Article
Computer Science, Artificial Intelligence
Xiaohan Yang, Zhen Wang, Wenhao Liu, Xinyi Chang, Nannan Wu
Summary: In recent years, researchers have been using hashing algorithms to improve the efficiency of large-scale cross-modal retrieval by mapping features into binary codes. However, existing cross-modal hashing algorithms often overlook the multi-label information by focusing only on single class labels. To address this issue, we propose DAMCH, a deep adversarial multi-label cross-modal hashing algorithm that considers both multi-label and deep features. Our algorithm preserves the Hamming neighbor relationship and ensures the same semantic information in binary features as in the original label. Additionally, our algorithm minimizes information loss during feature mapping and ensures consistent feature distribution across modalities. Experimental results show that DAMCH outperforms state-of-the-art methods.
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
(2023)
Article
Computer Science, Information Systems
Fan Yang, Qiaoxi Zhang, Fumin Ma, Xiaojian Ding, Yufeng Liu, Deyu Tong
Summary: This paper proposes an efficient discrete cross-modal hashing method that incorporates an asymmetric model, semantic supervised intersection scheme, category correlations embedding, optimization strategy, and linear projection to improve retrieval performance and effectiveness.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Ge Song, Xiaoyang Tan, Jun Zhao, Ming Yang
Summary: RMSH is designed for more accurate multi-label cross-modal retrieval, addressing modality discrepancies and noise through fine-grained similarity of rich semantics and robust margin-adaptive triplet loss. The effective bounds derived from information coding-theoretic analysis enable our method to achieve state-of-the-art performance on multiple benchmarks.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Xitao Zou, Song Wu, Erwin M. Bakker, Xinzhi Wang
Summary: In this paper, a novel multi-label enhancement based self-supervised deep cross-modal hashing approach is proposed to capture semantic affinity more accurately and avoid noise in modalities, achieving state-of-the-art performance in cross-modal hashing retrieval applications.
Article
Engineering, Electrical & Electronic
Xitao Zou, Xinzhi Wang, Erwin M. Bakker, Song Wu
Summary: This paper introduces a deep cross-modal hashing method based on multi-label semantics preservation, aiming to improve the accuracy of hashing retrieval by leveraging multiple labels of training data. Experimental results demonstrate that the proposed method outperforms prominent baselines and achieves state-of-the-art performance in cross-modal hashing retrieval.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Chunpu Sun, Huaxiang Zhang, Li Liu, Dongmei Liu, Lin Wang
Summary: In this paper, a novel Multi-label Adversarial Fine-grained Cross-modal Retrieval Based on Transformer (MLAT) method is proposed to bridge the semantic gap and eliminate modal specific features. The method constructs a semantic consistency enhanced module and a multi-stage adversarial learning module to optimize feature representations.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Computer Science, Artificial Intelligence
Xin Shu, Guoying Zhao
Summary: In this paper, a novel framework is proposed to integrate semantic correlation and feature correlation for cross-modal retrieval. By using semantic transformation, the model avoids explicitly computing the covariance matrix, which leads to a huge saving of computational cost. Experimental results demonstrate the accuracy and efficiency of the proposed method on three multi-label datasets.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Youxiang Duan, Ning Chen, Peiying Zhang, Neeraj Kumar, Lunjie Chang, Wu Wen
Summary: This study proposes a novel deep hashing method called MS(2)GAH, which integrates Graph Attention Networks (GATs) to establish cross-modal hashing. It utilizes multi-label annotations to enhance semantic relevance between modalities, and uses an end-to-end label encoder to guide feature extraction of specific-modality networks, narrowing the modality gap.
PATTERN RECOGNITION
(2022)
Article
Engineering, Civil
Rushi Lan, Yu Tan, Xiaoqin Wang, Zhenbing Liu, Xiaonan Luo
Summary: This paper proposes a novel supervised hashing method, LGDH, which simultaneously preserves the comprehensive manifold structure and discriminative balanced codes in the Hamming space. By utilizing local category distribution and label-guided matrix construction, LGDH improves the discriminative power and balance of hash codes. Extensive experiments show that LGDH outperforms other methods in cross-modal tasks.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Donglin Zhang, Xiao-Jun Wu, Jun Yu
Summary: The novel cross-media hashing approach, LFMH, learns modality-specific latent subspace with similar semantic using flexible matrix factorization and guides hash learning with semantic labels. This method addresses issues related to representing cross-media data and preserving similarity relationships effectively.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
XianHua Zeng, Ke Xu, YiCai Xie
Summary: With the rapid development of big data and the Internet, cross-modal retrieval has become a popular research topic. Cross-modal hashing is an important research direction in cross-modal retrieval, and recent unsupervised methods have achieved great results. However, narrowing the heterogeneous gap between different modalities and generating more discriminative hash codes remain the main challenges. In this paper, we propose a novel unsupervised cross-modal hashing method called Pseudo-label Driven Deep Hashing to address these challenges. Experimental results demonstrate the superiority of our method compared to several unsupervised cross-modal hashing methods.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian
Summary: The proposed FLPCL method utilizes deep feature learning and partial correlation learning to infer relationships between modalities and learn effective multimodal representations. It outperforms state-of-the-art methods on cross-modal retrieval tasks.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Lei Zhu, Jiayu Song, Xiangxiang Wei, Hao Yu, Jun Long
Summary: The paper presents a concept augmentation-based method CAESAR for cross-modal retrieval, which includes cross-modal correlation learning and concept augmentation-based semantic mapping learning. By developing a multi-modal CNNs based CCA model and a concept learning model CaeNet, the approach captures semantic information and learns semantic relationships between multi-modal samples.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Jinghua Liu, Songwei Yang, Yaojin Lin, Chenxi Wang, Cheng Wang, Jixiang Du
Summary: Multi-label feature selection is an important task in processing multi-semantic high-dimensional data. This paper proposes a new algorithm called FSEP, which considers label significance and pairwise label correlations. The proposed method achieves encouraging results compared with state-of-the-art MFS algorithms, as demonstrated by extensive experiments.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Shengsheng Qian, Dizhan Xue, Quan Fang, Changsheng Xu
Summary: With the increasing amount of multimodal data, cross-modal retrieval has become a hot research topic, but existing techniques have limitations in eliminating modality heterogeneity, considering label relationships, and efficiently aligning representation and label similarity. To address these problems, this article proposes two models that use dual generative adversarial networks to project multimodal data into a common representation space, employ multi-hop graph neural networks to model label relation dependencies, and introduce a novel soft multi-label contrastive loss to align representation and label similarity. Experimental results on three benchmark datasets demonstrate the superiority of the proposed method.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)