arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1711.08922cs.CV
收藏

从第三人的观点总结第一人称视频

Summarizing First-Person Videos from Third Persons' Points of Views

National Taiwan University(台湾大学);National Chiao Tung University(国立交通大学)

Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang

摘要:

视频精彩片段或摘要是计算机视觉中有趣的主题之一,它有利于查看、搜索或存储等各种应用。然而,大多数现有的研究依赖于第三人称视频的训练数据,这不能容易地推广到突出第一人称的。为了得到一个有效的模型来总结第一人称视频,我们提出了一种新的深度神经网络架构,用于描述和区分具有不同视角的视频中的重要时空信息。我们提出的模型是在半监督环境中实现的,其中在训练过程中呈现了完全注释的第三人称视频,未标记的第一人称视频和少量注释的第一人称视频。在我们的实验中,定性和定量评估基准和我们收集的第一人称视频数据集。

英文摘要:

Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person ones. With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view. Our proposed model is realized in a semi-supervised setting, in which fully annotated third-person videos, unlabeled first-person videos, and a small number of annotated first-person ones are presented during training. In our experiments, qualitative and quantitative evaluations on both benchmarks and our collected first-person video datasets are presented.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