# Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis

arXiv: https://arxiv.org/abs/2510.11907 · HTML: https://mlsanity.com/paper/2510.11907/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario](https://mlsanity.com/paper/2305.14836/) (2023)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023)
- [Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens](https://mlsanity.com/paper/2312.08870/) (2023)
- [Reducing Hallucinations in Vision-Language Models via Latent Space Steering](https://mlsanity.com/paper/2410.15778/) (2024)
- [VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes](https://mlsanity.com/paper/2405.05885/) (2024)
- [TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning](https://mlsanity.com/paper/2404.09275/) (2024)
- [WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2407.15350/) (2024)
- [ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding](https://mlsanity.com/paper/2410.00982/) (2024)
- [From Data to Actions in Intelligent Transportation Systems: a Prescription of Functional Requirements for Model Actionability](https://mlsanity.com/paper/2002.02210/) (2020)
- [Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis](https://mlsanity.com/paper/2404.08229/) (2024)
- [Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring](https://mlsanity.com/paper/2502.11304/) (2025)
- [Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey](https://mlsanity.com/paper/2412.00348/) (2024)
- [Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts](https://mlsanity.com/paper/2305.07019/) (2023)
- [Safety in Traffic Management Systems: A Comprehensive Survey](https://mlsanity.com/paper/2308.06204/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance](https://mlsanity.com/paper/2510.20016/) (2025)
- [A Contextual Analysis of Driver-Facing and Dual-View Video Inputs for Distraction Detection in Naturalistic Driving Environments](https://mlsanity.com/paper/2512.20025/) (2025)
- [Hybrid Congestion Classification Framework Using Flow-Guided Attention and Empirical Mode Decomposition](https://mlsanity.com/paper/2605.04752/) (2026)

## Abstract (arXiv)

Traffic safety analysis requires complex video understanding to capture fine-grained behavioral patterns and generate comprehensive descriptions for accident prevention. In this work, we present a unique dual-model framework that strategically utilizes the complementary strengths of VideoLLaMA and Qwen2.5-VL through task-specific optimization to address this issue. The core insight behind our approach is that separating training for captioning and visual question answering (VQA) tasks minimizes task interference and allows each model to specialize more effectively. Experimental results demonstrate that VideoLLaMA is particularly effective in temporal reasoning, achieving a CIDEr score of 1.1001, while Qwen2.5-VL excels in visual understanding with a VQA accuracy of 60.80%. Through extensive experiments on the WTS dataset, our method achieves an S2 score of 45.7572 in the 2025 AI City Challenge Track 2, placing 10th on the challenge leaderboard. Ablation studies validate that our separate training strategy outperforms joint training by 8.6% in VQA accuracy while maintaining captioning quality.