3,989 Hits in 3.5 sec

MESH: A Flexible Manifold-Embedded Semantic Hashing for Cross-Modal Retrieval

Fangming Zhong, Guangze Wang, Zhikui Chen, Feng Xia
2020 IEEE Access  
To address these issues, in this article, we propose a two-step cross-modal retrieval method named Manifold-Embedded Semantic Hashing (MESH).  ...  Moreover, the two-step scheme makes MESH flexible to various hashing functions.  ...  To address these two issues, in this article, we propose a two-step cross-modal retrieval method named Manifold-Embedded Semantic Hashing (MESH).  ... 
doi:10.1109/access.2020.3015528 fatcat:k42zalqde5afbk5hlw3sj736im

Cross-Modal Hashing by lp -Norm Multiple Subgraph Combination

Dongxiao Ren, Junwei Huang, Zhonghua Wang, Fang Lu
2021 IEEE Access  
To better deal with diversified real world data, we propose MSC, a novel cross-modal hashing approach based on the generalized l p -norm Multiple Subgraph Combination.  ...  INDEX TERMS Cross-modal hashing, feature combination, information fusion. 19682 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Step 3 (Hash Function Learning): Based on the learned hash codes, we design a cross-modal self-taught hash function learning procedure.  ... 
doi:10.1109/access.2021.3052605 fatcat:budiej6vsvfvtki2pu2uzjudii

Supervised Matrix Factorization Hashing for Cross-Modal Retrieval

Jun Tang, Ke Wang, Ling Shao
2016 IEEE Transactions on Image Processing  
The target of cross-modal hashing is to embed heterogeneous multimedia data into a common low-dimensional Hamming space, which plays a pivotal part in multimedia retrieval due to the emergence of big multimodal  ...  To address this issue, we propose a cross-modal hashing method based on collective matrix factorization, which considers both the label consistency across different modalities and the local geometric consistency  ...  Regularized cross-modal hashing (RCMH) [33] employs a three-step strategy, including hashing, regularization and partitioning, to learn a common multi-modal Hamming space.  ... 
doi:10.1109/tip.2016.2564638 pmid:27168597 fatcat:ihinkjn3hraj7hljppsqci7pja

Online Cross-Modal Scene Retrieval by Binary Representation and Semantic Graph

Mengshi Qi, Yunhong Wang, Annan Li
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Further more, we propose a two-step optimization procedure based on stochastic gradient descent for online update.  ...  To address the aforementioned problems, we propose a new framework for online cross-modal scene retrieval based on binary representations and semantic graph.  ...  Cross-modal similarity-sensitive hashing (CMSSH) [2] use Adaboost method to construct hash function for each modality. Cross-view hashing (CVH) [17] extends spectral hashing to cross-modal.  ... 
doi:10.1145/3123266.3123311 dblp:conf/mm/QiWL17 fatcat:5r2isvhhxfe3lmnbfd5as5jc4a

Cross-Modal Self-Taught Hashing for large-scale image retrieval

Liang Xie, Lei Zhu, Peng Pan, Yansheng Lu
2016 Signal Processing  
Experimental results on two web image datasets demonstrate the effectiveness of CMSTH compared to representative cross-modal and unimodal hashing methods.  ...  Then we use Robust Matrix Factorization (RMF) to transfer the multi-modal topics to hash codes which are more suited to quantization, and these codes form a unified hash space.  ...  Some cross-modal hashing methods are only binary versions of traditional cross-modal retrieval approaches [9, 10] .  ... 
doi:10.1016/j.sigpro.2015.10.010 fatcat:2lkzoss4jrdhlgodxfi743gnzi

Unsupervised multi-graph cross-modal hashing for large-scale multimedia retrieval

Liang Xie, Lei Zhu, Guoqi Chen
2016 Multimedia tools and applications  
As a result, more precise cross-modal relationship can be preserved in the hash space. Then Nyström approximation approach is leveraged to efficiently construct the graphs.  ...  MGCMH is unsupervised method which integrates multi-graph learning and hash function learning into a joint framework, to learn unified hash space for all modalities.  ...  We have confirmed that graph approach is effective in cross-modal hashing.  ... 
doi:10.1007/s11042-016-3432-0 fatcat:hn5pwu2l35bqtkjru52c7wfh5i

Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval

Devraj Mandal, Kunal N. Chaudhury, Soma Biswas
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The approach first learns the optimum hash codes for the two modalities simultaneously, so as to preserve the semantic similarity between the data points, and then learns the hash functions to map from  ...  Most of the existing approaches have been developed for the case where there is one-to-one correspondence between the data of the two modalities.  ...  Acknowledgements The authors would like to thank Mr. Viresh Ranjan (Stony Brook University) for useful discussions during the progress of this work.  ... 
doi:10.1109/cvpr.2017.282 dblp:conf/cvpr/MandalCB17 fatcat:sdzvy565gjfi5pjgnyfcwhi2j4

