Visual Graph Mining

TL;DR

This paper introduces a novel approach for mining maximal-size frequent subgraphs in visual data, enabling the discovery of common objects in cluttered, unlabeled images and videos by addressing data fuzziness and variability.

Contribution

It formulates a new definition of visual subgraph patterns and proposes an efficient approximate method for mining these patterns in complex visual data.

Findings

Method successfully mines common patterns in diverse visual datasets

Demonstrates robustness to data fuzziness and variability

Validates generality across videos and RGB/RGB-D images

Abstract

In this study, we formulate the concept of "mining maximal-size frequent subgraphs" in the challenging domain of visual data (images and videos). In general, visual knowledge can usually be modeled as attributed relational graphs (ARGs) with local attributes representing local parts and pairwise attributes describing the spatial relationship between parts. Thus, from a practical perspective, such mining of maximal-size subgraphs can be regarded as a general platform for discovering and modeling the common objects within cluttered and unlabeled visual data. Then, from a theoretical perspective, visual graph mining should encode and overcome the great fuzziness of messy data collected from complex real-world situations, which conflicts with the conventional theoretical basis of graph mining designed for tabular data. Common subgraphs hidden in these ARGs usually have soft attributes, with considerable inter-graph variation. More importantly, we should also discover the latent pattern space, including similarity metrics for the pattern and hidden node relations, during the mining process. In this study, we redefine the visual subgraph pattern that encodes all of these challenges in a general way, and propose an approximate but efficient solution to graph mining. We conduct five experiments to evaluate our method with different kinds of visual data, including videos and RGB/RGB-D images. These experiments demonstrate the generality of the proposed method.