Validation ablations show that visual evidence, procedural context, and difficulty-aware planning improve ranking quality, with the largest gain on complex questions.
Abstract
We describe DAEP, team BIGC's submission to NLPCC 2026 Shared Task 1 Track 3: Difficulty-Aware Temporal Answer Grounding in Video Corpus (DA-TAGVC). The task requires retrieving the target video from 50 candidates and localizing the answer-supporting span. DAEP ranks videos with subtitle, visual, and procedural-context evidence, expands high-scoring anchors into temporal spans, and reranks spans for final output. Its main design is to convert the task-provided simple/complex input label into an inference-time evidence plan controlling modality weights, Top-K aggregation, boundary threshold, expansion length, and reranking strength. In the official evaluation, BIGC ranks first among ten systems with an Average score of 0.2728. Validation ablations show that visual evidence, procedural context, and difficulty-aware planning improve ranking quality, with the largest gain on complex questions.
Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V, and proposes PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition.
Bai-Xuan Xu, Yinyui Xu, Tianshi ZHENG et al.· 2 citations
This submission to the MedReason 2026 challenge is described, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference, and it is found that MCQ retrieval must compare answer \emph{semantics} rather than answer labels.
VideoEvent is a lightweight and efficient training-free framework that segments an input video into question-relevant temporal events and selectively supplements them with low-level visual cues such as background and object layout, making it highly suitable for practical deployment.
Chen-Chen Lin, Ming-Han Lee, Kun-Ru Wu et al.· International Conference on...· 0 citations
Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors, so TempCloze is introduced, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs.
Wen-Qi Pei, Henry Hengyuan Zhao, Yi-Lai Liu et al.· 0 citations
DiaVTG, a novel VTG framework designed to enhance temporal localization precision, is proposed to reformulate temporal localization as a video understanding problem and demonstrates that the training-free method consistently improves performance across various Vid-LLM architectures.
Hong-Yu Huang, Junyi Yang, Sipeng Yang et al.· The Visual Computer· 0 citations
Video-language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be improved under target shift without retraining the models or changing their answers. We collect option-probability lists from three fixed video-language models under four...
Guo-Xiang Ren, Rohitash Chandra· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
