Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion

Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion SHIH-YAO LIN, National Taiwan University YEN-YU LIN and CHU-SONG CHEN, Academia Sinica YI-PING HUNG, Tainan National University of the Arts This article addresses the problem of recognizing partially observed human actions. Videos of actions acquired in the real world often contain corrupt frames caused by various factors. These frames may appear irregularly, and make the actions only partially observed. They change the appearance of actions and degrade the performance of pretrained recognition systems. In this article, we propose an approach to address the corrupt-frame problem without knowing their locations and durations in advance. The proposed approach includes two key components: outlier filtering and observation completion. The former identifies and filters out unobserved frames, and the latter fills up the filtered parts by retrieving coherent alternatives from training data. Hidden Conditional Random Fields (HCRFs) are then used to recognize the filtered and completed actions. Our approach has been evaluated on three datasets, which contain both fully observed actions and partially observed actions with either real or synthetic corrupt frames. The experimental results show that our approach performs favorably against the other state-of-the-art methods, especially when corrupt frames are http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) Association for Computing Machinery

Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion

Download PDF
23 pages

Loading next page...
 
/lp/association-for-computing-machinery/recognizing-human-actions-with-outlier-frames-by-observation-filtering-MJqjQ7DLa9
Publisher
Association for Computing Machinery
Copyright
Copyright © 2017 by ACM Inc.
ISSN
1551-6857
DOI
10.1145/3089250
Publisher site
See Article on Publisher Site

Abstract

Recognizing Human Actions with Outlier Frames by Observation Filtering and Completion SHIH-YAO LIN, National Taiwan University YEN-YU LIN and CHU-SONG CHEN, Academia Sinica YI-PING HUNG, Tainan National University of the Arts This article addresses the problem of recognizing partially observed human actions. Videos of actions acquired in the real world often contain corrupt frames caused by various factors. These frames may appear irregularly, and make the actions only partially observed. They change the appearance of actions and degrade the performance of pretrained recognition systems. In this article, we propose an approach to address the corrupt-frame problem without knowing their locations and durations in advance. The proposed approach includes two key components: outlier filtering and observation completion. The former identifies and filters out unobserved frames, and the latter fills up the filtered parts by retrieving coherent alternatives from training data. Hidden Conditional Random Fields (HCRFs) are then used to recognize the filtered and completed actions. Our approach has been evaluated on three datasets, which contain both fully observed actions and partially observed actions with either real or synthetic corrupt frames. The experimental results show that our approach performs favorably against the other state-of-the-art methods, especially when corrupt frames are

Journal

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) – Association for Computing Machinery

Published: Jul 12, 2017

There are no references for this article.