Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2606.01106 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917551258206208 |
|---|---|
| author | Sun, Yuyang Wu, Yongliang Zhu, Xingyu Chen, Yuxia Jiang, Zhenxiang Ji, Yangguang Zhu, Wenbo Shi, Yanxi Wu, Jay Wang, Shuo Yang, Xu |
| author_facet | Sun, Yuyang Wu, Yongliang Zhu, Xingyu Chen, Yuxia Jiang, Zhenxiang Ji, Yangguang Zhu, Wenbo Shi, Yanxi Wu, Jay Wang, Shuo Yang, Xu |
| contents | TimeLogicQA evaluates whether video question answering systems can reason over temporal relations such as event existence, ordering, persistence, boundary conditions, and overlap. We address this task with a visual evidence routing pipeline that separates perception from symbolic temporal reasoning. The system first parses each question into event targets, answer mode, candidate options, and temporal operators. It then routes videos according to duration and operator difficulty, using ordered full-frame evidence for short clips and event-focused candidate windows for long videos. A multimodal large language model produces structured visual evidence for the relevant events, while programmatic verifiers recover dense action intervals and a deterministic reducer applies operator-specific temporal rules to produce the final answer. Conservative fusion accepts an answer only when the visual evidence, temporal program, and confidence checks agree, reducing noisy answer flips. On the official test evaluation, our final system achieves an AvgAcc of 81.8. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01106 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA Sun, Yuyang Wu, Yongliang Zhu, Xingyu Chen, Yuxia Jiang, Zhenxiang Ji, Yangguang Zhu, Wenbo Shi, Yanxi Wu, Jay Wang, Shuo Yang, Xu Computer Vision and Pattern Recognition TimeLogicQA evaluates whether video question answering systems can reason over temporal relations such as event existence, ordering, persistence, boundary conditions, and overlap. We address this task with a visual evidence routing pipeline that separates perception from symbolic temporal reasoning. The system first parses each question into event targets, answer mode, candidate options, and temporal operators. It then routes videos according to duration and operator difficulty, using ordered full-frame evidence for short clips and event-focused candidate windows for long videos. A multimodal large language model produces structured visual evidence for the relevant events, while programmatic verifiers recover dense action intervals and a deterministic reducer applies operator-specific temporal rules to produce the final answer. Conservative fusion accepts an answer only when the visual evidence, temporal program, and confidence checks agree, reducing noisy answer flips. On the official test evaluation, our final system achieves an AvgAcc of 81.8. |
| title | Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.01106 |