。

排序理由该集群包含一篇介绍用于评估AI模型的新数据集的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 41 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍用于评估AI模型的新数据集的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Shaden Shaar, Bradon Thymes, Majd Aldaye, Claire Cardie, Bharath Hariharan · 2026-11-04 05:00

LF-VideoQA：用长篇心智理论问题评估长视频理解能力

arXiv:2611.00383v1 Announce Type: cross Abstract: The hardest part of understanding a long video is not pinpointing any one moment but synthesizing many, e.g., answering a question that requires tracking what develops across hours of content and articulating how the pieces fit to…

本文如何被排名

报道来源 [1]

LF-VideoQA：用长篇心智理论问题评估长视频理解能力

相关实体

相关话题