Journal article · 2024 · Open access
Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion
IEEE Transactions on Circuits and Systems for Video Technology, 35(1), 148–161 · Published 4 September 2024 · DOI 10.1109/tcsvt.2024.3454366
In brief
“Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion” is a 2024 journal article by Xiao Wang and 5 co-authors, published in IEEE Transactions on Circuits and Systems for Video Technology. OpenAlex counts 54 citations as of 22 November 2026, which puts it in the top 4% of works published in 2024 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 54
- Most cited in
- 2025 (27)
- Field-weighted impact
- 4.68
- References
- 76
- Authors
- 6
Abstract
Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the relations between pedestrian images and attribute labels. In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels. Specifically, the attribute phrases are first expanded into sentences, and then the pre-trained vision-language model CLIP is adopted as our backbone for feature embedding of visual images and attribute descriptions. The contrastive learning objective connects the vision and language modalities well in the CLIP-based feature space, and the Transformer layers used in CLIP can capture the long-range relations between pixels. Then, a multi-modal Transformer is adopted to fuse the dual features effectively and feed-forward network is used to predict attributes. To optimize our network efficiently, we propose the region-aware prompt tuning technique to adjust very few parameters (i.e., only the prompt vectors and classification heads) and fix both the pre-trained VL model and multi-modal Transformer. Our proposed PAR algorithm only adjusts 0.75% learnable parameters compared with the fine-tuning strategy. It also achieves new state-of-the-art performance on both standard and zero-shot settings for PAR, including RAPv1, RAPv2, WIDER, PA100K, and PETA-ZS, RAP-ZS datasets. The source code and pre-trained models will be released onhttps://github.com/Event-AHU/OpenPAR.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, X., Jin, J., Li, C., Tang, J., Zhang, C., & Wang, W. (2024). Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion. IEEE Transactions on Circuits and Systems for Video Technology, 35(1), 148–161. https://doi.org/10.1109/tcsvt.2024.3454366
MLA 9
Wang, Xiao, et al. “Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion.” IEEE Transactions on Circuits and Systems for Video Technology, vol. 35, no. 1, 2024, pp. 148–161. https://doi.org/10.1109/tcsvt.2024.3454366.
Chicago
Wang, Xiao, Jiandong Jin, Chenglong Li, Jin Tang, Cheng Zhang, and Wei Wang. 2024. “Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion.” IEEE Transactions on Circuits and Systems for Video Technology 35 (1): 148–161. https://doi.org/10.1109/tcsvt.2024.3454366.
Harvard
Wang, X. et al. (2024) ‘Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion’, IEEE Transactions on Circuits and Systems for Video Technology, 35(1), pp. 148–161. doi:10.1109/tcsvt.2024.3454366.
IEEE
X. Wang, J. Jin, C. Li, J. Tang, C. Zhang, and W. Wang, “Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 35, no. 1, pp. 148–161, 2024, doi: 10.1109/tcsvt.2024.3454366.
BibTeX
@article{wang2024pedestrian,
title = {{Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion}},
author = {Wang, Xiao and Jin, Jiandong and Li, Chenglong and Tang, Jin and Zhang, Cheng and Wang, Wei},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {35},
number = {1},
pages = {148--161},
doi = {10.1109/tcsvt.2024.3454366},
url = {https://doi.org/10.1109/tcsvt.2024.3454366}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 4 | |
| 2025 | 27 | |
| 2026 | 23 |
Its field-weighted citation impact is 4.68: it has been cited 4.68 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- pedestrian attribute recognition
- vision-language fusion
- CLIP
- prompt tuning
- multimodal transformer
- contrastive learning
- zero-shot learning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wang, X., Jin, J., Li, C., Tang, J., Zhang, C., & Wang, W. (2024). Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion. IEEE Transactions on Circuits and Systems for Video Technology, 35(1), 148–161. https://doi.org/10.1109/tcsvt.2024.3454366
How many times has this paper been cited?
54 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Xiao Wang, Jiandong Jin, Chenglong Li, Jin Tang, Cheng Zhang, Wei Wang.
What is the DOI of this paper?
10.1109/tcsvt.2024.3454366, permanently at https://doi.org/10.1109/tcsvt.2024.3454366. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.