Abstract | ||
---|---|---|
In this paper we focus on the problem of multi-label image recognition for visually-aware recommender systems. We propose a two stage approach in which a deep convolutional neural network is firstly fine-tuned on a part of the training set. Secondly, an attention-based aggregation network is trained to compute the weighted average of visual features in an input image set. Our approach is implemented as a mobile fashion recommender system application. It is experimentally show on the Amazon Fashion dataset that our approach achieves an F1-measure of 0.58 for 15 recommendations, which is twice as good as the 0.25 F1measure for conventional averaging of feature vectors. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-37334-4_26 | ANALYSIS OF IMAGES, SOCIAL NETWORKS AND TEXTS, AIST 2019 |
Keywords | DocType | Volume |
Visually-aware recommender system, Fashion recommendation, Multi-label image set recognition, Feature aggregation, Deep convolution neural networks, Mobile applications | Conference | 11832 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kirill V. Demochkin | 1 | 0 | 0.34 |
Andrey V. Savchenko | 2 | 0 | 0.68 |