EUVIMEDEUVIMED entdecken
Crossref

An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes With the Arbitrary Length

Kaihang Jiang, Wai Keung Wong, Xiaozhao Fang, Weijun Sun, Guoxu Zhou, Shengli Xie, Xiaochun Cao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-09 · 48 (9) · 10382-10400

DOI: 10.1109/tpami.2026.3688816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-09. Verfasst von Kaihang Jiang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: Laboratory for Artificial Intelligence in Design, InnoHK Initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, numerous hashing techniques have been developed to boost efficient cross-modal retrieval. Once a retrieval model is deployed, the hash code length is fixed to achieve optimal performance. To address different retrieval scenarios while maintaining retrieval accuracy, a common approach is to redesign and retrain the original model with different hash code length. However, this retraining process can increase the training load and may lead to worse results. To tackle these challenges, we present Regenerated Cross-Modal Hashing (RCMH), a novel cross-modal hashing framework designed to improve the quality of existing hash codes and convert them to arbitrary lengths with high efficiency. First, we clip or pad the existing hash codes to initialize them with the target length, under the supervision of the similarity matrix generated by the augmented label information. Second, we introduce a linear-nonlinear competitive reconstruction approach to reduce the semantic gaps and further capture the deeper relationships from linear image features and nonlinear text features. In this way, each pair of samples is compared and selected to obtain reconstructed binary codes that can preserve the modality-specific properties. Finally, to reduce the training costs caused by iterations of variables, the regenerate hashing term is utilized to regenerate final hash codes with the reconstructed binary codes while preserving the information from the existing hash codes without iterative optimization. Notably, RCMH can be integrated with existing state-of-the-art (SOTA) methods with robustness, helping them to adjust the hash code length and achieve better retrieval performance.

Förderung

  • Laboratory for Artificial Intelligence in Design
  • InnoHK Initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government
  • National Natural Science Foundation of China

Zitieren

APA

Jiang, K., Wong, W. K., Fang, X., Sun, W., Zhou, G., Xie, S., & Cao, X. (2026). An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes With the Arbitrary Length. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(9), 10382-10400. https://doi.org/10.1109/tpami.2026.3688816

Vancouver

Jiang K, Wong WK, Fang X, Sun W, Zhou G, Xie S, et al. An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes With the Arbitrary Length. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(9):10382-10400. doi:10.1109/tpami.2026.3688816

BibTeX
@article{Jiang2026,
  author = {Jiang, Kaihang and Wong, Wai Keung and Fang, Xiaozhao and Sun, Weijun and Zhou, Guoxu and Xie, Shengli and Cao, Xiaochun},
  title = {An Efficient Regenerated Cross-Modal Hashing: Improving Existing Hash Codes With the Arbitrary Length},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {9},
  pages = {10382--10400},
  doi = {10.1109/tpami.2026.3688816}
}
Kostenlos starten →