A Deformable Mixture Parsing Model with Parselets

Liang

et al. 2015

IEEE Trans. Multimedia

Self Cite

In this paper, we propose a novel semisupervised learning strategy to address human parsing. Existing human parsing datasets are relatively small due to the required tedious human labeling. We present a general, affordable and scalable solution, which harnesses the rich contexts in those easily available web videos to boost any existing human parser. First, we crawl a large number of unlabeled videos from the web. Then for each video, the cross-frame contexts are utilized for human pose co-estimation, and then video co-parsing to obtain satisfactory human parsing results for all frames. More specifically, SIFT flow and super-pixel matching are used to build correspondences across different frames, and these correspondences then contextualize the pose estimation and human parsing in individual frames. Finally these parsed video frames are used as the reference corpus for the non-parametric human parsing component of the whole solution. To further improve the accuracy of video co-parsing, we propose an active learning method to incorporate human guidance, where the labelers are required to assess the accuracies of the pose estimation results of certain selected video frames. Then we take reliable frames as the seed frames to guide the video pose co-estimation. Our human parsing framework can then easily incorporate the human feedback to train a better fashion parser. Extensive experiments on two benchmark fashion datasets as well as a newly collected challenging Fashion Icon dataset well demonstrate the encouraging performance gain from our general pipeline for human parsing.

“…The FI dataset is quite different from existing human parsing datasets [39], [7] in two aspects. Firstly, some images in FI may contain multiple humans.…”

Section: Dataset Collectionmentioning

confidence: 99%

“…Despite the great progresses achieved [40], [7], [39], [22], human parsing has not been fully solved. It is very challenging due to the following reasons.…”

mentioning

confidence: 98%

Fashion Parsing With Video Context

Liang

et al. 2015

IEEE Trans. Multimedia

Self Cite

IEEE Trans. Pattern Anal. Mach. Intell.

“…The main insight of this method was the use of body pose estimation for clothing parsing. Dong et al [34] later propose clothing parsing as an inference problem over parselets, a basis group of image regions that constitute clothing items. Liu et al also propose a method to eliminate pixel-level supervision in learning using image-level color tags [35].…”

Section: Clothing Parsingmentioning

confidence: 99%

Retrieving Similar Styles to Parse Clothing

Yamaguchi

Kiapour

Ortiz

et al. 2015

138

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.

Computer Vision -- ACCV 2014

“…Recent advances in 2D pose estimation [16,17] have enabled a more advanced segmentation of humans [18]. However, most approaches have focused on figure/ground labeling [19,20].…”

Section: Related Workmentioning

confidence: 99%

A High Performance CRF Model for Clothes Parsing

Simo-Serra

Fidler

Moreno-Noguer

et al. 2015

Abstract. In this paper we tackle the problem of clothing parsing: Our goal is to segment and classify different garments a person is wearing. We frame the problem as the one of inference in a pose-aware Conditional Random Field (CRF) which exploits appearance, figure/ground segmentation, shape and location priors for each garment as well as similarities between segments, and symmetries between different human body parts. We demonstrate the effectiveness of our approach on the Fashionista dataset [1] and show that we can obtain a significant improvement over the state-of-the-art.