Clothing Co-parsing by Joint Image Segmentation and Labeling

By Wei Yang, Ping Luo, Liang Lin. 2014

212 citations recorded by the source corpus.

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 configurations. We propose a data-driven framework consisting of two phases of inference. The first phase, referred as "image co-segmentation", iterates to extract consistent regions on images and jointly refines 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 configuration (e.g., item location and mutual interactions). The joint label assignment can be solved using the efficient 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-of-the-art methods.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images (2019, methodology): “In contrast, CCP [20], DeepFashion [14], and ModaNet [21] obtain category labels from human annotators.”
I Know That Person: Generative Full Body and Face De-identification of People in Images (2017, methodology): “Images from the Clothing CoParsing (CCP) dataset [36].”
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback (2021, background): “…past few years, covering different applications such as fashionability and style prediction [50, 28, 22, 51], fashion image generation [46], product search and recommendation [25, 72, 19, 41, 63], fashion apparel pix-elwise segmentation [27, 74, 69], and body-diverse clothing recommendation [24].”
Fashion Landmark Detection in the Wild (2016, background): “To better capture discriminative information in fashion items, previous works have explored the usage of full image [2], general object proposals [2], bounding boxes [9,17] and even masks [22,18,23,24].”
Garment modeling with a depth camera (2015, unknown): “Recently, some garment image parsing methods [Yamaguchi et al. 2012; Liu et al. 2012; Yamaguchi et al. 2015; Yang et al. 2014] are proposed in the field of computer vision.”
Deep Human Parsing with Active Template Regression (2015, methodology): “More specifically, the structure outputs are predicted by two separate networks.”
Learning Feature Pyramids for Human Pose Estimation (2017, background): “, activity recognition [60, 54], clothing parsing [57, 58, 36], human re-identification [65], and human-computer interaction.”
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations (2016, background): “Some other datasets in the vision community were dedicated to the tasks of clothes segmentation, parsing [32, 31, 23, 16, 33] and fashion modeling [24, 30], while DeepFashion focuses on clothes recognition and retrieval.”
Learning Fashion Compatibility with Bidirectional LSTMs (2017, methodology): “Most recent works utilize standard segmentation methods, in combination with human pose information, to parse different garment types [25, 27] for effective retrieval.”
InstaGAN: Instance-aware Image-to-Image Translation (2018, background): “We sample two classes from various datasets, including clothing co-parsing (CCP) (Yang et al., Figure 8: Translation results on CCP dataset, using predicted mask for inference.”