Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrieval

TL;DR

This paper introduces a symmetric network with spatial relationship modeling for natural language-based vehicle retrieval, effectively integrating appearance, environment, and temporal context to improve retrieval accuracy.

Contribution

It proposes a novel symmetric network architecture combined with spatial relationship modeling to enhance cross-modal vehicle retrieval using natural language descriptions.

Findings

Achieved 43.92% MRR accuracy on the AI City Challenge.

First place on the public leaderboard for natural language vehicle retrieval.

Demonstrated effectiveness through qualitative and quantitative experiments.

Abstract

Natural language (NL) based vehicle retrieval aims to search specific vehicle given text description. Different from the image-based vehicle retrieval, NL-based vehicle retrieval requires considering not only vehicle appearance, but also surrounding environment and temporal relations. In this paper, we propose a Symmetric Network with Spatial Relationship Modeling (SSM) method for NL-based vehicle retrieval. Specifically, we design a symmetric network to learn the unified cross-modal representations between text descriptions and vehicle images, where vehicle appearance details and vehicle trajectory global information are preserved. Besides, to make better use of location information, we propose a spatial relationship modeling methods to take surrounding environment and mutual relationship between vehicles into consideration. The qualitative and quantitative experiments verify the effectiveness of the proposed method. We achieve 43.92% MRR accuracy on the test set of the 6th AI City Challenge on natural language-based vehicle retrieval track, yielding the 1st place among all valid submissions on the public leaderboard. The code is available at https://github.com/hbchen121/AICITY2022_Track2_SSM.