<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">
Repository logo

MoM: Multi-to-Multi Identification of Decoupled Multifaceted Clustering with Dynamic Representation Fusion

Loading...
Thumbnail Image

Files

Size: 11.66 MB, File format: Adobe PDF

Authors

Zhang, Peipei

Zhu, Wenjie

Zhou, Qinli

Yan, Wei Qi

Supervisor

Degree name

Journal Title

Journal ISSN

Volume Title

Publisher

ACM

Abstract

Multifaceted clustering is dedicated to excavating diverse and heterogeneous facets from complex multimedia data, which is a critical task for multimedia content understanding. Existing approaches primarily focus on decomposing a single dataset into multiple subspaces or sequentially generating alternative clusterings. However, these methods are severely constrained by the inherent limited information contained in the data itself, resulting in suboptimal clustering performance and indistinct facet mining results. To address the issue, we propose a novel paradigm shift from Single-to-Multi to Multi-to-Multi (MoM) clustering for multimedia data, which proactively integrates multiple informative views for decoupled multifaceted discovery, breaking the bottleneck of single-source data information scarcity. The proposed MoM framework consists of two core modules: the Dynamic Representation Fusion (DRF) module and the Decoupled Multifaceted Clustering (DMC) module. Specifically, the DRF module implements an adaptive fusion strategy that generates and dynamically fuses diverse representations guided by the anchors derived from a pretrained model, ensuring both fidelity and diversity. The DMC module leverages a structured self-expression model to jointly learn shared and facet-specific affinity matrices, producing well-separated and interpretable clusters. Unlike existing methods that passively decompose limited data into disjoint subspaces, our end-to-end framework actively employs a clustering-oriented representation fusion strategy to learn decoupled features tailored to each clustering facet. Extensive experiments show that MoM consistently outperforms state-of-the-art multifaceted clustering methods, validating the effectiveness of our MoM framework.

Description

Keywords

46 Information and Computing Sciences, 4611 Machine Learning, Networking and Information Technology R&D (NITRD), deep multifaceted clustering, dynamic representation fusion, decoupled representation learning

Source

MM '26: Proceedings of the 34th ACM International Conference on Multimedia. Rio de Janeiro, Brazil. November 10 - 14, 2026. Pages 14616 - 14625. ISBN: 9798400722134 DOI: 10.1145/3767308

Rights statement

© 2026 Owner/Author. Open access.

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwise noted, this item's license is described as Creative Commons Attribution 4.0