Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline

• URL: http://arxiv.org/abs/2608.08867v1
• Date: Sun, 09 Aug 2026 19:08:56 GMT
• Title: Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline
• Abstract summary: ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint.<n>We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking.<n>On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504.
• Score: 0.10874100424278173
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traffic surveillance cameras capture accidents continuously, yet converting raw CCTV footage into structured event records that pinpoint when, where, and what type of collision occurred remains unsolved at scale. The ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint: no labeled real-world training data is available. We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking. A first pass sparsely samples the full clip to anchor the collision moment in time; a second pass re-examines a tight window around that estimate using frames annotated with stable vehicle identities and normalized bounding-box coordinates, which gives the model both a visual overlay and an explicit numeric description of the same scene. On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504, surpassing all organizer-published baselines including the best multi-model ensemble (0.412) by a 22% relative margin.

Related papers

• Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection [54.03436243843709]
  This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection.<n>The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles.
  arXiv  Detail & Related papers  (2026-09-07T15:16:15Z)
• SynCrash: A Multi-Stage Pipeline for Zero-Shot Accident Detection and Localization in Traffic Surveillance Video [0.0]
  We present SynCrash, a pipeline for zero-shot accident detection, spatial localization, and collision-type classification in CCTV video.<n>Our approach addresses the ACCIDENT at CVPR 2026 Challenge, which requires predicting when an accident occurs, where in the frame the impact happens, and what type of collision it is.
  arXiv  Detail & Related papers  (2026-08-30T12:42:59Z)
• SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation [73.2142090645987]
  SC3-Eval is a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator.<n>We demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison.
  arXiv  Detail & Related papers  (2026-06-17T02:15:46Z)
• A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation [20.309082260025992]
  We propose a framework that bridges the gap between the frame-level temporal risk estimation task and coarsely labelled binary accident datasets.<n>Our method achieves 2nd place in the 2026 CVPR@AUTOPILOT Zero-Shot Accident Anticipation competition.
  arXiv  Detail & Related papers  (2026-06-08T14:25:16Z)
• Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video [0.0]
  Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited.<n>We present a no-fine-tuning pipeline that elicits this joint output from frozen vision-language models.
  arXiv  Detail & Related papers  (2026-05-02T16:05:44Z)
• Instance-level Visual Active Tracking with Occlusion-Aware Planning [61.982298426203165]
  Visual Active Tracking (VAT) aims to control cameras to follow a target in 3D space.<n>VAT faces two key bottlenecks in real-world deployment: confusion from visually similar distractors and severe failure under occlusions.<n>We propose OA-VAT, a unified pipeline with three complementary modules.
  arXiv  Detail & Related papers  (2026-04-23T09:11:50Z)
• ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos [0.0]
  ACCIDENT is a benchmark dataset for traffic accident detection in CCTV footage.<n>It is designed to evaluate models in supervised (IID and OOD) and zero-shot settings.
  arXiv  Detail & Related papers  (2026-04-10T18:51:19Z)
• A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video [0.0]
  We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge.<n>The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world training data.<n>Our method separates the problem into three independent modules.
  arXiv  Detail & Related papers  (2026-04-05T05:18:19Z)
• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis [84.23233209017192]
  This paper presents a synthetic dataset for novel driving view synthesis evaluation.<n>It includes testing images captured by deviating from the training trajectory by $1-4$ meters.<n>We establish the first realistic benchmark for evaluating existing NVS approaches under front-only and multicamera settings.
  arXiv  Detail & Related papers  (2024-06-26T14:00:21Z)
• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving [76.29141888408265]
  We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:37:00Z)
• Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation [0.3441021278275805]
  There is no difference between accident and near-miss at the time before the accident happened. Our contribution is to redefine the accident definition and re-annotate the accident inconsistency on DADA-2000 dataset together with near-miss. The proposed method integrates two different components: conditional style translation (CST) and separable 3-dimensional convolutional neural network (S3D)
  arXiv  Detail & Related papers  (2023-01-06T22:04:47Z)

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.