# TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living Source: [TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living]() Collection index: [llms.txt]() Data updated: 2026-06-20T05:00:13.953Z Authors: Arkaprava Sinha, Dominick Reilly, Siddharth Krishnan, Hieu Le, Srijan Das Published: 2026-06-18T17:59:48.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Long-form Video Question Answering on OPENTSUBENCH](): Long-form Video Question Answering; OPENTSUBENCH; Object Centric Accuracy: 53.9. - [Temporal Grounding on Charades-STA (R@0.3, R@0.5, R@0.7, mIoU)](): Temporal Grounding; Charades-STA; mIoU: not recorded. ## Original sources and implementation [Original paper]() [PDF]()