Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA

• URL: http://arxiv.org/abs/2606.01106v1
• Date: Sun, 31 May 2026 08:49:04 GMT
• Title: Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
• Abstract summary: TimeLogicQA evaluates whether video question answering systems can reason over temporal relations.<n>We address this task with a visual evidence routing pipeline that separates perception from symbolic temporal reasoning.
• Score: 15.724849094439987
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Question-Aware Evidence Ledgers for Video Relational Reasoning [49.15616982043187]
  We present a test-time reasoning pipeline built around a strong GPT-5.5 video QA solver and a set of question-aware evidence ledgers.<n>The pipeline achieves 92.95% overall accuracy and 93.79% macro accuracy on the challenge test split.
  arXiv  Detail & Related papers  (2026-06-01T17:18:03Z)
• Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA Challenge [15.724849094439987]
  We present an inference-only system built around adaptive test-time computation.<n>The system first answers each question with a direct video-language model pass, then uses multiple lightweight views to find unstable questions.<n>On the test split, the final system obtains 90.07 average accuracy and 87.81 macro average accuracy.
  arXiv  Detail & Related papers  (2026-05-31T08:45:06Z)
• NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning [25.109179044490844]
  Long-Form Question Answering (LVQA) poses challenges beyond traditional visual question answering (VQA)<n> Vanilla approaches, which sample frames uniformly and feed them to a VLM with the question, incur significant token overhead.<n>NeuS-QA translates a natural language question into a formal temporal logic expression, constructs a video automaton from frame-level semantic propositions.
  arXiv  Detail & Related papers  (2025-09-22T17:15:13Z)
• TimeLogic: A Temporal Logic Benchmark for Video QA [64.32208175236323]
  We introduce the TimeLogic QA (TLQA) framework to automatically generate temporal logical questions.<n>We leverage 4 datasets, STAR, Breakfast, AGQA, and CrossTask, and generate 2k and 10k QA pairs for each category.<n>We assess the VideoQA model's temporal reasoning performance on 16 categories of temporal logic with varying temporal complexity.
  arXiv  Detail & Related papers  (2025-01-13T11:12:59Z)
• Visual Causal Scene Refinement for Video Question Answering [117.08431221482638]
  We present a causal analysis of VideoQA and propose a framework for cross-modal causal reasoning, named Visual Causal Scene Refinement (VCSR) Our VCSR involves two essential modules, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention. Experiments on the NExT-QA, Causal-VidQA, and MSRVTT-QA datasets demonstrate the superiority of our VCSR in discovering visual causal scene and achieving robust video question answering.
  arXiv  Detail & Related papers  (2023-05-07T09:05:19Z)
• Locate before Answering: Answer Guided Question Localization for Video Question Answering [70.38700123685143]
  LocAns integrates a question locator and an answer predictor into an end-to-end model. It achieves state-of-the-art performance on two modern long-term VideoQA datasets.
  arXiv  Detail & Related papers  (2022-10-05T08:19:16Z)
• Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering [73.11017833431313]
  Multi-modal video question answering aims to predict correct answer and localize the temporal boundary relevant to the question. We devise a weakly supervised question grounding (WSQG) setting, where only QA annotations are used. We transform the correspondence between frames and subtitles to Frame-Subtitle (FS) self-supervision, which helps to optimize the temporal attention scores.
  arXiv  Detail & Related papers  (2022-09-08T07:20:51Z)
• NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions [80.60423934589515]
  We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark. We set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. We find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning.
  arXiv  Detail & Related papers  (2021-05-18T04:56:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.