Abstract | ||
---|---|---|
In this paper we investigate the use of a deep Convolutional Neural Network (CNN) to predict image aesthetics. To this end we fine-tune a canonical CNN architecture, originally trained to classify objects and scenes, by casting the image aesthetic prediction as a regression problem. We also investigate whether image aesthetic is a global or local attribute, and the role played by bottom-up and top-down salient regions to the prediction of the global image aesthetic. Experimental results on the canonical Aesthetic Visual Analysis (AVA) dataset show the robustness of the solution proposed, which outperforms the best solution in the state of the art by almost 17% in terms of Mean Residual Sum of Squares Error (MRSSE). |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-48680-2_11 | ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2016 |
Field | DocType | Volume |
Aesthetics,Convolutional neural network,Computer science,Robustness (computer science),Artificial intelligence,Deep learning,Residual sum of squares,Computer vision,Architecture,Pattern recognition,Support vector machine,Regression problems,Salient | Conference | 10016 |
ISSN | Citations | PageRank |
0302-9743 | 5 | 0.47 |
References | Authors | |
19 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Bianco | 1 | 226 | 24.48 |
Luigi Celona | 2 | 66 | 7.70 |
Paolo Napoletano | 3 | 339 | 37.19 |
Raimondo Schettini | 4 | 1476 | 154.06 |