| 大会名称 |
|---|
| 2009年 情報科学技術フォーラム(FIT) |
| 大会コ－ド |
| F |
| 開催年 |
| 2009 |
| 発行日 |
| 2009/8/20 |
| セッション番号 |
| 5J |
| セッション名 |
| 画像特徴 |
| 講演日 |
| 2009/09/03 |
| 講演場所(会議室等) |
| J会場（9号館2F 924教室） |
| 講演番号 |
| H-050 |
| タイトル |
| Affective Analysis of Films by Low-Level Visual Features |
| 著者名 |
| テイシェイラ ヘネ, 山崎 俊彦, 相澤 清晴, |
| キーワード |
| Affective Analysis, Pleasure-Arousal-Dominance, Dynamic Bayesian Network, Color-Emotion, Saliency |
| 抄録 |
| Many algorithms and works have helped in the understanding and development of affective analysis of films. In spite of the progress done up to now, it is still not very precise how the low-level features of movies shape the resulting affective state of the viewer. In this work we evaluate different visual features and investigate how they impact the evaluated emotion under two paradigms: the dimensional approach (in terms of Pleasure, Arousal and Dominance) and the categorial approach. The evaluation is conducted by using Dynamic Bayesian Networks in the following topologies: a Hidden Markov Model network and Auto Regressive Hidden Markov Model network. |
| 本文pdf |
| PDF download (604.4KB) |