跳到主要导航 跳到搜索 跳到主要内容

Predicting Human Activities Using Stochastic Grammar

  • Siyuan Qi
  • , Siyuan Huang
  • , Ping Wei
  • , Song Chun Zhu
  • University of California at Los Angeles

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

83 引用 (Scopus)

摘要

This paper presents a novel method to predict future human activities from partially observed RGB-D videos. Human activity prediction is generally difficult due to its non-Markovian property and the rich context between human and environments. We use a stochastic grammar model to capture the compositional structure of events, integrating human actions, objects, and their affordances. We represent the event by a spatial-temporal And-Or graph (ST-AOG). The ST-AOG is composed of a temporal stochastic grammar defined on sub-activities, and spatial graphs representing sub-activities that consist of human actions, objects, and their affordances. Future sub-activities are predicted using the temporal grammar and Earley parsing algorithm. The corresponding action, object, and affordance labels are then inferred accordingly. Extensive experiments are conducted to show the effectiveness of our model on both semantic event parsing and future activity prediction.

源语言英语
主期刊名Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
出版商Institute of Electrical and Electronics Engineers Inc.
页1173-1181
页数9
ISBN(电子版)9781538610329
DOI
出版状态已出版 - 22 12月 2017
活动16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, 意大利
期限: 22 10月 2017 → 29 10月 2017

丛书

姓名Proceedings of the IEEE International Conference on Computer Vision
卷2017-October
ISSN(印刷版)1550-5499

会议

会议16th IEEE International Conference on Computer Vision, ICCV 2017
国家/地区意大利
市Venice
时期22/10/17 → 29/10/17

学术指纹

探究 'Predicting Human Activities Using Stochastic Grammar' 的科研主题。它们共同构成独一无二的学术指纹。

引用此