Recognizing human actions with outlier frames by observation filtering and completion

4Citations
Citations of this article
18Readers
Mendeley users who have this article in their library.
Get full text

Abstract

This article addresses the problem of recognizing partially observed human actions. Videos of actions acquired in the realworld 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 present.

References Powered by Scopus

Learning spatiotemporal features with 3D convolutional networks

7966Citations
N/AReaders
Get full text

Long-term recurrent convolutional networks for visual recognition and description

4132Citations
N/AReaders
Get full text

A bayesian hierarchical model for learning natural scene categories

3318Citations
N/AReaders
Get full text

Cited by Powered by Scopus

You2me: Inferring body pose in egocentric video via first and second person interactions

70Citations
N/AReaders
Get full text

Online early-late fusion based on adaptive HMM for sign language recognition

54Citations
N/AReaders
Get full text

Cross-Domain Knowledge Transfer for Skeleton-based Action Recognition based on Graph Convolutional Gradient Reversal Layer

1Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Lin, S. Y., Lin, Y. Y., Chen, C. S., & Hung, Y. P. (2017). Recognizing human actions with outlier frames by observation filtering and completion. ACM Transactions on Multimedia Computing, Communications and Applications, 13(3). https://doi.org/10.1145/3089250

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 8

80%

Lecturer / Post doc 1

10%

Researcher 1

10%

Readers' Discipline

Tooltip

Computer Science 5

45%

Engineering 5

45%

Sports and Recreations 1

9%

Save time finding and organizing research with Mendeley

Sign up for free