1,443 Hits in 3.1 sec

Online Adaptive Supervised Hashing for Large-Scale Cross-Modal Retrieval

Ruoqi Su, Di Wang, Zhen Huang, Yuan Liu, Yaqiang An
2020 IEEE Access  
INDEX TERMS Multimodal hashing, cross-modal retrieval, online learning.  ...  In recent years, with the continuous growth of multimedia data on the Internet, multimodal hashing has attracted increasing attention for its efficiency in large-scale cross-modal retrieval.  ...  Online cross-modal hashing (OCMH) [3] , dynamic multi-view hashing (DMVH) [4] , and online collective matrix factorization hashing (OCMFH) [5] are representative unsupervised online multimodal hashing  ... 
doi:10.1109/access.2020.3037968 fatcat:hj2e3wiy35cufpwzpbzv2miure

Efficient Discrete Supervised Hashing for Large-scale Cross-modal Retrieval [article]

Tao Yao, Xiangwei Kong, Lianshan Yan, Wenjing Tang, Qi Tian
2019 arXiv   pre-print
In this paper, to address above issues, we propose a supervised cross-modal hashing method based on matrix factorization dubbed Efficient Discrete Supervised Hashing (EDSH).  ...  Supervised cross-modal hashing has gained increasing research interest on large-scale retrieval task owning to its satisfactory performance and efficiency.  ...  Accordingly, many discrete cross-modal hashing methods have been proposed to address this issue [3] , [9] , [10] .  ... 
arXiv:1905.01304v1 fatcat:envxs5ylgvei3ifm4bec7lvqme

Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval [article]

Lei Zhu, Zi Huang, Zhihui Li, Liang Xie, Heng Tao Shen
2019 arXiv   pre-print
The key idea is to directly augment the semantics of discrete image hash codes by exploring auxiliary contextual modalities.  ...  To address the problem, in this paper, we propose a novel hashing approach, dubbed as Discrete Semantic Transfer Hashing (DSTH).  ...  Linear cross-modal hashing (LCMH) [8] .  ... 
arXiv:1904.11207v1 fatcat:j3myydxqkza5tntcaidmonzneq

Adaptive Multi-modal Fusion Hashing via Hadamard Matrix [article]

Jun Yu, Donglin Zhang, Zhenqiu Shu, Feng Chen
2021 arXiv   pre-print
Among the techniques available in the literature, multi-modal hashing, which can encode heterogeneous multi-modal features into compact hash codes, has received particular attention.  ...  Most of the existing multi-modal hashing methods adopt the fixed weighting factors to fuse multiple modalities for any query data, which cannot capture the variation of different queries.  ...  Discrete Latent Factor model based cross-modal Hashing (DLFH) [25] directly learns the binary hash codes without continuous relaxation.  ... 
arXiv:2009.12148v4 fatcat:7izcyfkjazhvla53l4wf35j55a

Cross-Modal Retrieval for CPSS Data

Fangming Zhong, Guangze Wang, Zhikui Chen, Feng Xia, Geyong Min
2020 IEEE Access  
In this paper, we propose a nonlinear discrete cross-modal hashing (NDCMH) method based on concise binary classification for CPSS data which fully investigates the nonlinear relationship embedding, discrete  ...  Furthermore, we execute the cross-modal retrieval service at cloud and fog.  ...  Discrete Cross-Modal Hashing (DDCMH) [53] .  ... 
doi:10.1109/access.2020.2967594 fatcat:nr4ghjvhi5c3vpg2ml4eq7x3ga

Exploring Consistent Preferences

Lei Zhu, Zi Huang, Xiaojun Chang, Jingkuan Song, Heng Tao Shen
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Our approach mainly solves two essential problems in scalable landmark hashing: 1) Intralandmark visual diversity, and 2) Discrete optimization of hashing codes.  ...  In this paper, we propose a novel discrete hashing with pair-exemplar (DHPE) to support scalable and e cient large-scale CBVLS.  ...  Coordinate discrete hashing (CDH) [21] is designed for cross-modal hashing, and the discrete optimization proceeds in a block coordinate descent manner.  ... 
doi:10.1145/3123266.3123301 dblp:conf/mm/ZhuHCSS17 fatcat:macfoja72naytapxfzcmn6rz64

Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search [article]

Lei Zhu, Zi Huang, Xiaobai Liu, Xiangnan He, Jingkuan Song, Xiaofang Zhou
2017 arXiv   pre-print
In this paper, we propose a novel hashing scheme, named as canonical view based discrete multi-modal hashing (CV-DMH), to handle these problems via a novel three-stage learning procedure.  ...  Second, multi-modal sparse coding is applied to transform visual features from multiple modalities into an intermediate representation.  ...  Coordinate discrete hashing (CDH) [30] is designed for cross-modal hashing [31] , and the discrete optimization proceeds in a block coordinate descent manner.  ... 
arXiv:1707.04047v1 fatcat:in4v4b4i2zarblkbuj2ajba254

Task-adaptive Asymmetric Deep Cross-modal Hashing [article]

