Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set

By Si Liu, Zheng Song, Guangcan Liu, Changsheng Xu, Hanqing Lu, Shuicheng Yan. 2012

391 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

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

In Industrial and Manufacturing Engineering

Citations in the corpus

Large scale visual recommendations from street fashion images (2014, methodology): “Fashion-Q1K dataset consists of 1000 skirt images which are used as input queries to recommender.”
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations (2016, background): “Recently, extensive research efforts have been devoted to clothes classification [11, 1, 29], attribute prediction [3, 13, 4, 24], and clothing item retrieval [17, 6, 10, 27, 15], because of their potential values to the industry.”
Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items (2013, background): “Effective solutions to clothing parsing could enable useful end-user applications such as pose independent clothing retrieval [26] or street to shop applications [16].”
Apparel Classification with Style (2012, neutral): “[20] and Wang et al.”
Exact clothing retrieval approach based on deep neural network (2016, background): “[3] address the problem through aligning body parts and constructing transform matrix with an auxiliary daily photo dataset to sparsely represent the discrepancy between the street”
Learning Fashion Compatibility with Bidirectional LSTMs (2017, background): “Liu et al. proposed a street-to-shop application that learns a mapping between photos taken by users with product images [11].”
Parsing Clothes in Unrestricted Images (2013, background): “It plays an important role in human pose estimation [16], action recognition, person search [7, 15], surveillance, cloth retrieval [9] and has applications in fashion industry [16].”
Fashion Landmark Detection in the Wild (2016, background): “Recent advances include predicting semantic attributes [16,8,9,17,3], clothes recognition and retrieval [4,18,19,20,2,3] and fashion trends discovery [6,21,7].”
Neural Compatibility Modeling With Probabilistic Knowledge Distillation (2020, background): “Existing researches mainly focus on clothing retrieval [4][5][6], fashion trending prediction [7], fashionability prediction [8] and compatibility modeling [2][9][10].”
Clothing Attributes Assisted Person Reidentification (2015, background): “For operability in manual annotation, clothing attributes are usually labeled as discrete values [17], [18], [20], [21].”
Clothing Co-parsing by Joint Image Segmentation and Labeling (2014, background): “In computer vision, several interesting works [30, 5, 17, 16] have been proposed on this task and showed promising results.”
A High Performance CRF Model for Clothes Parsing (2014, methodology): “This is reflected in the growing interest in recognizing clothing from images [3,4,5,6,7,8,9,10], as this can enable a wide variety of applications such as trying on virtual garments in online shopping.”
VITON: An Image-Based Virtual Try-on Network (2017, methodology): “Most existing methods focus on clothing parsing [43, 27], clothing recognition by attributes [30], matching clothing seen on the street to online products [29, 13], fashion recommendation [18], visual compatibility learning [42, 15], and fashion trend prediction [2].”
Deep domain adaptation for describing people based on fine-grained clothing attributes (2015, background): “[33] addressed a similar cross-domain clothing retrieval problem, but their work relies on a different methodology than ours, deals with a different application, and only considers a small set of coarse-grained attributes which are manually labeled.”
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network (2015, methodology): “Due to the huge impact for e-commerce applications, there is a growing interest in methods for clothing retrieval [20, 33, 31, 44] and outfit recommendation [18].”
Hi, magic closet, tell me what to wear! (2012, positive): “The second type of attributes are detail attributes, which are manually selected according to previous research [19].”
Hipster Wars: Discovering Elements of Fashion Styles (2014, background): “Recent papers have looked at the problem of parsing clothing (predicting pixel-wise labelings of garment items) [35,36] and clothing recognition for applications [22,23,11].”
Deep Human Parsing with Active Template Regression (2015, methodology): “With the fast growth of on-line fashion sales, fashion related applications, such as clothing recognition and retrieval [29], [22], automatic product suggestions [21], have shown huge potential in e-commerce.”