Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
cs.CV, cs.AI
Submitted: 2025-07-02
Updated: 2026-11-01
Terminology
Sources
- GPT-4 Technical Report
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
- Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
- Improved Baselines with Visual Instruction Tuning
- PaLM-E: An Embodied Multimodal Language Model
- CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions
- When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Pentagon relation and Biedenharn-Elliott identity
- Harnessing Neuron Stability to Improve DNN Verification
- Partially hyperbolic diffeomorphisms that are center fixing
- On the consistency of relative facts
- Joint Discriminative and Generative Learning for Person Re-identification
- Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
- Bulk-Boundary Correspondence in the Quantum Hall Effect
- ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding
- TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs