Cluster Canonical Correlation Analysis

By Nikhil Rasiwasia et al
Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Related Work
3. Canonical Correlation Analysis (CCA)
4. Cluster Canonical Correlation Analysis
4.1 Mean Canonical Correlation Analysis
4.2 Cluster Canonical Correlation Analysis
4.3 Cluster Kernel Canonical Correlation Analysis
5. Experiments
5.1 Datasets
5.2 Features

Summary

Cluster Canonical Correlation Analysis is a paper that introduces cluster-CCA as a technique for joint dimensionality reduction of two sets of data points, with a focus on multiple clusters or classes within each set. The paper discusses the problem setting, proposed solutions including mean-CCA and cluster-KCCA, computational complexities, and experimental evaluations on various datasets for cross-modal retrieval tasks.
×
This is where the content will go.