Matching-CNN Meets KNN: Quasi-Parametric Human Parsing

Liu, Si; Liang, Xiaodan; Liu, Luoqi; Shen, Xiaohui; Yang, Jianchao; Xu, Changsheng; Li, Lin; Cao, Xiaochun; Yan, Shuicheng

doi:10.48550/arxiv.1504.01220

Cited by 9 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first extract the mask to separate clothing from its background in the image using the method proposed by (Liu et al 2015). Then, for extracting the color features, we adopt the interpretable aesthetic features and extracting algorithms proposed by (Wang et al 2013).…”

Section: Feature Extractionmentioning

confidence: 99%

Learning to Appreciate the Aesthetic Effects of Clothing

Jia

Huang

Shen

et al. 2016

AAAI

View full text Add to dashboard Cite

How do people describe clothing? The words like “formal”or "casual" are usually used. However, recent works often focus on recognizing or extracting visual features (e.g., sleeve length, color distribution and clothing pattern) from clothing images accurately. How can we bridge the gap between the visual features and the aesthetic words? In this paper, we formulate this task to a novel three-level framework: visual features(VF) - image-scale space (ISS) - aesthetic words space(AWS). Leveraging the art-field image-scale space served as an intermediate layer, we first propose a Stacked Denoising Autoencoder Guided by CorrelativeLabels (SDAE-GCL) to map the visual features to the image-scale space; and then according to the semantic distances computed byWordNet::Similarity, we map the most often used aesthetic words in online clothing shops to the image-scale space too. Employing upper body menswear images downloaded from several global online clothing shops as experimental data, the results indicate that the proposed three-level framework can help to capture the subtle relationship between visual features and aesthetic words better compared to several baselines. To demonstrate that our three-level framework and its implementation methods are universally applicable, we finally present some interesting analyses on the fashion trend of menswear in the last 10 years.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Learning to Appreciate the Aesthetic Effects of Clothing

Jia

Huang

Shen

et al. 2016

AAAI

View full text Add to dashboard Cite

show abstract

Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features

Xia

Zhu

Wang

et al. 2016

AAAI

View full text Add to dashboard Cite

Parsing human into semantic parts is crucial to human-centric analysis. In this paper, we propose a human parsing pipeline that uses pose cues, e.g., estimates of human joint locations, to provide pose-guided segment proposals for semantic parts. These segment proposals are ranked using standard appearance cues, deep-learned semantic feature, and a novel pose feature called pose-context. Then these proposals are selected and assembled using an And-Or graph to output a parse of the person. The And-Or graph is able to deal with large human appearance variability due to pose, choice of clothing, etc. We evaluate our approach on the popular Penn-Fudan pedestrian parsing dataset, showing that it significantly outperforms the state of the art, and perform diagnostics to demonstrate the effectiveness of different stages of our pipeline.

show abstract

Unsupervised Learning of Visual Representations using Videos

Wang

Gupta

2015

Preprint

View full text Add to dashboard Cite

Matching-CNN Meets KNN: Quasi-Parametric Human Parsing

Cited by 9 publications

References 20 publications

Learning to Appreciate the Aesthetic Effects of Clothing

Learning to Appreciate the Aesthetic Effects of Clothing

Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features

Unsupervised Learning of Visual Representations using Videos

Contact Info

Product

Resources

About