Estimation of Emotions Evoked by Images Based on Multiple Gaze-based CNN Features
| Autor: | Takahiro Ogawa, Naoki Saito, Satoshi Asamizu, Taiga Matsui, Miki Haseyama |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Feature extraction Locality ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Computer Science::Human-Computer Interaction Semantics Gaze Convolutional neural network Visualization Discriminative model Artificial intelligence Canonical correlation business |
| Zdroj: | LifeTech |
| DOI: | 10.1109/lifetech.2019.8884060 |
| Popis: | This paper presents a method for estimating emotions evoked by watching images based on multiple visual features considering relationship with gaze information. The proposed method obtains multiple visual features from multiple middle layers of a Convolutional Neural Network. Then the proposed method newly derives their gaze-based visual features maximizing correlation with gaze information by using Discriminative Locality Preserving Canonical Correlation Analysis. The final estimation result is calculated by integrating multiple estimation results obtained from these gaze-based visual features. Consequently, successful emotion estimation becomes feasible by using such multiple estimation results which correspond to different semantic levels of target images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|