Multi-Stage VLM Pipeline for Zero-Shot Traffic Accident Understanding
We present the 1st-place solution to the ACCIDENT challenge at the CVPR 2026 AUTOPILOT Workshop, which asks for zero-shot prediction of accident timing, impact centroid, and collision type from CCTV footage. On a frozen Qwen3-VL-32B-Instruct checkpoint we build a three-stage pipeline (full-video joint prediction, time refinement, and single-frame grounding of the impact centroid), run the same pipeline a second time on a 235B Mixture-of-Experts sibling, blend the two outputs 9:1, and finally snap each predicted point onto the nearest vehicle detection. The final system reaches Public LB 0.55469 / Private LB 0.57080, roughly +0.21 over the strongest host baseline (Molmo-7B, 0.358) and wins the challenge. We ablate each component, report the negative results that shaped the final design, and release the code at https://github.com/fuumin621/cvpr2026-accident-1st-place-solution.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance variations. Objects may leave and re-ent…
A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video
We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge. The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world…
A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction
Current social science efforts automatically populate event databases of "who did what to whom?" tuples, by applying event extraction (EE) to text such as news. The event databases are used to analyze sociopolitical dyna…
Computational EfficiencyEvent ExtractionInstruction FollowingLanguage Modeling+3Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding
In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural…
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection
Intent discovery is a crucial task in natural language processing, and it is increasingly relevant for various of industrial applications. Identifying novel, unseen intents from user inputs remains one of the biggest cha…
intent-classificationIntent ClassificationIntent DetectionIntent Discovery+1