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

TL;DR

This paper presents a novel approach for dense video captioning in traffic safety videos, combining parallel decoding, CLIP-based visual features, domain adaptation, and knowledge transfer to improve event analysis accuracy.

Contribution

It introduces a parallel dense video captioning framework with CLIP features, domain adaptation, and knowledge transfer, advancing traffic safety video understanding.

Findings

Achieved 6th place in AI City Challenge 2024.

Enhanced captioning accuracy through domain-specific adaptation.

Improved visual-language modeling with CLIP features.

Abstract

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