Towards Predicting the Likeability of Fashion Images
نویسندگان
چکیده
In this paper, we propose a method for ranking fashion images to find the ones which might be liked by more people. We collect two new datasets from image sharing websites (Pinterest and Polyvore). We represent fashion images based on attributes: semantic attributes and data-driven attributes. To learn semantic attributes from limited training data, we use an algorithm on multi-task convolutional neural networks to share visual knowledge among different semantic attribute categories. To discover data-driven attributes unsupervisedly, we propose an algorithm to simultaneously discover visual clusters and learn fashion-specific feature representations. Given attributes as representations, we propose to learn a ranking SPN (sum product networks) to rank pairs of fashion images. The proposed ranking SPN can capture the high-order correlations of the attributes. We show the effectiveness of our method on our two newly collected datasets.
منابع مشابه
The Influence of Perceived Personality Characteristics on Positive Attitude Towards and Suitability of a Celebrity as a Marketing Campaign Endorser
It is a common strategy to use celebrity endorsers in marketing campaigns. However, scientific literature on the effective use of celebrity endorsers has mainly focused on the credibility and the attractiveness of the celebrity. This study examines another endorser characteristic, which, despite other fields of psychological research confirming its importance, has not received much attention wi...
متن کاملThe social-devaluation effect: interactive evaluation deteriorates likeability of objects based on daily relationship
Although previous research has explored the effects of discussion on optimal and collective group outcomes, it is unclear how an individual's preference for an object is modulated by discussion with others. This study investigated the determinants of likeability ratings under two conditions. In Experiment 1, pairs of participants consisting of friends evaluated various photographic images. Unde...
متن کاملThe Study of Social Factors Affecting the Tendency towards Childbearing among Young Women in Mazandaran Province
Fertility behavior based on stimuli, decision making process, and related attitudes can be considered as social behavior that occurs in a social environment. The general objective of this research is to investigate the social factors affecting the tendency towards childbearing among married women in Mazandaran province. The sample size of this study is 100 people who were selected by purposive ...
متن کاملEvaluation of Attention Bias in Morphine and Methamphetamine Abusers towards Emotional Scenes during Early Abstinence: An Eye-Tracking Study
Introduction: We hypothesized that inappropriate attention during the period of abstinence in individuals with substance use disorder can result in an inadequate perception of emotion and unsuitable reaction to emotional scenes. The main aim of this research was to evaluate the attentional bias towards emotional images in former substance abusers and compare it to healthy adults. Methods:...
متن کاملPredicting of the Quality Attributes of Orange Fruit Using Hyperspectral Images
Background: Hyperspectral image analysis is a fast and non-destructive technique that is being used to measure quality attributes of food products. This research investigated the feasibility of predicting internal quality attributes, such as Total Soluble Solids (TSS), pH, Titratable Acidity (TA), and maturity index (TSS/TA); and external quality attributes such as color components (L*, a*, b*)...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1511.05296 شماره
صفحات -
تاریخ انتشار 2015