An Universal Image Attractiveness Ranking Framework
| Autor: | Houdong Hu, Mark Bolin, Pawel Pietrusinski, Aleksandr Livshits, Alexey Volkov, Ning Ma |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Attractiveness
FOS: Computer and information sciences Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Convolutional neural network 030218 nuclear medicine & medical imaging Data modeling Ranking (information retrieval) Computer Science - Information Retrieval Machine Learning (cs.LG) 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering business.industry Rank (computer programming) Pattern recognition Data set 020201 artificial intelligence & image processing Pairwise comparison Artificial intelligence business Information Retrieval (cs.IR) |
| Zdroj: | WACV |
| DOI: | 10.48550/arxiv.1805.00309 |
| Popis: | We propose a new framework to rank image attractiveness using a novel pairwise deep network trained with a large set of side-by-side multi-labeled image pairs from a web image index. The judges only provide relative ranking between two images without the need to directly assign an absolute score, or rate any predefined image attribute, thus making the rating more intuitive and accurate. We investigate a deep attractiveness rank net (DARN), a combination of deep convolutional neural network and rank net, to directly learn an attractiveness score mean and variance for each image and the underlying criteria the judges use to label each pair. The extension of this model (DARN-V2) is able to adapt to individual judge's personal preference. We also show the attractiveness of search results are significantly improved by using this attractiveness information in a real commercial search engine. We evaluate our model against other state-of-the-art models on our side-by-side web test data and another public aesthetic data set. With much less judgments (1M vs 50M), our model outperforms on side-by-side labeled data, and is comparable on data labeled by absolute score. Comment: Accepted by 2019 Winter Conference on Application of Computer Vision (WACV) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|