臺灣大學: 電信工程學研究所陳宏銘林耿生Lin, Keng-ShengKeng-ShengLin2013-03-272018-07-052013-03-272018-07-052012http://ntur.lib.ntu.edu.tw//handle/246246/252705因為戲劇節目中富含情感的段落往往是最吸引觀眾的部分,所以利用情緒為 基礎的精采片段擷取系統對於戲劇影片檢索和預告片生成是相當有助益的。在本 篇論文當中,我們將精采片段擷取公式化成迴歸的問題,並利用迴歸理論預測影 片片段引發觀眾情感的程度。有別於一般系統從實驗性的觀察中定義試誤性的規 則,本系統利用機器學習決定精采片段與影音特徵的關係。此外,我們從心理學 和戲劇學的角度分析戲劇節目的特性以提出與精采片段相關的影音特徵:人臉、 音樂情緒、鏡頭長度、動作幅度。最後,我們利用量化的方式分析本系統在精采 片段擷取上的準確度。Emotion-based highlights extraction is useful for retrieval and automatic trailer generation of drama video because the rich emotion part of a drama video is often the center of attraction to the viewer. In this thesis, we formulate highlights extraction as a regression problem to extract highlight segments and to predict how strong the viewer’s emotion would be evoked by the video segments. Unlike conventional rule-based approaches that rely on heuristics, the proposed system determines the relation between drama highlights and audiovisual features by machine learning. We also examine the special characteristics of drama video and propose human face, music emotion, shot duration, and motion magnitude as feature sets for highlights extraction. Quantitative evaluation results are provided to illustrate the performance of the system.1161070 bytesapplication/pdfen-US情感內容精采片段戲劇節目機器學習迴歸Affective contenthighlights extractiondrama videomachine learningregressionthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/252705/1/ntu-101-R99942041-1.pdf