結合兩階段網絡於影片精彩片段之擷取

Abstract

直播在網路中形成一股浪潮，帶給人們更臨場的觀看體驗，以及更即時的互動，吸引眾多的數位原住民。多數直播服務都有提供即時聊天室以增加即時互動性，而這些留言除了傳達出觀眾當下的情緒、想法，也提供了另一種和影片內容有關的豐富資訊來源，可用來挖掘觀眾對影片內容的意見。因此我們希望用這樣的概念來做精彩片段之擷取，以觀眾留言背後隱藏的意見來判別出影片中何處是精彩片段的開始與結束。並且結合當前主流的two-staged network的概念，透過兩階段的學習，先過濾出可能的片段，再進一步衡量這些片段屬於精彩片段的機率，減少訓練時間，且提升預測結果表現。最終本研究希望能夠設計出一套系統，可以有效率的透過留言去定位出人們喜愛的精彩片段。

Live streaming raises a burst of upsurge on the Internet. The reason is that it brings people a more on-the-spot viewing experience and more immediate interaction. Most live streaming services provide instant chat rooms to increase interaction. These messages convey the emotion of the audience and provide another rich source of information related to the video content, which can be used to mining the audience's opinions on the video content. Therefore, we hope to use this concept to extract highlight and use the information implicit in the audience message to locate highlight in the video. We also introduce the current mainstream two-staged network concept, through two-stage learning, the first filter out possible segments, further measure the probability that these segments belong to highlight, reduce training time, and improve the performance of prediction results. In the end, this study wants to design a system that can efficiently locate popular highlights through messages.