From Lifestyle Vlogs to Everyday Interactions

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(2017)

引用 130|浏览174
暂无评分
摘要
A major stumbling block to progress in understanding basic human interactions, such as getting out of bed or opening a refrigerator, is lack of good training data. Most past efforts have gathered this data explicitly: starting with a laundry list of action labels, and then querying search engines for videos tagged with each label. In this work, we do the reverse and search implicitly: we start with a large collection of interaction-rich video data and then annotate and analyze it. We use Internet Lifestyle Vlogs as the source of surprisingly large and diverse interaction data. We show that by collecting the data first, we are able to achieve greater scale and far greater diversity in terms of actions and actors. Additionally, our data exposes biases built into common explicitly gathered data. We make sense of our data by analyzing the central component of interaction -- hands. We benchmark two tasks: identifying semantic object contact at the video level and non-semantic contact state at the frame level. We additionally demonstrate future prediction of hands.
更多
查看译文
关键词
interaction-rich video data,video level,action labels,search engines,Internet lifestyle vlogs,semantic object contact,nonsemantic contact state
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要