Author name cluster

Zhan Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

Stationary and Clustering Transformer Hashing for Cross-modal Retrieval

Zhan Yang
Yiran Liu
Youyuan Huang
Yinan Li

Unsupervised cross-modal hashing has gained significant attention for efficient retrieval between heterogeneous modalities through encoding data into the unified binary representations, offering low storage cost and fast response. However, the constraints of existing methods persist in bridging the cross-modal semantic gap and capturing fine-grained global semantic structures without explicit labels. In this paper, we propose an innovative unsupervised Stationary distribution and soft Clustering Transformer Hashing approach for cross-modal retrieval, denoted as SCTH. Initially, a Transformer-based modality fusion encoder is employed to extract abundant cross-modal semantic representations, further integrated with contrastive hashing to minimize the semantic gap. To enhance the inter-modal alignment, a pseudo-classifier clustering module with entropy-regularized contrastive loss is presented, ensuring balanced and diverse cluster assignments in unsupervised settings. Additionally, a Markovian stationary distribution strategy stabilizes the feature representations through mitigating the interference of noise and outliers. Comprehensive experiments on MIRFlickr, NUS-WIDE, and IAPR-TC12 datasets validate that SCTH outperforms state-of-the-art hashing methods in cross-modal retrieval tasks, demonstrating superior generalization performance.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis

Yinan Li
Jun Long
Zhan Yang

Hashing has been widely applied in large-scale multimodal retrieval by mapping heterogeneous modalities data into binary codes. However, most cross-modal hashing methods cannot make the most of semantic information to construct the association relations of sample pairs, resulting in unsatisfactory retrieval accuracy. Concept lattice is a powerful tool for data mining and information retrieval, and for all we know, this is the first time to combine formal concept analysis and hash learning to improve cross-modal hashing retrieval performance. In this paper, we propose a novel framework for Asymmetric Cross-modal Hashing based on Formal Concept Analysis, denoted as ACHFCA. Initially, a flash-projection three-layer semantic enhancement descriptor is designed to extract latent representations from heterogeneous modalities. Subsequently, an asymmetric hash learning framework is established to enhance the semantics of different layers based on the fine-grained similarity values reconstructed from concept lattice to reinforce the discriminative competence of the model. Finally, an effective discrete optimization algorithm is proposed, which can directly learn compact hash codes. Comprehensive experiments on MIRFlickr, NUS-WIDE and IAPR-TC12 datasets demonstrate the superior performance of ACHFCA to state-of-the-art hashing approaches.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Statistical Model-driven Similarity Hashing: Bridging Modalities for Efficient Unsupervised Retrieval

Mingjin Kuai
Jun Long
Zhan Yang

Unsupervised deep cross-modal hash retrieval aims to map multi-modal features into binary hash codes without labels, which is of interest due to its storage efficiency, query speed and convenient applications. However, existing approaches suffer from two main limitations: (1) Slightly insufficient consideration of text instance similarity, along with independent or redundant fusion to learn multi-modal similarity information. (2) They ignore the noisy adjacent correlations between multi-modal instances, leading to a lack of discriminative power in the generated hash codes. To address these challenges, we propose a new approach called Statistical Model-driven Similarity Hashing (SMSH). Specifically, we introduce Jaccard similarity when constructing the text similarity matrix. It reduces the similarity error between text instances while better considering the asymmetry of the elements in the text features. After that, we integrate the original similarity information between various modalities to construct a unified similarity matrix. The gaps between modalities are bridged while reducing the redundant information in them. In addition, we introduce a Statistical Model-driven Similarity Enhancement (SMSE) approach, which reduces the noise of similarity relations between multi-modal instances by using a Gaussian Mixture Model to keep instances with lower semantic similarity as far away from each other as possible. Experiments on three benchmark datasets demonstrate the excellent performance of the SMSH method.

PDF Details DOI