Cross-Media Hashing with Neural Networks

Yueting Zhuang, Zhou Yu, Wei Wang, Fei Wu, Siliang Tang, Jian Shao
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
Inspired by recent advances in deep learning, we propose a cross-media hashing approach based on multi-modal neural networks.  ...  Cross-media hashing, which conducts cross-media retrieval by embedding data from different modalities into a common low-dimensional hamming space, has attracted intensive attention in recent years.  ...  Most of the existing cross-media hashing approaches exploit the symbiosis of multi-modal data when learning hash functions.  ... 
doi:10.1145/2647868.2655059 dblp:conf/mm/ZhuangYWWTS14 fatcat:lj7kidnxyjf4zjlnegwxw3nhoq

Unsupervised Deep Cross-modality Spectral Hashing [article]

Tuan Hoang and Thanh-Toan Do and Tam V. Nguyen and Ngai-Man Cheung
2020 arXiv   pre-print
The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning.  ...  This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval.  ...  The second step of the two-step hashing approach is to learn hash functions to map inputs to the learned binary codes in the first step.  ... 
arXiv:2008.00223v3 fatcat:i2xbdck5gncinhai362j2xnmpu

Deep Multi-Semantic Fusion-Based Cross-Modal Hashing

Xinghui Zhu, Liewu Cai, Zhuoyang Zou, Lei Zhu
2022 Mathematics  
To this end, this paper proposes deep multi-semantic fusion-based cross-modal hashing (DMSFH), which uses two deep neural networks to extract cross-modal features, and uses a multi-label semantic fusion  ...  Due to the low costs of its storage and search, the cross-modal retrieval hashing method has received much research interest in the big data era.  ...  Related Work According to learning manner, the existing cross-modal hashing techniques fall into two categories: unsupervised approaches and supervised approaches.  ... 
doi:10.3390/math10030430 fatcat:yri6dbd53zglhc77wtpswxgsoa

SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network [article]

Jian Zhang, Yuxin Peng, Mingkuan Yuan
2018 arXiv   pre-print
To address these problems, in this paper we propose a novel Semi-supervised Cross-Modal Hashing approach by Generative Adversarial Network (SCH-GAN).  ...  Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities.  ...  Those two models act as two players to play a minimax game to optimize each other, and promote cross-modal hashing performance.  ... 
arXiv:1802.02488v1 fatcat:3zxx64d7eza6xk6gt4rkmyb4vq

Fusion-supervised Deep Cross-modal Hashing [article]

Li Wang, Lei Zhu, En Yu, Jiande Sun, Huaxiang Zhang
2020 arXiv   pre-print
In this paper, we propose a novel Fusion-supervised Deep Cross-modal Hashing (FDCH) approach.  ...  Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages.  ...  CONCLUSION In this paper, we propose a novel Fusion-supervised Deep Cross-modal Hashing (FDCH) approach.  ... 
arXiv:1904.11171v2 fatcat:u7jcf2h2fzajvcyyo4y5akar3i

Discriminative coupled dictionary hashing for fast cross-media retrieval

Zhou Yu, Fei Wu, Yi Yang, Qi Tian, Jiebo Luo, Yueting Zhuang
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
The existing cross-media hashing approaches only aim at learning hash functions to preserve the intra-modality and inter-modality correlations, but do not directly capture the underlying semantic information  ...  To perform fast cross-media retrieval, we learn hash functions which map data from the dictionary space to a low-dimensional Hamming space.  ...  That is to say, all the cross-media hashing approaches can be adapted to uni-modal hashing.  ... 
doi:10.1145/2600428.2609563 dblp:conf/sigir/YuWYTLZ14 fatcat:igpcpkocsrggvmldkcboj2ofly

SDMCH: Supervised Discrete Manifold-Embedded Cross-Modal Hashing

Xin Luo, Xiao-Ya Yin, Liqiang Nie, Xuemeng Song, Yongxin Wang, Xin-Shun Xu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
To address these issues, in this paper, we present a novel cross-modal hashing method, named Supervised Discrete Manifold-Embedded Cross-Modal Hashing (SDMCH).  ...  Cross-modal hashing methods have attracted considerable attention. Most pioneer approaches only preserve the neighborhood relationship by constructing the correlations among heterogeneous modalities.  ...  Two-Step Hashing Two-step hashing [Lin et al., 2013; Luo et al., 2018] decomposes the hash learning problem into two steps: 1) The binary code inference step; 2) the hash function learning step.  ... 
doi:10.24963/ijcai.2018/349 dblp:conf/ijcai/LuoYNSWX18 fatcat:v6embsbtu5akrp4ncn2tfezkkq

Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval [article]

Lu Wang, Jie Yang
2020 arXiv   pre-print
Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across  ...  To address above challenges, in this paper, a novel Asymmetric Correlation Quantization Hashing (ACQH) method is proposed.  ...  For example, two-step hashing [15] , [16] , [17] decomposes the hashing learning process into two steps: a compact binary code production step and a hash functions constructing step based on the learnt  ... 
arXiv:2001.04625v1 fatcat:jfp4jl3i25fsraiuqa5msdu24m
« Previous Showing results 1 — 15 out of 3,989 results