InsightVQA: 高维情感认知视觉问答基准
InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark
AI总结：
为解决现有基准仅关注情感识别而缺乏深层认知推理的问题，提出大规模层次化视觉问答数据集InsightVQA，包含725K问答对，并构建评估基准InsightVQA-Bench和基线模型InsightNet。
摘要：
视觉情感理解要求模型不仅识别情感状态，还要理解其产生原因并进行更高层次的认知推理。然而，现有基准主要关注情感识别，对基于依据的理解和面向响应的分析支持有限。为弥补这一差距，我们引入了 extbf{InsightVQA}，一个用于情感理解和认知推理的层次化视觉问答大规模数据集。我们从六个公开来源收集的351K图像出发，应用严格的多阶段过滤流程，筛选出138K高置信度图像。每张图像在三个层次上进行标注：用于情感和效价识别的感知QA、通过约束引导生成从视觉触发提取构建的基于依据的理解QA，以及以响应意图预测和序列洞察推理为中心的认知QA。总计，InsightVQA包含725K个问答对。我们还提出了 extbf{InsightVQA-Bench}，一个包含30K样本的高质量评估基准，用于细粒度评估。为支持评估，我们引入了 extbf{InsightNet}，一个针对多模态大语言模型的情感调优基线。结果表明，InsightVQA对基于依据的情感理解和推理提出了重大挑战。
英文摘要：
Visual emotion understanding requires models not only to recognize emotional states, but also to why they arise and perform higher-level cognitive reasoning. However, existing benchmarks mainly focus on emotion recognition, offering limited support for grounded understanding and response-oriented analysis. To address this gap, we introduce \textbf{InsightVQA}, a large-scale dataset for hierarchical visual question answering on emotion understanding and cognitive reasoning. Building from 351K images collected from six public sources, we apply a rigorous multi-stage filtering pipeline to curate 138K high-confidence images. Each image is annotated at three hierarchical levels: perception QA for emotion and valence recognition, grounded understanding QA constructed from visual trigger extraction through constraint-guided generation, and cognition QA centered on response intent prediction and sequential insight reasoning. In total, InsightVQA contains 725K QA pairs. We further present \textbf{InsightVQA-Bench}, a high-quality evaluation benchmark comprising 30K samples for fine-grained evaluation. To support evaluation, we introduce \textbf{InsightNet}, an emotion-tuned baseline for MLLMs. Results demonstrate that InsightVQA poses significant challenges for grounded emotion understanding and reasoning.
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。
