995 Hits in 3.9 sec

Co-Regularized Hashing for Multimodal Data

Yi Zhen, Dit-Yan Yeung
2012 Neural Information Processing Systems  
We propose a novel multimodal hash function learning method, called Co-Regularized Hashing (CRH), based on a boosted coregularization framework.  ...  In this paper, we study hash function learning in the context of multimodal data.  ...  In this paper, we propose a novel multimodal HFL method, called Co-Regularized Hashing (CRH), based on a boosted co-regularization framework.  ... 
dblp:conf/nips/ZhenY12 fatcat:wnncvfz3bnghxfnden43dcihoa

A Comprehensive Survey on Cross-modal Retrieval [article]

Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, Liang Wang
2016 arXiv   pre-print
In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of multimodal data. It takes one type of data as the query to retrieve relevant data of another type.  ...  Real-valued representation learning methods aim to learn real-valued common representations for different modalities of data.  ...  [69] propose a novel multimodal hash function learning method, called Co-Regularized Hashing (CRH), based on a boosted co-regularization framework.  ... 
arXiv:1607.06215v1 fatcat:jfbmmlvzrvcmtmzezogzuxvvqu

A Probabilistic Framework for Multimodal Retrieval using Integrative Indian Buffet Process

Bahadir Ozdemir, Larry S. Davis
2014 Neural Information Processing Systems  
The procedure consists of a Bayesian nonparametric framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal  ...  Experiments on two multimodal datasets, PASCAL-Sentence and SUN-Attribute, demonstrate the effectiveness of the proposed retrieval procedure in comparison to the state-of-the-art algorithms for learning  ...  Zhen and Yeung described two recent methods: Co-regularized hashing [11] based on a boosted co-regularization framework and a probabilistic generative approach called multimodal latent binary embedding  ... 
dblp:conf/nips/OzdemirD14 fatcat:z7fretvxlzehxguagghvddaogm

A Review of Hashing Methods for Multimodal Retrieval

Wenming Cao, Wenshuo Feng, Qiubin Lin, Guitao Cao, Zhihai He
2020 IEEE Access  
Among many retrieval methods, the hashing method is widely used in multimodal data retrieval due to its low storage cost, fast and effective characteristics.  ...  With the advent of the information age, the amount of multimedia data has exploded. That makes fast and efficient retrieval in multimodal data become an urgent requirement.  ...  CMSSH does not consider the similarity within the data modalities. Co-Regularized Hashing (CRH) has improved the CMSSH and added a loss function within the modalities.  ... 
doi:10.1109/access.2020.2968154 fatcat:e3vmte5hrnhu3b3lf5ws4gwnhm

Iterative Multi-View Hashing for Cross Media Indexing

Yao Hu, Zhongming Jin, Hongyi Ren, Deng Cai, Xiaofei He
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
To make such systems practically possible for large mount of multimedia data, two critical issues must be carefully considered: (a) reduce the storage as much as possible; (b) model the relationship of  ...  the heterogeneous media data.  ...  the joint preservation of between-view correlations based on a co-regularized boosting framework. • CVH algorithm [15] , which extends traditional spectral hashing in single view to the multi-view case  ... 
doi:10.1145/2647868.2654906 dblp:conf/mm/HuJRCH14 fatcat:y4qy7twlsfdgbaasf6dptskv4m

Multimodal Biometric Template Protection Based on a Cancelable SoftmaxOut Fusion Network

Jihyeon KIM, Yoon Gyo Jung, Andrew Beng Jin Teoh
2022 Applied Sciences  
The first module carries out feature extraction and fusion, while the second and third are responsible for the hashing of fused features and compression.  ...  By end-to-end, we mean a model that receives raw biometric data as input and produces a protected template as output.  ...  Unlike RPMoT, which is data-agnostic, PSMoT is data-driven.  ... 
doi:10.3390/app12042023 fatcat:ybtm3fqsc5e5tbmgazu5zvu75i

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

Zechao Li, Lu Jin, Jinhui Tang
2019 arXiv   pre-print
In this work, we propose a novel Deep Semantic Multimodal Hashing Network for scalable multimodal retrieval.  ...  Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage.  ...  Cross-View Hashing (CVH) [39] , Co-Regularized Hashing [40] and Inter-Media Hashing (IMH) [41] utilize unlabeled training data to generate binary hash codes.  ... 
arXiv:1901.02662v2 fatcat:r6o3pql7nrhxbnr62ytoxojn24

Deep Multi-level Semantic Hashing for Cross-modal Retrieval

Zhenyan Ji, Weina Yao, Wei Wei, Houbing Song, Huaiyu Pi
2019 IEEE Access  
With the rapid growth of multimodal data, the cross-modal search has widely attracted research interests.  ...  And a deep hashing framework is designed for multi-label image-text cross retrieval tasks.  ...  A common point of these methods is that they all use shallow architectures for multimodal embedding. That is not efficient in capturing features of data in different types.  ... 
doi:10.1109/access.2019.2899536 fatcat:xynopqlgyfhe3ef6su55zqczim

Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization

Dongqing Zhang, Wu-Jun Li
In particular, more and more attentions have been payed to multimodal hashing for search in multimedia data with multiple modalities, such as images with tags.  ...  Due to its low storage cost and fast query speed, hashing has been widely adopted for similarity search in multimedia data.  ...  co-regularized hashing (CRH) (Zhen and Yeung 2012a) .  ... 
doi:10.1609/aaai.v28i1.8995 fatcat:3iwq26o3wzglbexonclrq73q4i

Learning Discriminative Representations for Semantic Cross Media Retrieval [article]

Aiwen Jiang and Hanxi Li and Yi Li and Mingwen Wang
2015 arXiv   pre-print
As a result, an efficient linear semantic down mapping is jointly learned for multimodal data, leading to a common space where they can be compared.  ...  The proposed method, named as shared discriminative semantic representation learning (SDSRL), is tested on two public multimodal dataset for both within- and inter- modal retrieval.  ...  Multimodal hashing methods in this category includes Inter Media Hashing (IMH) [12] , Latent Semantic Sparse Hashing (LSSH) [13] , CMFH [14] , CSLP [15] , QCH [16] and Regularized CrossModal Hashing  ... 
arXiv:1511.05659v1 fatcat:tql2gfux5jbypkaoggly6jq75y

Collective Matrix Factorization Hashing for Multimodal Data

Guiguang Ding, Yuchen Guo, Jile Zhou
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we study the problems of learning hash functions in the context of multimodal data for cross-view similarity search.  ...  Nearest neighbor search methods based on hashing have attracted considerable attention for effective and efficient large-scale similarity search in computer vision and information retrieval community.  ...  Co-Regularized Hashing (CRH) [26] , whose objective function intends to project data far from 0 for good generalization, and at the same time, preserve the inter-modality similarity effectively.  ... 
doi:10.1109/cvpr.2014.267 dblp:conf/cvpr/DingGZ14 fatcat:wjjusjtlofc3pbucoy2c6yl6qq

Deep semantic cross modal hashing based on graph similarity of modal-specific

Junzheng Li
2021 IEEE Access  
Deep Semantic Multimodal Hashing Network for Scalable Multimedia Retrieval (DSMHN) [24] is a unified deep multimodal hashing framework, which learns compact and high-quality hash codes by exploiting  ...  Self-Supervised Deep Multimodal Hashing (SSDMH) [43] learns unified hash codes as well as deep hash functions for different modalities in a selfsupervised manner.  ... 
doi:10.1109/access.2021.3093357 fatcat:uyouxawgzbhzhlrsufj4iauiuy

Data Curation for Preclinical and Clinical Multimodal Imaging Studies

Grace Gyamfuah Yamoah, Liji Cao, Chao Wu Wu, Freek J. Beekman, Bert Vandeghinste, Julia G. Mannheim, Stefanie Rosenhain, Kevin Leonardic, Fabian Kiessling, Felix Gremse
2019 Molecular Imaging and Biology  
This work aimed at developing a free secure file format for multimodal imaging studies, supporting common in vivo imaging modalities up to five dimensions as a step towards establishing data curation standards  ...  However, while standards for data storage in the clinical medical imaging field exist, data curation standards for biomedical research are yet to be established.  ...  This transformation is used for co-registration of images obtained from two different modalities.  ... 
doi:10.1007/s11307-019-01339-0 pmid:30868426 fatcat:35awqgytazaz5fveddsvohvz3y

Unsupervised Cross-Media Hashing with Structure Preservation [article]

Xiangyu Wang, Alex Yong-Sang Chia
2016 arXiv   pre-print
The need for effective and accurate data retrieval from heterogeneous data sources has attracted much research interest in cross-media retrieval.  ...  These hash codes empower the similarity between data of different media types to be evaluated directly.  ...  Specifically, supervised methods such as Co-Regularized Hashing [23] and Semantic Correlation Maximization Hashing [22] require prior knowledge such as semantic labels of the features (i.e. class labels  ... 
arXiv:1603.05782v1 fatcat:2kdhbs3qcjfatost6nqydfsxtq

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  ...  data.  ...  Co-Regularized Hashing (CRH) [30] uses a boosted coregularized framework to learn a set of hash functions for each bit of the hash codes from one modality.  ... 
doi:10.1109/tip.2016.2564638 pmid:27168597 fatcat:ihinkjn3hraj7hljppsqci7pja
« Previous Showing results 1 — 15 out of 995 results