TimeProVe: 先提出后验证，实现日常活动中的高效长视频时间推理
TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living
AI总结：
提出TimeProVe框架，先通过轻量模块生成基于动作的候选假设，再调用昂贵VLM验证，在长视频问答中降低75%VLM调用和93%推理成本，性能提升7.3%。
摘要：
长视频问答（LVQA）需要在数小时未修剪的视频中识别稀疏的、与查询相关的证据。现有方法要么使用大型视觉语言模型（VLM）密集处理视频，导致计算成本过高，要么依赖稀疏的基于字幕的推理，这往往会遗漏时间局部化和以运动为中心的证据。我们提出TimeProVe，一种用于长视频中时间基础推理的高效混合框架。TimeProVe首先使用轻量模块生成基于动作的答案-证据假设，随后仅调用昂贵的VLM进行针对性验证。我们框架的核心在于基于动作的候选证据（ACE）模块，该模块通过轻量级LLM推理将时间局部化的动作转换为查询条件化的候选答案和支持证据窗口。我们进一步引入OpenTSUBench（OTB），一个开放基准测试，旨在评估真实世界日常活动（ADL）场景中的时间基础推理。实验表明，TimeProVe在OTB上比最强基线高出7.3%，同时减少了75%的VLM调用和93%的推理成本。此外，在没有显式时间基础训练的情况下，TimeProVe在Charades-STA上取得了竞争性性能，并在结合基础VLM增强时达到了最先进的结果。
英文摘要：
Long Video Question Answering (LVQA) requires identifying sparse, query-relevant evidence within hours-long untrimmed videos. Existing approaches either process videos densely with large vision-language models (VLMs), incurring prohibitive computational cost, or rely on sparse caption-based reasoning, which often misses temporally localized and motion-centric evidence. We introduce TimeProVe, a cost-efficient hybrid framework for temporally grounded reasoning in long videos. TimeProVe first employs lightweight modules to generate action-grounded answer--evidence hypotheses and subsequently invokes an expensive VLM only for targeted verification. The core of our framework lies in the Action-based Candidate Evidence (ACE) module, which converts temporally localized actions into query-conditioned candidate answers and supporting evidence windows through lightweight LLM reasoning. We further introduce OpenTSUBench (OTB), an open-ended benchmark designed to evaluate temporally grounded reasoning in real-world Activities of Daily Living (ADL) scenarios. Experiments show that TimeProVe outperforms the strongest baseline on OTB by 7.3%, while reducing VLM calls by 75% and inference cost by 93%. Furthermore, without explicit temporal grounding training, TimeProVe achieves competitive performance on Charades-STA, and reaches state-of-the-art results when enhanced with grounding VLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
