A Multimodal Design Patent Retrieval Method Based on Chinese-CLIP

DOI

10.2991/978-94-6463-958-2_10How to use a DOI?

Keywords

multimodal patent retrieval; Chinese-CLIP model; design patent

Abstract

To address the limitations of current multimodal patent retrieval, this paper proposes a Chinese-CLIP-based multimodal design patent retrieval method. By expanding textual information, optimizing the image encoder, and improving the retrieval process, it enhances retrieval accuracy. Experimental results demonstrate that the proposed method outperforms baseline models.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shengnan Zhang
AU  - Kaiyao Qin
PY  - 2025
DA  - 2025/12/26
TI  - A Multimodal Design Patent Retrieval Method Based on Chinese-CLIP
BT  - Proceedings of the 5th International Conference on Management Science and Software Engineering (ICMSSE 2025)
PB  - Atlantis Press
SP  - 74
EP  - 80
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-958-2_10
DO  - 10.2991/978-94-6463-958-2_10
ID  - Zhang2025
ER  -