BriefGPT.xyz
May, 2016
超越字幕到叙事: 视频多句子字幕
Beyond Caption To Narrative: Video Captioning With Multiple Sentences
HTML
PDF
Andrew Shin, Katsunori Ohnishi, Tatsuya Harada
TL;DR
本研究提出了一种视频片段分割、多帧生成多个盛传、并采用自然语言技术将其连接成故事式视频字幕的方法，实现丰富内容的视频字幕生成，结果表明该方法不需要显式输入视频级别特征即可提供丰富内容，与最新技术方法相同。
Abstract
Recent advances in image captioning task have led to increasing interests in
video captioning
task. However, most works on
video captioning
are focused on generating single input of aggregated features, which har
→