跳到主要导航 跳到搜索 跳到主要内容

Joint Implicit and Explicit Language Learning for Pedestrian Attribute Recognition

  • Yukang Zhang
  • , Lei Tan
  • , Yang Lu
  • , Yan Yan
  • , Hanzi Wang*
  • *此作品的通讯作者
  • Xiamen University
  • National University of Singapore

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Pedestrian attribute recognition (PAR) has received increasing attention due to its wide application in video surveillance and pedestrian analysis. Some text-enhanced methods tackle this task by facilitating interactive learning between the attributes and the visual images. However, these generic languages fail to uniquely describe different pedestrian images, missing individual characteristics. In this paper, we propose a Joint Implicit and Explicit Language Guidance Enhancement Learning (JGEL) method, which converts each pedestrian image into a language description with dual language learning to effectively learn enhanced attribute information. Specifically, we first propose an Implicit Language Guidance Learning (ILGL) stream. It projects visual image features into the text embedding space to generate pseudo-word tokens, implicitly modeling image attributes and providing personalized descriptions. Moreover, we propose an Explicit Attribute Enhancement Learning (EAEL) stream to guide the generated pseudo-word tokens obtained by ILGL explicitly aligned with pedestrian attributes, which can effectively align the pseudo-word tokens with the attribute concepts in the text embedding space. Extensive experiments show that JGEL has significant advantages in improving the performance of PAR and the challenging zero-shot PAR task.

源语言英语
主期刊名Proceedings of the AAAI Conference on Artificial Intelligence
编辑Sven Koenig, Chad Jenkins, Matthew E. Taylor
出版商Association for the Advancement of Artificial Intelligence
页12970-12978
页数9
版本15
ISBN(印刷版)9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067, 9781577359067
DOI
出版状态已出版 - 2026
已对外发布是
活动40th AAAI Conference on Artificial Intelligence, AAAI 2026 - Singapore, 新加坡
期限: 20 1月 2026 → 27 1月 2026

丛书

姓名Proceedings of the AAAI Conference on Artificial Intelligence
编号15
卷40
ISSN(印刷版)2159-5399
ISSN(电子版)2374-3468

会议

会议40th AAAI Conference on Artificial Intelligence, AAAI 2026
国家/地区新加坡
市Singapore
时期20/01/26 → 27/01/26

学术指纹

探究 'Joint Implicit and Explicit Language Learning for Pedestrian Attribute Recognition' 的科研主题。它们共同构成独一无二的学术指纹。

引用此