A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks
Abstract
In this paper, we present an efficient alternative to the traditional vocabulary based on bag-of-visual words (BoW) used for visual classification tasks. Our representation is both conceptually and computationally superior to the bag-of-visual words: (1) We iteratively generate a Maximum Likelihood estimate of an image given a set of characteristic features in contrast to the BoW methods where an image is represented as a histogram of visual words, (2) We randomly sample a set of characteristic features instead of employing computation-intensive clustering algorithms used during the vocabulary generation step of BoW methods. Our performance compares favorably to the state-of-the-art on experiments over three challenging human action and a scene categorization dataset, demonstrating the universal applicability of our method.
Cite
Text
Bhattacharya et al. "A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995746Markdown
[Bhattacharya et al. "A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/bhattacharya2011cvpr-probabilistic/) doi:10.1109/CVPR.2011.5995746BibTeX
@inproceedings{bhattacharya2011cvpr-probabilistic,
title = {{A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks}},
author = {Bhattacharya, Subhabrata and Sukthankar, Rahul and Jin, Rong and Shah, Mubarak},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2011},
pages = {2593-2600},
doi = {10.1109/CVPR.2011.5995746},
url = {https://mlanthology.org/cvpr/2011/bhattacharya2011cvpr-probabilistic/}
}