From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model

• URL: http://arxiv.org/abs/2512.05277v1
• Date: Thu, 04 Dec 2025 21:57:10 GMT
• Title: From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
• Abstract summary: Temporal understanding in autonomous driving (AD) remains a significant challenge.<n>Prior work has introduced datasets and benchmarks aimed at improving temporal reasoning.<n>No existing benchmark focuses exclusively on unique challenges of temporal understanding in ego-centric AD footage.
• Score: 13.666165551248701
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal understanding in autonomous driving (AD) remains a significant challenge, even for recent state-of-the-art (SoTA) Vision-Language Models (VLMs). Prior work has introduced datasets and benchmarks aimed at improving temporal reasoning, but these have emphasized other video content, including sports, cooking, and movies. No existing benchmark focuses exclusively on the unique challenges of temporal understanding in ego-centric AD footage. To fill this gap, the Temporal Understanding in Autonomous Driving (TAD) benchmark is presented, which evaluates VLMs' ability to capture the dynamic relationships between actions in AD. TAD comprises nearly 6,000 question-answer (QA) pairs, spanning 7 human-designed tasks. In addition, an evaluation is performed that consists of 9 closed- and open-source generalist models as well as SoTA AD specialist models. When applied to TAD, current SoTA models demonstrated substandard accuracies, largely due to imperfect fine-grained motion understanding. To improve motion understanding and overall accuracy on TAD, two novel training-free solutions are proposed: Scene-CoT, that leverages Chain-of-Thought (CoT) and TCogMap, which incorporates an ego-centric temporal cognitive map. The proposed approaches are integrated with existing VLMs and improve average accuracy on TAD by up to 17.72%. By introducing TAD, benchmarking multiple SoTA models, and proposing effective enhancements, this work aims to catalyze future research on temporal understanding in AD. The benchmark and evaluation code are available at \href{https://huggingface.co/datasets/vbdai/TAD}{Hugging Face} and \href{https://github.com/vbdi/tad_bench}{Github}, respectively.

Related papers

• EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding [12.811023931580523]
  EgoSAT is the first comprehensive benchmark for egocentric video reasoning in streaming settings.<n>It is designed to evaluate the capabilities of modern vision-language models (VLMs)<n>EgoSAT contains 1,997 unique videos spanning 165 hours of egocentric footage and around 4,800 high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2026-06-23T10:59:25Z)
• DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving [15.87281823665284]
  We introduce DriveSpatial, a benchmark of 15.6K-verified QA pairs across 20 tasks from five large-scale autonomous driving datasets.<n>Unlike prior benchmarks DriveSpatial is generated from a dynamic multi-language scene graph that encodes object states, spatial relations, interactions, camera visibility, and temporal correspondences.<n>We find that the strongest model trails humans by 28.4 points, with Cognitive Scene Construction emerging as the key bottleneck.
  arXiv  Detail & Related papers  (2026-05-22T02:52:06Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding [22.43740206690383]
  Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals.<n>VAGU is the first benchmark to integrate anomaly understanding and grounding.<n>We propose Glance then Scrutinize (GtS), a training-free framework guided by textual prompts.<n>We also propose the JeAUG metric, which jointly evaluates semantic interpretability and temporal precision.
  arXiv  Detail & Related papers  (2025-07-29T05:17:48Z)
• HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding [120.84817886550765]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos.<n>Existing human-centric benchmarks predominantly emphasize video generation quality and action recognition, while overlooking essential perceptual and cognitive abilities required in human-centered scenarios.<n>We propose a rigorously curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric video understanding.
  arXiv  Detail & Related papers  (2025-07-07T11:52:24Z)
• STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving [16.602141801221364]
  STSBench is a framework to benchmark holistic understanding of vision-language models (VLMs) for autonomous driving.<n>The benchmark features 43 diverse scenarios spanning multiple views, resulting in 971 human-verified multiple-choice questions.<n>A thorough evaluation uncovers shortcomings in existing models' ability to reason about fundamental traffic dynamics in complex environments.
  arXiv  Detail & Related papers  (2025-06-06T16:25:22Z)
• Dynamic-Aware Video Distillation: Optimizing Temporal Resolution Based on Video Semantics [68.85010825225528]
  Video datasets present unique challenges due to the presence of temporal information and varying levels of redundancy across different classes.<n>Existing DD approaches assume a uniform level of temporal redundancy across all different video semantics, which limits their effectiveness on video datasets.<n>We propose Dynamic-Aware Video Distillation (DAViD), a Reinforcement Learning (RL) approach to predict the optimal Temporal Resolution of the synthetic videos.
  arXiv  Detail & Related papers  (2025-05-28T11:43:58Z)
• Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos [51.8995932557911]
  EgoTempo is a dataset designed to evaluate temporal understanding in the egocentric domain.<n>We show that state-of-the-art Multi-Modal Large Language Models (MLLMs) on benchmarks achieve remarkably high performance using just text or a single frame as input.<n>We hope EgoTempo will catalyze new research in the field and inspire models that better capture the complexity of temporal dynamics.
  arXiv  Detail & Related papers  (2025-03-17T18:50:36Z)
• ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events [0.20132569095596248]
  We present ChronoSense, a new benchmark for evaluating Large Language Models' temporal understanding.<n>We assess the performance of seven recent LLMs using this benchmark and the results indicate that models handle Allen relations, even symmetrical ones, quite differently.<n>Overall, the models' low performance highlights the need for improved temporal understanding in LLMs.
  arXiv  Detail & Related papers  (2025-01-06T14:27:41Z)
• Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models [44.99833362998488]
  Temporal Semantic Alignment via Dynamic Prompting (TSADP) is a novel framework that enhances temporal reasoning capabilities.<n>We evaluate TSADP on the VidSitu dataset, augmented with enriched temporal annotations.<n>Our analysis highlights the robustness, efficiency, and practical utility of TSADP, making it a step forward in the field of video-language understanding.
  arXiv  Detail & Related papers  (2024-12-16T02:37:58Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)
• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models [75.42002690128486]
  TemporalBench is a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. It consists of 10K video question-answer pairs, derived from 2K high-quality human annotations detailing the temporal dynamics in video clips. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)

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.