基于视频锚定蕴含树推理的常识视频问答
Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning
AI总结：
提出首个视频锚定蕴含树推理方法，通过四步显式锚定视频片段，增强VQA推理并去偏，实验验证其跨基准、模型和推理类型的有效性。
摘要：
本文提出了首个用于常识视频问答（VQA）的视频锚定蕴含树推理方法。尽管大型视觉语言模型（VLMs）取得了显著进展，但人们日益担忧它们会学习视频与可能答案之间的虚假相关性，这种担忧因其黑盒特性及残留的基准测试偏差而加剧。我们的方法通过四个步骤将VQA任务明确锚定到视频片段：蕴含树构建、视频语言蕴含验证、树推理和动态树扩展。该方法的一个关键优势是其对当前基于视频和图像的VLMs在不同推理类型上的通用性。为支持公平评估，我们设计了一种基于大语言模型的去偏程序，该程序重写VQA基准答案集以强制模型进行推理。在现有基准和去偏基准上的系统实验突显了我们的方法组件在不同基准、VLMs和推理类型上的影响。
英文摘要：
This paper proposes the first video-grounded entailment tree reasoning method for commonsense video question answering (VQA). Despite the remarkable progress of large visual-language models (VLMs), there are growing concerns that they learn spurious correlations between videos and likely answers, reinforced by their black-box nature and remaining benchmarking biases. Our method explicitly grounds VQA tasks to video fragments in four steps: entailment tree construction, video-language entailment verification, tree reasoning, and dynamic tree expansion. A vital benefit of the method is its generalizability to current video and image-based VLMs across reasoning types. To support fair evaluation, we devise a de-biasing procedure based on large-language models that rewrites VQA benchmark answer sets to enforce model reasoning. Systematic experiments on existing and de-biased benchmarks highlight the impact of our method components across benchmarks, VLMs, and reasoning types.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
