3 papers
cs.CV2026
StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References
Boyu He, Yunfan Ye, Chang Liu +3
Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics,…
cs.SD2026
TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control
Shihao He, Yihan Xia, Fang Liu +2
Digital audio workstations expose rich effect chains, yet a semantic gap remains between perceptual user intent and low-level signal-processing parameters. We study retrieval-groun…
cs.LG2024
FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art Commissions
Changjuan Ran, Yeting Guo, Fang Liu +2
The unique artistic style is crucial to artists' occupational competitiveness, yet prevailing Art Commission Platforms rarely support style-based retrieval. Meanwhile, the fast-gro…