UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics

• URL: http://arxiv.org/abs/2602.21137v1
• Date: Tue, 24 Feb 2026 17:33:12 GMT
• Title: UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics
• Authors: Joseph Raj Vishal, Nagasiri Poluri, Katha Naik, Rutuja Patil, Kashyap Hegde Kota, Krishna Vinod, Prithvi Jai Ramesh, Mohammad Farhadi, Yezhou Yang, Bharatesh Chakravarthi,
• Abstract summary: This paper introduces Urban Dynamics VideoQA, a benchmark dataset that captures the unscripted real-world behavior of dynamic urban scenes.<n> UDVideoQA is curated from 16 hours of traffic footage recorded at multiple city intersections under diverse traffic, weather, and lighting conditions.<n>The dataset contains 28K question-answer pairs generated across 8 hours of densely annotated video, averaging one question per second.
• Score: 19.634532810889507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence [70.2803680525165]
  We introduce Open-o3 Video, a non-agent framework that integrates explicit evidence into video reasoning.<n>The model highlights key objects and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations.<n>On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mL timestamp by 24.2%.
  arXiv  Detail & Related papers  (2025-10-23T14:05:56Z)
• ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts [56.75723197779384]
  ARC-Hunyuan-Video is a multimodal model that processes visual, audio, and textual signals end-to-end for structured comprehension.<n>Our model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning.
  arXiv  Detail & Related papers  (2025-07-28T15:52:36Z)
• Object-centric Video Question Answering with Visual Grounding and Referring [43.963739052764595]
  We introduce a VideoLLM model, capable of performing both object referring for input and grounding for output in video reasoning tasks.<n>We also propose STOM, a novel approach that propagates arbitrary visual prompts input at any single timestamp to the remaining frames within a video.<n>We conduct comprehensive experiments on VideoInfer and other existing benchmarks across video question answering and referring object segmentation.
  arXiv  Detail & Related papers  (2025-07-25T18:11:23Z)
• InterAct-Video: Reasoning-Rich Video QA for Urban Traffic [21.849445040376537]
  Deep learning has advanced video-based traffic monitoring through question answering (VideoQA) models.<n>Existing VideoQA models struggle with the complexity of real-world traffic scenes.<n>InterAct VideoQA is a curated dataset designed to benchmark and enhance VideoQA models for traffic monitoring tasks.
  arXiv  Detail & Related papers  (2025-07-19T20:30:43Z)
• Advancing Egocentric Video Question Answering with Multimodal Large Language Models [10.111636068164504]
  Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement.<n>This paper systematically evaluates both proprietary and open-source Multimodal Large Language Models (MLLMs) on QaEgo4Dv2.
  arXiv  Detail & Related papers  (2025-04-06T16:58:23Z)
• Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks [0.0]
  This study evaluates state-of-the-art VideoQA models using non-benchmark synthetic and real-world traffic sequences.<n>VideoLLaMA-2 advances with 57% accuracy, particularly in compositional reasoning and consistent answers.<n>These findings underscore VideoQA's potential in traffic monitoring but also emphasize the need for improvements in multi-object tracking, temporal reasoning, and compositional capabilities.
  arXiv  Detail & Related papers  (2024-12-02T05:15:32Z)
• Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs [20.168429351519055]
  Video understanding is a crucial next step for multimodal large language models (LMLMs)<n>We propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation.<n>We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities.
  arXiv  Detail & Related papers  (2024-06-13T17:50:05Z)
• Perception Test: A Diagnostic Benchmark for Multimodal Video Models [78.64546291816117]
  We propose a novel multimodal video benchmark to evaluate the perception and reasoning skills of pre-trained multimodal models. The Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities. The benchmark probes pre-trained models for their transfer capabilities, in a zero-shot / few-shot or limited finetuning regime.
  arXiv  Detail & Related papers  (2023-05-23T07:54:37Z)
• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries [89.24431389933703]
  We present the Query-based Video Highlights (QVHighlights) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.
  arXiv  Detail & Related papers  (2021-07-20T16:42:58Z)
• DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering [75.01757991135567]
  We propose a Dual-Visual Graph Reasoning Unit (DualVGR) which reasons over videos in an end-to-end fashion. Our DualVGR network achieves state-of-the-art performance on the benchmark MSVD-QA and SVQA datasets.
  arXiv  Detail & Related papers  (2021-07-10T06:08:15Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.