EUVIMEDEUVIMED entdecken
Crossref

DMV ‐ CLIP : Disentangled Multimodal Visual Adaptation for Text‐Driven Face Editing

Minghao Li, Fan Zhang, Xin Wei, Huan Wan, Haoruo Zhang, Xuhui Huang

Expert Systems · 2026-08 · 43 (8)

DOI: 10.1111/exsy.70345 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Expert Systems, online erschienen am 29.06.2026. Verfasst von Minghao Li und 5 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text‐driven face editing has attracted widespread interest due to its intuitive control and user‐friendly interaction. However, current state‐of‐the‐art (SOTA) methods face two main challenges: (1) they utilize unfinetuned general image‐text encoders for modality fusion, making it difficult to comprehend domain‐specific knowledge in facial attribute editing (dozens of fine‐grained facial attributes such as moustache and lipsticks); (2) they roughly optimize all attributes simultaneously using a cross‐entropy loss, leading to severe mutual interference among attributes. To this end, we propose Disentangled Multimodal Visual Adaptation for CLIP (DMV‐CLIP). First, DMV‐CLIP incorporates learnable context tokens to inject facial domain knowledge into the CLIP model via multimodal prompt learning (MPL). Second, it employs directional contrastive learning (DCL) to disentangle facial attributes and enable precise editing. Finally, DMV‐CLIP utilizes a vision‐language consistency model (VLCM) to maintain identity consistency while ensuring that the generated images strictly adhere to the semantic instructions.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province

Zitieren

APA

Li, M., Zhang, F., Wei, X., Wan, H., Zhang, H., & Huang, X. (2026). DMV ‐ CLIP : Disentangled Multimodal Visual Adaptation for Text‐Driven Face Editing. Expert Systems, 43(8). https://doi.org/10.1111/exsy.70345

Vancouver

Li M, Zhang F, Wei X, Wan H, Zhang H, Huang X. DMV ‐ CLIP : Disentangled Multimodal Visual Adaptation for Text‐Driven Face Editing. Expert Systems. 2026;43(8). doi:10.1111/exsy.70345

BibTeX
@article{Li2026,
  author = {Li, Minghao and Zhang, Fan and Wei, Xin and Wan, Huan and Zhang, Haoruo and Huang, Xuhui},
  title = {DMV ‐ CLIP : Disentangled Multimodal Visual Adaptation for Text‐Driven Face Editing},
  journal = {Expert Systems},
  year = {2026},
  volume = {43},
  number = {8},
  doi = {10.1111/exsy.70345}
}
Kostenlos starten →