Improving Image Clustering using Sparse Text and the Wisdom of the Crowds

TL;DR

This paper introduces a novel image clustering approach that leverages sparse text data and crowd-sourced knowledge by fusing image and text features through a common dictionary, enhancing clustering accuracy.

Contribution

It presents a new fusion method combining image and text features using a shared dictionary and applies topic modeling for improved clustering performance.

Findings

Enhanced clustering accuracy with fused features

Effective use of crowd wisdom via a common dictionary

Improved topic modeling results

Abstract

We propose a method to improve image clustering using sparse text and the wisdom of the crowds. In particular, we present a method to fuse two different kinds of document features, image and text features, and use a common dictionary or "wisdom of the crowds" as the connection between the two different kinds of documents. With the proposed fusion matrix, we use topic modeling via non-negative matrix factorization to cluster documents.