Name
Abstract | ||
|---|---|---|
Computer vision and machine learning have great potential to aid in aesthetic judgments and exploration, particularly in the understanding of shapes. This paper presents our work in a well-defined but largely unexplored problem in this field: the automated recognition of apparel silhouette attributes for real-world products. Silhouette attributes, such as v-neck for dresses and open toe for shoes, are very important attributes for understanding the appearance of apparel but difficult to recognize automatically. We propose methods employing multi-modal features and supervised learning to automatically recognize silhouette attributes based on product images and the associated text. These algorithms are extensively tested on a large dataset of dresses, tops, and shoes provided by online retailers. The proposed silhouette recognition approach achieves high recognition accuracy on the nine silhouette categories. Our approach and experiments are also expected to stimulate future research on this topic. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/WACV.2012.6162993 | WACV |
Keywords | Field | DocType |
supervised learning,aesthetic judgment,shape recognition,v-neck dress,retail data processing,learning (artificial intelligence),product images,online retailers,apparel silhouette attributes automated recognition,associated text,aesthetic judgments,proposed silhouette recognition approach,automated recognition,internet,object recognition,computer vision,shape understanding,apparel appearance,aesthetic exploration,high recognition accuracy,machine learning,text analysis,open toe shoes,text classifier,multimodal features,silhouette category,apparel silhouette attribute,silhouette attribute,feature extraction,skin,visualization,shape,learning artificial intelligence,dictionaries | Computer vision,Pattern recognition,Visualization,Silhouette,Computer science,Clothing,Supervised learning,Feature extraction,Artificial intelligence,Machine learning,The Internet,Cognitive neuroscience of visual object recognition | Conference |
ISSN | ISBN | Citations |
1550-5790 E-ISBN : 978-1-4673-0232-6 | 978-1-4673-0232-6 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wei Zhang | 1 | 0 | 0.34 |
| Emilio Antunez | 2 | 210 | 16.18 |
| Salih Gokturk | 3 | 43 | 3.75 |
| Baris Sumengen | 4 | 225 | 13.99 |