Abstract

This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic confifigurations. We propose a data-driven framework consisting of two phases of inference. The fifirst phase, referred as “image co-segmentation”, iterates to extract consistent regions on images and jointly refifines the regions over all images by employing the exemplar-SVM (ESVM) technique [23]. In the second phase (i.e. “region colabeling”), we construct a multi-image graphical model by taking the segmented regions as vertices, and incorporate several contexts of clothing confifiguration (e.g., item location and mutual interactions). The joint label assignment can be solved using the effificient Graph Cuts algorithm. In addition to evaluate our framework on the Fashionista dataset [30], we construct a dataset called CCP consisting of 2098 high-resolution street fashion photos to demonstrate the performance of our system. We achieve 90.29% / 88.23% segmentation accuracy and 65.52% / 63.89% recognition rate on the Fashionista and the CCP datasets, respectively, which are superior compared with state-ofthe-art methods