Efficiently Exploiting the Context of Object-Action Context for Object Recognition
Article No.: 84, Pages 1 - 4
Abstract
This research features object recognition that exploits the context of object-action to enhance the recognition performance. We propose an efficient method that integrates human interaction with objects into object recognition using a Bayesian approach based on a simple probabilistic graph model. Experimental results show that our method of using the object-action context is quite effective for object recognition despite of large variation in the appearance of objects.
References
[1]
Moor, D. J., Essa, I. A. and Hays, M. H.1999. Exploiting Human Actions and Object Context for Recognition Tasks. In Proceedings of the International Conference Computer Vision (Kerkyra, Greece, September 20--27, 1999). 80--86.
[2]
Gupta, A., Kembhavi, A. and Davis, L. S. 2009. Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition. IEEE Trans. on Pattern Anal. Mach. Intell. 31, 10 (Oct. 2009), 1775--1798.
[3]
Yao, B. and FeiFei, L. 2012. Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses. IEEE Trans. Pattern Anal. Mach. Intell. 34, 9 (Sept. 2012), 1691--1703.
[4]
Raptis, M. and Sigal, L. 2013. Poselet Key- framing: A Model for Human Activity Recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (Portland, Oregon, USA, June 23--28, 2013). 2650--2657.
[5]
Zhu, J., Zou, H., Rosset, S. and Hastie, T. 2009. Multi-class Adaboost. Statistics and Its Interface. 2, 3, 349--360.
[6]
Maji, S., Bourdev, L.D. and Malik, J. 2011. Action Recognition from a Distributed Representation of Pose and Appearance. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (Colorado, Springs, USA, June 20--25, 2011). 3177--3184
[7]
Bourdev, L., Yang, F. and Fergus, R. 2014. Deep Poselets for Human Detection. arXiv:1407.0717.
[8]
Dalal, N. and Triggs, B. 2005. Histogram of Oriented Gradients for Human Detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (San Diego, CA, USA, June 20--25, 2005). 886--893.
[9]
Action videos. https://vision.skku.ac.kr
[10]
Google Images. https://images.google.com
[11]
ImageNet. https://www.image-net.org
Index Terms
- Efficiently Exploiting the Context of Object-Action Context for Object Recognition
Recommendations
Context based object categorization: A critical survey
The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images include occlusion, poor quality, noise or background clutter, and this task becomes ...
Visual object-action recognition: Inferring object affordances from human demonstration
This paper investigates object categorization according to function, i.e., learning the affordances of objects from human demonstration. Object affordances (functionality) are inferred from observations of humans using the objects in different types of ...
Context-based object recognition
PerMIS '09: Proceedings of the 9th Workshop on Performance Metrics for Intelligent SystemsSeveral methods have been developed for context-based object recognition within aerial imagery. These methods were inspired by human object recognition, which has been shown to rely on contextual information as opposed to classical appearance based ...
Comments
Information & Contributors
Information
Published In
January 2016
658 pages
ISBN:9781450341424
DOI:10.1145/2857546
Copyright © 2016 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
- SIGAPP: ACM Special Interest Group on Applied Computing
- SKKU: SUNGKYUNKWAN UNIVERSITY
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 January 2016
Check for updates
Author Tags
Qualifiers
- Short-paper
- Research
- Refereed limited
Funding Sources
Conference
IMCOM '16
Sponsor:
- SIGAPP
- SKKU
IMCOM '16: The 10th International Conference on Ubiquitous Information Management and Communication
January 4 - 6, 2016
Danang, Viet Nam
Acceptance Rates
Overall Acceptance Rate 213 of 621 submissions, 34%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 64Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in