Fengling Li, Tong Wang, Lei Zhu, Zheng Zhang, Xinhua Wang
2022 arXiv   pre-print
Supervised cross-modal hashing aims to embed the semantic correlations of heterogeneous modality data into the binary hash codes with discriminative semantic labels.  ...  Motivated by this, we present a Task-adaptive Asymmetric Deep Cross-modal Hashing (TA-ADCMH) method in this paper.  ...  Online query hashing As we discussed earlier, TA-ADCMH is a deep asymmetric cross-modal hashing method. It learns task-adaptive hash functions for different retrieval tasks.  ... 
arXiv:2004.00197v2 fatcat:osykjo375jdy5hkpo6kbhxnbsq

Online Enhanced Semantic Hashing: Towards Effective and Efficient Retrieval for Streaming Multi-Modal Data [article]

Xiao-Ming Wu, Xin Luo, Yu-Wei Zhan, Chen-Lu Ding, Zhen-Duo Chen, Xin-Shun Xu
2022 arXiv   pre-print
The second point is that all existing online multi-modal hashing methods fail to effectively handle unseen new classes which come continuously with streaming data chunks.  ...  In this paper, we propose a new model, termed Online enhAnced SemantIc haShing (OASIS).  ...  This paper conceives a new online multi-modal hashing method and proffers an efficient and effective discrete online optimization algorithm.  ... 
arXiv:2109.04260v2 fatcat:sqerk6zx7newdilrvefj26kwje

Fusion-supervised Deep Cross-modal Hashing [article]

Li Wang, Lei Zhu, En Yu, Jiande Sun, Huaxiang Zhang
2020 arXiv   pre-print
Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages.  ...  In this paper, we propose a novel Fusion-supervised Deep Cross-modal Hashing (FDCH) approach.  ...  It has a closed-form solution as follow: W2 = β Y Y T + I −1 Y G T (14) Online Cross-modal Retrieval For a new query that is out of the retrieval database, we can easily obtain its hash code as long  ... 
arXiv:1904.11171v2 fatcat:u7jcf2h2fzajvcyyo4y5akar3i

Deep Semantic Multimodal Hashing Network for Scalable Multimedia Retrieval [article]

Zechao Li, Lu Jin, Jinhui Tang
2019 arXiv   pre-print
We conduct extensive experiments for both unimodal and cross-modal retrieval tasks on three widely-used multimodal retrieval datasets.  ...  In DSMHN, two sets of modality-specific hash functions are jointly learned by explicitly preserving both the inter-modality similarities and the intra-modality semantic labels.  ...  Deep Cross-Modal Hashing (DCMH) [73] directly learns unified discrete hash codes with the deep neural networks.  ... 
arXiv:1901.02662v2 fatcat:r6o3pql7nrhxbnr62ytoxojn24

Supervised Matrix Factorization for Cross-Modality Hashing [article]

Hong Liu, Rongrong Ji, Yongjian Wu, Gang Hua
2016 arXiv   pre-print
In this paper, we propose a novel cross-modality hashing algorithm termed Supervised Matrix Factorization Hashing (SMFH) which tackles the multi-modal hashing problem with a collective non-matrix factorization  ...  Matrix factorization has been recently utilized for the task of multi-modal hashing for cross-modality visual search, where basis functions are learned to map data from different modalities to the same  ...  However, the integration of both approaches towards supervised cross-modality hashing is not an easy task. In one aspect, it is hard to optimize the discrete Hamming distances.  ... 
arXiv:1603.05572v5 fatcat:yi4yj675kzhmlp3m4ke5myayq4

Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [article]

Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen, Ngai-Man Cheung
2021 arXiv   pre-print
We proposed a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH).  ...  In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval.  ...  Hashing (SMH) [3] , Quantized Correlation Hashing (QCH) [4] , Semantics-Preserving Hashing (SePH) [5] , Discrete Cross-modal Hashing (DCH) [6] , and Supervised Matrix Factorization Hashing (SMFH)  ... 
arXiv:2112.06489v1 fatcat:5gfpy7t5jnbvjoodg4mrs4awxi

Unsupervised Visual Hashing with Semantic Assistant for Content-Based Image Retrieval

Lei Zhu, Jialie Shen, Liang Xie, Zhiyong Cheng
2017 IEEE Transactions on Knowledge and Data Engineering  
In this study, we propose a novel unsupervised visual hashing approach called semantic-assisted visual hashing (SAVH).  ...  visual hashing without any explicit semantic labels.  ...  Unsupervised Cross-Modal Hashing The core idea of UCMH is to map heterogeneous modalities into the common Hamming space, where similarities are computed to return cross-modal retrieval results.  ... 
doi:10.1109/tkde.2016.2562624 fatcat:uawbxj6uebdipjue5qcpcpiv2q

Transitive Hashing Network for Heterogeneous Multimedia Retrieval [article]

Zhangjie Cao, Mingsheng Long, Qiang Yang
2016 arXiv   pre-print
Existing work on cross-modal hashing assumes heterogeneous relationship across modalities for hash function learning.  ...  Cross-modal hashing enables efficient retrieval from database of one modality in response to a query of another modality.  ...  The codes and configurations will be made available online. Results NUS-WIDE: We follow the experimental protocols in [2] .  ... 
arXiv:1608.04307v1 fatcat:l2xakppke5b5vgwcgs7wwliufq
« Previous Showing results 1 — 15 out of 1,443 results