Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

最新推荐文章于 2022-07-04 19:22:24 发布

转载最新推荐文章于 2022-07-04 19:22:24 发布 · 1.6k 阅读

文章标签：

#action #localization #video #semantic #algorithm #behavior

本文介绍了一种新颖的无监督学习方法，用于学习人类行动类别。通过提取空间-时间兴趣点将视频序列表示为时空词集合，算法自动学习这些时空词的概率分布以及对应于人类行动类别的中间主题。该方法不仅能够进行不同行动的分类，还能同时在新颖且复杂的视频序列中定位多种行动。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

Juan Carlos Niebles^1,2, Hongcheng Wang¹, Li Fei-Fei¹

¹University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
²Universidad del Norte, Barranquilla, Colombia

Summary

To automatically classify or localize different actions in video sequences is very useful for a variety of tasks, such as video surveillance, object-level video summarization, video indexing, digital library organization, etc. However, it remains a challenging task for computers to achieve robust action recognition due to cluttered background, camera motion, occlusion, and geometric and photometric variances of objects.

We present a novel unsupervised learning method for learning human action categories. A video sequence is represented as a collection of spatial-temporal words by extracting space-time interest points. The algorithm learns the probability distributions of the spatial-temporal words and intermediate topics corresponding to human action categories automatically using a probabilistic Latent Semantic Analysis (pLSA) model. The learned model is then used for human action categorization and localization in a novel video, by maximizing the posterior of action category (topic) distributions. The contributions of this work are as follows:

Unsupervised learning of actions using 'video words' representation: We deploy a pLSA model with 'bag of video words' representation for video analysis;
Multiple action localization and categorization: Our approach is not only able to classify different actions, but also to localize different actions simultaneously in a novel and complex video sequence.

Our Algorithm

Resources

Juan Carlos Niebles, Hongcheng Wang and Li Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, Accepted for Oral Presentation At British Machine Vision Conference (BMVC), Edinburgh, 2006.
Full Text: PDF
Juan Carlos Niebles, Hongcheng Wang and Li Fei-Fei, Unsupervised Learning of Human Action Categories, in Video Proceedings, International Conference on Computer Vision and Pattern Recognition (VPCVPR), New York, 2006.
Full Text: PDF (One Page)
Video Demo: AVI
There is also a poster about this work, presented at IMA Workshop: Visual Learning and Recognition, Minneapolis, 2006.

Selected References

Piotr Dollár, Vincent Rabaud, Garrison Cottrell and Serge Belongie. Behavior Recognition via Sparse Spatio-Temporal Features. VS-PETS 2005, Beijing, China.
Author site: http://vision.ucsd.edu/~pdollar/research/research.html