paper-with-me

Papers

Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities

2023-08-01 · Kaijian Liu, Shixiang Tang, Ziyue Li, Zhishuai Li, Lei Bai, Feng Zhu, Rui Zhao

Person clustering with multi-modal clues, including faces, bodies, and voices, is critical for various tasks, such as movie parsing and identity-based movie editing. Related methods such as multi-view clustering mainly project multi-modal features into a joint feature space. However, multi-modal clue features are usually rather weakly correlated due to the semantic gap from the modality-specific uniqueness. As a result, these methods are not suitable for person clustering. In this paper, we propose a Relation-Aware Distribution representation Network (RAD-Net) to generate a distribution representation for multi-modal clues. The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering. Accordingly, we introduce a graph-based method to construct distribution representation and employ a cyclic update policy to refine distribution representation progressively. Our method achieves substantial improvements of +6% and +8.2% in F-score on the Video Person-Clustering Dataset (VPCD) and VoxCeleb2 multi-view clustering dataset, respectively. Codes will be released publicly upon acceptance.

📄 PDF Abstract BibTeX arXiv:2308.00588

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringRelation

Similar Papers 제목 키워드 기반

Distribution Context Aware Loss for Person Re-identification

2019-11-17 · Zhigang Chang, Qin Zhou, Mingyang Yu, Shibao Zheng 외

To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature embedding. How…

ClusteringMetric LearningPerson Re-IdentificationTriplet

Relation-Aware Global Attention for Person Re-identification

2019-04-05 · CVPR 2020 6 · Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Xin Jin 외

For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discrimin…

ClusteringImage ClassificationPerson Re-IdentificationRelation+1

Oracle-guided Contrastive Clustering

2022-11-01 · Mengdie Wang, Liyuan Shang, Suyun Zhao, Yiming Wang 외

Deep clustering aims to learn a clustering representation through deep architectures. Most of the existing methods usually conduct clustering with the unique goal of maximizing clustering performance, that ignores the pe…

Active LearningClusteringContrastive LearningDeep Clustering

Deep Learning-Based Approach for Improving Relational Aggregated Search

2025-10-01 · Sara Saad Soliman, Ahmed Younes, Islam Elkabani, Ashraf Elsayed arxiv

Due to an information explosion on the internet, there is a need for the development of aggregated search systems that can boost the retrieval and management of content in various formats. To further improve the clusteri…

Representation Learning

Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs

2025-03-28 · Ziye Chen, Yiqun Duan, Riheng Zhu, Zhenbang Sun 외

Personalized multiple clustering aims to generate diverse partitions of a dataset based on different user-specific aspects, rather than a single clustering. It has recently drawn research interest for accommodating varyi…

Clustering