POVQA: 基于偏好的视频问答与数据效率的推理
POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
AI总结：
提出POVQA方法，通过时间池化压缩视频帧、监督微调加偏好优化，在长视频问答中实现数据高效推理。
摘要：
长视频多模态问答需要对视觉证据和对话进行结构化推理，但大型视觉语言模型（LVLMs）受限于上下文窗口和计算限制。我们提出POVQA，将每秒压缩为时间池化图像（1 fps池化图像），以在固定token预算下保持密集的时间覆盖。然后，我们在推理+答案目标上对Qwen2.5-VL-7B进行监督微调（SFT），并可选地应用直接偏好优化（DPO）进行偏好对齐。我们引入ReasonVQA作为初步诊断数据集，包含12部电影和239个人工标注的QA+推理三元组，用于在压缩下对长上下文多模态推理进行受控分析。在ReasonVQA上，SFT将最佳纯池化基线从0.212 F1提升至0.550 F1，表明池化证据加推理监督在此设置中提供了主要性能提升。在零样本迁移中，POVQA在SFT+DPO后在TVQA上也达到64.7%。这些结果是初步的：ReasonVQA规模小，池化可能丢失细粒度时间顺序，且DPO效果在不同设置中并非一致正面。代码、数据集和额外定性评估见\href{https://povqa.github.io}{https://povqa.github.io}。
英文摘要：
Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense temporal coverage under a fixed token budget. We then train Qwen2.5-VL-7B with supervised fine-tuning (SFT) on rationale+answer targets, and optionally apply Direct Preference Optimization (DPO) for preference alignment. We introduce ReasonVQA as a pilot diagnostic dataset with 12 movies and 239 human-annotated QA+rationale triplets for controlled analysis of long-context multimodal reasoning under compression. On ReasonVQA, SFT improves the best pooled-only baseline from 0.212 to 0.550 F1, showing that pooled evidence plus rationale supervision provides the main performance gains in this setting. In zero-shot transfer, POVQA also reaches 64.7\% on TVQA after SFT+DPO. These results are preliminary: ReasonVQA is small, pooling can lose fine-grained temporal order, and DPO effects are not uniformly positive across settings. Code, dataset, and additional qualitative evaluations are available at \href{https://povqa.github.io}{https://povqa.github.io}.
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。
