Fine-grained similarity semantic preserving deep hashing for cross-modal retrieval

被引:0
|
作者
Li, Guoyou [1 ]
Peng, Qingjun [2 ]
Zou, Dexu [2 ]
Yang, Jinyue [2 ]
Shu, Zhenqiu [3 ]
机构
[1] Yunnan Power Grid Corp, Kunming, Peoples R China
[2] Yunnan Power Grid Corp, Elect Power Res Inst, Kunming, Peoples R China
[3] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming, Peoples R China
基金
中国国家自然科学基金;
关键词
cross-modal fusion; similarity semantic preserving; quantization loss; deep hashing; intra-modal similarity; inter-modal similarity; fine-grained similarity; NETWORK;
D O I
10.3389/fphy.2023.1194573
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Cross-modal hashing methods have received wide attention in cross-modal retrieval owing to their advantages in computational efficiency and storage cost. However, most existing deep cross-modal hashing methods cannot employ both intra-modal and inter-modal similarities to guide the learning of hash codes and ignore the quantization loss of hash codes, simultaneously. To solve the above problems, we propose a fine-grained similarity semantic preserving deep hashing (FSSPDH) for cross-modal retrieval. Firstly, this proposed method learns different hash codes for different modalities to preserve the intrinsic property of each modality. Secondly, the fine-grained similarity matrix is constructed by using labels and data features, which not only maintains the similarity between and within modalities. In addition, quantization loss is used to learn hash codes and thus effectively reduce information loss caused during the quantization procedure. A large number of experiments on three public datasets demonstrate the advantage of the proposed FSSPDH method.
引用
收藏
页数:10
相关论文
共 50 条
  • [31] TECMH: Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval
    Li, Qiqi
    Ma, Longfei
    Jiang, Zheng
    Li, Mingyong
    Jin, Bo
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 75 (02): : 3713 - 3728
  • [32] Two-Stage Asymmetric Similarity Preserving Hashing for Cross-Modal Retrieval
    Huang, Junfan
    Kang, Peipei
    Han, Na
    Chen, Yonghao
    Fang, Xiaozhao
    Gao, Hongbo
    Zhou, Guoxu
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (01) : 429 - 444
  • [33] Deep Multi-Level Semantic Hashing for Cross-Modal Retrieval
    Ji, Zhenyan
    Yao, Weina
    Wei, Wei
    Song, Houbing
    Pi, Huaiyu
    IEEE ACCESS, 2019, 7 : 23667 - 23674
  • [34] Generalized Semantic Preserving Hashing for n-Label Cross-Modal Retrieval
    Mandal, Devraj
    Chaudhury, Kunal N.
    Biswas, Soma
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2633 - 2641
  • [35] Fast Semantic Preserving Hashing for Large-Scale Cross-Modal Retrieval
    Wang, Xingzhi
    Liu, Xin
    Peng, Shujuan
    Cheung, Yiu-ming
    Hu, Zhikai
    Wang, Nannan
    2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019), 2019, : 1348 - 1353
  • [36] Label-Based Deep Semantic Hashing for Cross-Modal Retrieval
    Weng, Weiwei
    Wu, Jiagao
    Yang, Lu
    Liu, Linfeng
    Hu, Bin
    NEURAL INFORMATION PROCESSING (ICONIP 2019), PT III, 2019, 11955 : 24 - 36
  • [37] Semantic-Consistent and Multilayer Similarity Based Cross-Modal Hashing Retrieval
    Liu, Yuanyuan
    Wang, Xiaoyan
    Zhang, Yuxin
    Zhu, Lu
    Data Analysis and Knowledge Discovery, 2024, 8 (07) : 89 - 102
  • [38] Deep Saliency Hashing for Fine-Grained Retrieval
    Jin, Sheng
    Yao, Hongxun
    Sun, Xiaoshuai
    Zhou, Shangchen
    Zhang, Lei
    Hua, Xiansheng
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 5336 - 5351
  • [39] Deep Cross-modal Hashing Based on Intra-modal Similarity and Semantic Preservation
    Li T.
    Liu L.
    Data Analysis and Knowledge Discovery, 2023, 7 (05) : 105 - 115
  • [40] VIDEO-MUSIC RETRIEVAL WITH FINE-GRAINED CROSS-MODAL ALIGNMENT
    Era, Yuki
    Togo, Ren
    Maeda, Keisuke
    Ogawa, Takahiro
    Haseyama, Miki
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 2005 - 2009