Hi, magic closet, tell me what to wear!

Liu, Si; Nguyên, Tam; Feng, Jiashi; Wang, Meng; Yan, Shuicheng

doi:10.1145/2393347.2396470

Cited by 111 publications

(142 citation statements)

References 6 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…For example, Lennon's study [Lennon 1990] investigated whether clothing may affect our sense of attraction between humans. Recently, Liu et al [2012a] introduced an interactive system which recommends the dressings according to the event. Apart from visual attractiveness, Zuckerman and Miyake [1993] investigated the voice attractiveness.…”

Section: Related Workmentioning

confidence: 99%

Towards decrypting attractiveness via multi-modality cues

Nguyên

Liu

et al. 2013

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

Decrypting the secret of beauty or attractiveness has been the pursuit of artists and philosophers for centuries. To date, the computational model for attractiveness estimation has been actively explored in computer vision and multimedia community, yet with the focus mainly on facial features. In this article, we conduct a comprehensive study on female attractiveness conveyed by single/multiple modalities of cues, that is, face, dressing and/or voice, and aim to discover how different modalities individually and collectively affect the human sense of beauty. To extensively investigate the problem, we collect the Multi-Modality Beauty (M 2 B) dataset, which is annotated with attractiveness levels converted from manual k-wise ratings and semantic attributes of different modalities. Inspired by the common consensus that middle-level attribute prediction can assist higher-level computer vision tasks, we manually labeled many attributes for each modality. Next, a tri-layer Dual-supervised Feature-Attribute-Task (DFAT) network is proposed to jointly learn the attribute model and attractiveness model of single/multiple modalities. To remedy possible loss of information caused by incomplete manual attributes, we also propose a novel Latent Dual-supervised Feature-Attribute-Task (LDFAT) network, where latent attributes are combined with manual attributes to contribute to the final attractiveness estimation. The extensive experimental evaluations on the collected M 2 B dataset well demonstrate the effectiveness of the proposed DFAT and LDFAT networks for female attractiveness prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards decrypting attractiveness via multi-modality cues

Nguyên

Liu

et al. 2013

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

show abstract

“…3, we compare the recommendation results of our model with three baselines (latent SVM [5], multi-class SVM and neural network). The performance is measured by Normalized Discounted Cumulative Gain (NDCG).…”

Section: Demonstrationmentioning

confidence: 99%

"Wow! you are so beautiful today!"

Liu¹,

Xu²,

Liu³

et al. 2013

Proceedings of the 21st ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

In this demo, we present Beauty e-Experts, a fully automatic system for hairstyle and facial makeup recommendation and synthesis. Given a user-provided frontal facial image with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suitable hairstyle and makeup, but also show the synthesis effects. Two problems are considered for the Beauty e-Experts system: what to recommend and how to wear, which describe a similar process of selecting and applying hairstyle and cosmetics in our daily life. For the what-to-recommend problem, we propose a multiple tree-structured super-graphs model to explore the complex relationships among the beauty attributes, beauty-related attributes and image features, and then based on this model, the most suitable beauty attributes for a given facial image can be efficiently inferred. For the how-to-wear problem, a facial image synthesis module is designed to seamlessly blend the recommended hairstyle and makeup into the user facial image. Extensive experimental evaluations and analysis on testing images well demonstrate the effectiveness of the proposed system.

show abstract

“…It is one of the fundamental tasks for understanding the clothes in photographs. Accompanied by other tasks including clothing segmentation [1][2][3][4] and garment attribute classification [5][6][7] these researches are widely used in visual applications such as clothing retrieval [8,9], clothing recommendation [10,11] and human recognition [12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Parsing fashion image into mid‐level semantic parts based on chain‐conditional random fields

Wang

Zhao

Yin

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

In this study, the authors address the problem of parsing fashion images into mid-level semantic parts including upper-clothing, lower-clothing, skin, hair and background. These mid-level parts provide the regional information of fashion items and have potential value in high-level parsing process. The key idea of the method is to parse the midlevel parts by region expanding. Owing to the co-occurrence of pose skeleton and the proposed parts, the region expanding process starts from the super-pixels crossed by specific segments of pose skeleton. The super-pixels are then merged with their neighbours by conditional inference based on their position and perceptual similarity. To avoid the difficulties of training on arbitrary graph structures, conditional random fields (CRFs) are constructed on super-pixel chains, which are extracted from the generated expanding trees. This is followed by a voting stage to mix up the probabilities estimated by the chain-CRFs to obtain the final result. Experiments on two datasets show that the new method outperforms related approaches in regional accuracy and has good generalisation capability. Furthermore, the method can be easily employed to improve the performance of high-level parsing. Its effectiveness has been verified by another group of experiments on two state-of-the-art high-level parsing approaches.

show abstract

Hi, magic closet, tell me what to wear!

Cited by 111 publications

References 6 publications

Towards decrypting attractiveness via multi-modality cues

Towards decrypting attractiveness via multi-modality cues

"Wow! you are so beautiful today!"

Parsing fashion image into mid‐level semantic parts based on chain‐conditional random fields

Contact Info

Product

Resources

About