UDVideoQA: 一个用于城市动态多对象时空推理的交通视频问答数据集
UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics
AI总结：
UDVideoQA是一个用于城市动态多对象时空推理的交通视频问答数据集，通过统一标注流程生成28K问题-答案对，评估视觉定位和因果推理能力。
摘要：
理解复杂多主体的城市交通动态仍然是视频语言模型面临的基本挑战。本文介绍了Urban Dynamics VideoQA，一个基准数据集，捕捉动态城市场景的非剧本现实行为。UDVideoQA是从16小时的交通录像中精心挑选的，这些录像是在多个城市交叉口在多样的交通、天气和光照条件下录制的。它采用事件驱动的动态模糊技术来确保隐私保护而不影响场景保真度。使用统一的标注流程，该数据集包含28,000个问题-答案对，这些对是基于8小时密集标注的视频生成的，平均每秒生成一个问题。其分类遵循层次推理级别，从基本理解和归因扩展到事件推理、反向推理和反事实推理，使系统能够系统地评估视觉定位和因果推理。全面的实验在UDVideoQA上基准测试了10个最先进的VideoLMs，并在互补的视频问题生成基准上测试了8个模型。结果揭示了一个持续的感知-推理差距，显示在抽象推理方面表现优异的模型在基本视觉定位上往往失败。虽然Gemini Pro在零样本准确率上表现最高，但对较小的Qwen2.5-VL 7B模型在UDVideoQA上进行微调可以缩小这一差距，使其性能与专有系统相当。在VideoQGen中，Gemini 2.5 Pro、Qwen3 Max生成了最相关和复杂的问题，尽管所有模型都表现出有限的语言多样性，凸显了人本评价的必要性。UDVideoQA套件，包括数据集、标注工具以及VideoQA和VideoQGen的基准测试，为推进稳健、隐私保护和现实多模态推理提供了基础。UDVideoQA可在https://ud-videoqa.github.io/UD-VideoQA/UD-VideoQA/上获取。
英文摘要：
Understanding the complex, multi-agent dynamics of urban traffic remains a fundamental challenge for video language models. This paper introduces Urban Dynamics VideoQA, a benchmark dataset that captures the unscripted real-world behavior of dynamic urban scenes. UDVideoQA is curated from 16 hours of traffic footage recorded at multiple city intersections under diverse traffic, weather, and lighting conditions. It employs an event-driven dynamic blur technique to ensure privacy preservation without compromising scene fidelity. Using a unified annotation pipeline, the dataset contains 28K question-answer pairs generated across 8 hours of densely annotated video, averaging one question per second. Its taxonomy follows a hierarchical reasoning level, spanning basic understanding and attribution to event reasoning, reverse reasoning, and counterfactual inference, enabling systematic evaluation of both visual grounding and causal reasoning. Comprehensive experiments benchmark 10 SOTA VideoLMs on UDVideoQA and 8 models on a complementary video question generation benchmark. Results reveal a persistent perception-reasoning gap, showing models that excel in abstract inference often fail with fundamental visual grounding. While models like Gemini Pro achieve the highest zero-shot accuracy, fine-tuning the smaller Qwen2.5-VL 7B model on UDVideoQA bridges this gap, achieving performance comparable to proprietary systems. In VideoQGen, Gemini 2.5 Pro, and Qwen3 Max generate the most relevant and complex questions, though all models exhibit limited linguistic diversity, underscoring the need for human-centric evaluation. The UDVideoQA suite, including the dataset, annotation tools, and benchmarks for both VideoQA and VideoQGen, provides a foundation for advancing robust, privacy-aware, and real-world multimodal reasoning. UDVideoQA is available at https://ud-videoqa.github.io/UD-VideoQA/UD-VideoQA/.
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。
