paper-with-me

홈 › Papers

Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis

2024-04-12 · Maged Shoman, Dongdong Wang, Armstrong Aboah, Mohamed Abdel-Aty

This paper introduces our solution for Track 2 in AI City Challenge 2024. The task aims to solve traffic safety description and analysis with the dataset of Woven Traffic Safety (WTS), a real-world Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding. Our solution mainly focuses on the following points: 1) To solve dense video captioning, we leverage the framework of dense video captioning with parallel decoding (PDVC) to model visual-language sequences and generate dense caption by chapters for video. 2) Our work leverages CLIP to extract visual features to more efficiently perform cross-modality training between visual and textual representations. 3) We conduct domain-specific model adaptation to mitigate domain shift problem that poses recognition challenge in video understanding. 4) Moreover, we leverage BDD-5K captioned videos to conduct knowledge transfer for better understanding WTS videos and more accurate captioning. Our solution has yielded on the test set, achieving 6th place in the competition. The open source code will be available at https://github.com/UCF-SST-Lab/AICity2024CVPRW

📄 PDF Abstract BibTeX arXiv:2404.08229

Code (1)

ucf-sst-lab/aicity2024cvprw 공식 구현 pytorch

Tasks

Dense Video CaptioningTransfer LearningVideo CaptioningVideo Understanding

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding

2024-07-22 · Quan Kong, Yuki Kawana, Rajat Saini, Ashutosh Kumar 외

In this paper, we address the challenge of fine-grained video event understanding in traffic scenarios, vital for autonomous driving and safety. Traditional datasets focus on driver or vehicle behavior, often neglecting …

Autonomous Driving

Enhancing Urban Traffic Safety: An Evaluation on Taipei's Neighborhood Traffic Environment Improvement Program

2024-01-30 · Frank Y. Huang, Po-Chun Huang

In densely populated urban areas, where interactions between pedestrians, vehicles, and motorcycles are frequent and complex, traffic safety is a critical concern. This paper evaluates the Neighborhood Traffic Environmen…

VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding

2025-07-13 · Younggun Kim, Ahmed S. Abdelrahman, Mohamed Abdel-Aty arxiv

Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, is a critical challenge for autonomous driving systems, as crashes involving VRUs often result in severe or fatal consequences. While…

Video Question AnsweringAutonomous VehiclesScene UnderstandingAutonomous Driving

Enhancing Vehicle Re-identification and Matching for Weaving Analysis

2024-07-05 · Mei Qiu, Wei Lin, Stanley Chien, Lauren Christopher 외

Vehicle weaving on highways contributes to traffic congestion, raises safety issues, and underscores the need for sophisticated traffic management systems. Current tools are inadequate in offering precise and comprehensi…

ManagementVehicle Re-Identification

Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving

2021-02-05 · Julian Bernhard, Alois Knoll

Balancing safety and efficiency when planning in dense traffic is challenging. Interactive behavior planners incorporate prediction uncertainty and interactivity inherent to these traffic situations. Yet, their use of si…

Autonomous Driving