Saliency Detection by Multiple-Instance Learning
- 7 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 43 (2), 660-672
- https://doi.org/10.1109/tsmcb.2012.2214210
Abstract
Saliency detection has been a hot topic in recent years. Its popularity is mainly because of its theoretical meaning for explaining human attention and applicable aims in segmentation, recognition, etc. Nevertheless, traditional algorithms are mostly based on unsupervised techniques, which have limited learning ability. The obtained saliency map is also inconsistent with many properties of human behavior. In order to overcome the challenges of inability and inconsistency, this paper presents a framework based on multiple-instance learning. Low-, mid-, and high-level features are incorporated in the detection procedure, and the learning ability enables it robust to noise. Experiments on a data set containing 1000 images demonstrate the effectiveness of the proposed framework. Its applicability is shown in the context of a seam carving application.Keywords
This publication has 35 references indexed in Scilit:
- Image saliency: From intrinsic to extrinsic contextPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Global contrast based salient region detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Robust Object Tracking with Online Multiple Instance LearningIeee Transactions On Pattern Analysis and Machine Intelligence, 2010
- An Object-Based Visual Attention Model for Robotic ApplicationsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2010
- SUN: A Bayesian framework for saliency using natural statisticsJournal of Vision, 2008
- Learning to Detect A Salient ObjectPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Visual attention detection in video sequences using spatiotemporal cuesPublished by Association for Computing Machinery (ACM) ,2006
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997
- Neural Mechanisms of Selective Visual AttentionAnnual Review of Neuroscience, 1995
- The principles of psychology, Vol I.Published by American Psychological Association (APA) ,1890