.png){kind=icon}
.png){kind=icon}
Return
Deep-based Self-refined Face-top Coordination
.png){kind=icon}
PRE
AI
DOI：10.1145/3446970.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Face-top coordination, which exists in most clothes-fitting scenarios, is challenging due to varieties of attributes, implicit correlations, and tradeoffs between general preferences and individual preferences. We present a Deep-Based Self-Refined (DBSR) system to simulate face-top coordination based on intuition evaluation. To this end, we first establish a well-coordinated face-top (WCFT) dataset from fashion databases and communities. Then, we use a jointly trained CNN Deep Canonical Correlation Analysis (DCCA) method to bridge the semantic face-top gap based on the WCFT dataset to deal with general preferences. Subsequently, an irrelevance-based Optimum-path Forest (OPF) method is developed to adapt the results to individual preferences iteratively. Experimental results and user study demonstrate the effectiveness of our method.
Keywords:
Fashion analysis
personalized face-top coordination
deep cross-modal learning
canonical correlation analysis
relevance feedback
optimum-path forest
Journal
IF:
6
Papers:
2.0K
Citations:
5.4K