Correlational Gaussian Processes for Cross-Domain Visual Recognition

Chengjiang Long, Gang Hua; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 118-126

Abstract


We present a probabilistic model that captures higher order co-occurrence statistics for joint visual recognition in a collection of images and across multiple domains. More importantly, we predict the structured output across multiple domains by correlating outputs from the multi-classes Gaussian process classifiers in each individual domain. A set of correlational tensors is adopted to model the relationship within a single domain as well as across multiple domains. This renders it possible to explore a high-order relational model instead of using just a set of pairwise relational models. Such tensor relations are based on both the positive and negative co-occurrences of different categories of visual instances across multi-domains. This is in contrast to most previous models where only pair-wise relationships are explored. We conduct experiments on four challenging image collections. The experimental results clearly demonstrate the efficacy of our proposed model.

Related Material


[pdf] [poster]
[bibtex]
@InProceedings{Long_2017_CVPR,
author = {Long, Chengjiang and Hua, Gang},
title = {Correlational Gaussian Processes for Cross-Domain Visual Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}