A Toet - IEEE transactions on pattern analysis and machine …, 2011 - ieeexplore.ieee.org
The predictions of 13 computational bottom-up saliency models and a newly introduced Multiscale Contrast Conspicuity (MCC) metric are compared with human visual conspicuity …
Stereoscopic 3D (S3D) displays provide an additional sense of depth compared to non- stereoscopic displays by sending slightly different images to the two eyes. But conventional …
A general standard for quantifying conspicuity is described. It derives from a simple and easy method to quantitatively measure the visual conspicuity of an object. The method stems …
Few animals can hide their signatures into their surroundings to hunt or avoid being hunted, termed as natural camouflage. Natural camouflage inspires researchers to design various …
We propose an algorithm for salient object detection (SOD) based on multi-scale graph ranking and iterative local–global object refinement. Starting from a set of multi-scale image …
We investigated how the physical differences associated with the articulation of speech affect the temporal aspects of audiovisual speech perception. Video clips of consonants and …
S Biswas, RV Babu - 2013 IEEE International Conference on …, 2013 - ieeexplore.ieee.org
In this paper, we have proposed a simple and effective approach to classify H. 264 compressed videos, by capturing orientation information from the motion vectors. Our major …
Recently, transformation‐based methods have been widely used in many computer vision areas because of their powerful representation ability. One of the most widely used …
In this article, we propose a Multi Layer Compound Markov Random Field (MLCMRF) Model to spatially segment different image frames of a given video sequence. The segmented …