Cover Image

Multi-Stage VLM Pipeline for Zero-Shot Traffic Accident Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tatematsu, Fumiya, Takahashi, Fumihiko
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video
by: Thakur, Amey, et al.
Published: (2026)

ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models
by: Sural, Shounak, et al.
Published: (2024)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives
by: Hu, Jinghao, et al.
Published: (2026)

SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
by: Lin, Jiawen, et al.
Published: (2025)

HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation
by: Lei, Qinqian, et al.
Published: (2025)

EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
by: Lei, Qinqian, et al.
Published: (2024)

Real-time Traffic Accident Anticipation with Feature Reuse
by: Song, Inpyo, et al.
Published: (2025)

Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding
by: Lohner, Aaron, et al.
Published: (2024)

Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis
by: Li, Lei-lei, et al.
Published: (2025)

Leveraging VLM-Based Pipelines to Annotate 3D Objects
by: Kabra, Rishabh, et al.
Published: (2023)

Zero-Shot Long-Form Video Understanding through Screenplay
by: Wu, Yongliang, et al.
Published: (2024)

Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
by: Klepachevskyi, Dmytro, et al.
Published: (2026)

MsFIN: Multi-scale Feature Interaction Network for Traffic Accident Anticipation
by: Wu, Tongshuai, et al.
Published: (2025)

Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video
by: Huang, Jiantang
Published: (2026)

Zero-Shot Multi-Animal Tracking in the Wild
by: Meier, Jan Frederik, et al.
Published: (2025)

MVSAnywhere: Zero-Shot Multi-View Stereo
by: Izquierdo, Sergio, et al.
Published: (2025)

Zero-Shot Multi-Object Scene Completion
by: Iwase, Shun, et al.
Published: (2024)

Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Dataset
by: Zimmer, Walter, et al.
Published: (2025)

SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding
by: Sheng, Zihao, et al.
Published: (2025)

T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
by: Qian, Yifei, et al.
Published: (2025)

A Recipe for Improving Remote Sensing VLM Zero Shot Generalization
by: Barzilai, Aviad, et al.
Published: (2025)

MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval
by: Tu, Rong-Cheng, et al.
Published: (2025)

VLM-in-the-Loop: A Plug-In Quality Assurance Module for ECG Digitization Pipelines
by: Li, Jiachen, et al.
Published: (2026)

AccidentGPT: Large Multi-Modal Foundation Model for Traffic Accident Analysis
by: Wu, Kebin, et al.
Published: (2024)

MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation
by: Raychaudhuri, Sonia, et al.
Published: (2025)

Benchmarking and Enhancing VLM for Compressed Image Understanding
by: Zhang, Zifu, et al.
Published: (2025)

VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding
by: Kim, Younggun, et al.
Published: (2025)

Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments
by: Rajiv, Manjunath Prasad Holenarasipura, et al.
Published: (2025)

TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings
by: Wilson, Bibin
Published: (2026)

A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology
by: Amster, Martin, et al.
Published: (2026)

Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary Queries
by: Robbins, Kevin, et al.
Published: (2026)

Structure-Preserving Zero-Shot Image Editing via Stage-Wise Latent Injection in Diffusion Models
by: Jeong, Dasol, et al.
Published: (2025)

Integrating Generative Adversarial Networks and Convolutional Neural Networks for Enhanced Traffic Accidents Detection and Analysis
by: Xi, Zhenghao, et al.
Published: (2025)

Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
by: Wang, Ning, et al.
Published: (2025)

MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM
by: Chen, Tao, et al.
Published: (2025)

Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
by: Dai, Fengyuan, et al.
Published: (2024)

Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection
by: Huang, Chaoqin, et al.
Published: (2023)

MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
by: Qu, Xiangyan, et al.
Published: (2025)

Multi-Teacher Multi-Objective Meta-Learning for Zero-Shot Hyperspectral Band Selection
by: Feng, Jie, et al.
Published: (2024)