Part-based clothing segmentation for person retrieval

Weber, Michael; Bauml, Martin

doi:10.1109/avss.2011.6027351

Cited by 35 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…many pictures from an event, a person will be wearing the same clothes throughout the event. Therefore, clothing recognition is a strong cue to identity and has been used to recognize people in personal photo collections [19], [20], [21], repeated shots [22], or in surveillance scenarios [23], [24].…”

Section: Clothing and Person Identificationmentioning

confidence: 99%

Retrieving Similar Styles to Parse Clothing

Yamaguchi

Kiapour

Ortiz

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

138

View full text Add to dashboard Cite

Abstract-Clothing recognition is a societally and commercially important yet extremely challenging problem due to large variations in clothing appearance, layering, style, and body shape and pose. In this paper, we tackle the clothing parsing problem using a retrieval-based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to recognize clothing items in the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse-masks (Paper Doll item transfer) from retrieved examples. We evaluate our approach extensively and show significant improvements over previous state-of-the-art for both localization (clothing parsing given weak supervision in the form of tags) and detection (general clothing parsing). Our experimental results also indicate that the general pose estimation problem can benefit from clothing parsing.

show abstract

Section: Clothing and Person Identificationmentioning

confidence: 99%

Retrieving Similar Styles to Parse Clothing

Yamaguchi

Kiapour

Ortiz

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

138

View full text Add to dashboard Cite

show abstract

“…Related to image retrieval, the approach proposed by Borras et al [6] describes the upper body clothing making use of texture and color features where a previous split-and-merge process based on homogeneity measures groups the different clothing parts. Another proposal in this scenario of application is due to Weber et al [7]. The authors make use of offline trained pose detector to deal with occlusions and different poses, before getting the clothing mask.…”

Section: Introductionmentioning

confidence: 99%

Stripe based clothes segmentation

Lorenzo-Navarro

Castrillón-Santana

Freire-Obregón

et al. 2015

2015 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

In this paper, a clothes segmentation method for fashion parsing is described. This method does not rely in a previous pose estimation but people segmentation. Therefore, novel and classic segmentation techniques have been considered and improved in order to achieve accurate people segmentation. Unlike other methods described in the literature, the output is the bounding box and the predominant color of the different clothes and not a pixel level segmentation. The proposal is based on dividing the person area into an initial fixed number of stripes, that are later fused according to similar color distribution. To assess the quality of the proposed method the experiments are carried out with the Fashionista dataset that is widely used in the fashion parsing community.

show abstract

“…The different parts of the clothes are obtained with a split-and-merge approach using homogeneity measures as criteria. Also in content-based image retrieval, Weber et al [14] introduce a novel approach by getting the mask of the clothing starting from a set of trained pose detectors in order to deal with occlusions and different poses inherent to humans. Manfredi et al [8] present an approach for segmenting garments in fashion stores databases.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of LBP and HOG Descriptors for Clothing Attribute Description

Lorenzo-Navarro

Castrillón

Enrique

et al. 2014

Video Analytics for Audience Measurement

View full text Add to dashboard Cite

Abstract. In this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been included in the comparison because they have been frequently used in clothing attributes classification. The experiments are carried out with a public available dataset, the clothing attribute dataset, that has 26 attributes in total. The obtained accuracies are over 75% in most cases, reaching 80% for the necktie or sleeve length attributes.

show abstract

Part-based clothing segmentation for person retrieval

Cited by 35 publications

References 18 publications

Retrieving Similar Styles to Parse Clothing

Retrieving Similar Styles to Parse Clothing

Stripe based clothes segmentation

Evaluation of LBP and HOG Descriptors for Clothing Attribute Description

Contact Info

Product

Resources

About