根据题目难易度动态调整证据权重，提升医学视频问答定位准确率。
DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding
- 按题目难度自动分配视觉、字幕、流程上下文证据权重
- 复杂问题定位准确率提升显著，整体平均得分0.2728
- 适合医学视频理解与智能问答系统研发者参考
本文介绍团队BIGC在NLPCC 2026共享任务1赛道3——医学视频语料库中难度感知的时间答案定位（DA-TAGVC）中的提交方案DAEP。该任务要求从50个候选视频中检索目标视频，并定位支持答案的时间片段。DAEP通过字幕、视觉和流程上下文证据对视频进行排序，将高分锚点扩展为时间区间，并对区间进行重排序以输出最终结果。其核心设计是将任务提供的简单/复杂输入标签转化为推理时的证据规划，动态控制模态权重、Top-K聚合、边界阈值、扩展长度和重排序强度。在官方评测中，BIGC系统以0.2728的平均得分位列十支参赛系统第一。验证消融实验表明，视觉证据、流程上下文及难度感知规划均提升了排名质量，尤其在复杂问题上收益最大。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。