Filters








2,903 Hits in 3.2 sec

Coupled Manifold Learning for Retrieval Across Modalities

Anees Kazi, Sailesh Conjeti, Amin Katouzian, Nassir Navab
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
doi:10.1109/iccvw.2017.157 dblp:conf/iccvw/KaziCKN17 fatcat:bdhqyk6eszck5ecf3yecxe6snq

Cross-Modal Manifold Learning for Cross-modal Retrieval [article]

Sailesh Conjeti, Anees Kazi, Nassir Navab, Amin Katouzian
2016 arXiv   pre-print
This paper presents a new scalable algorithm for cross-modal similarity preserving retrieval in a learnt manifold space.  ...  complementary information shall be aggregated and interpreted across modalities to form the final decision.  ...  Cross-modal Correlation > 0.1 Manifold alignment preserving global geometry (MA-F and MA-I) [8] F and I FC Eigen-value threshold > 10E − 05; k for OSE = 20 Learning coupled feature spaces (LCFS) [7] F  ... 
arXiv:1612.06098v1 fatcat:itleeic7qzenpn6m4diwgxswkq

Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold

Yan Li, Ruiping Wang, Zhiwu Huang, Shiguang Shan, Xilin Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
, and then iteratively optimize the intra-and inter-space Hamming distances in a maxmargin framework to learn the hash functions for the two spaces.  ...  Retrieving videos of a specific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspect searching.  ...  Extensive experiments on face video retrieval demonstrated the superiority of our method over the state-of-the-art single modality and multiple modalities hash learning methods.  ... 
doi:10.1109/cvpr.2015.7299108 dblp:conf/cvpr/LiWHSC15 fatcat:dmqi7lgqzvdz7pzcaxfcgtirti

Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics [article]

Donghuo Zeng, Yi Yu, Keizo Oyama
2020 arXiv   pre-print
The generative (G) model learns the correlation of two couples of transferred pairs to generate new audio-sheet pair for a fixed lyrics to challenge the discriminative (D) model.  ...  In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared across three major musical modalities: sheet  ...  We expect that our model can surpass CCA model in each couple of cross-modal retrieval in the future.  ... 
arXiv:2007.14856v1 fatcat:vnuhvabyvngj7diypj4lsqupju

MULTI-MODAL RETRIEVAL IN NEWS FEED APP USING GCDL TECHNIQUE

2017 International Journal of Recent Trends in Engineering and Research  
Existing methods proposed to use Canonical Correlation Analysis (CCA), manifolds learning, dual-wing harmoniums, deep autoencoder, and deep Boltzmann machine to approach the task.  ...  Since each modality having different representation methods and correlational structures, a variety of methods studied the problem from the aspect of learning correlations between different modalities.  ...  .  Cross-view Hashing maps similar objects to similar codes across the views to enable cross-view similarity search.  Discriminative coupled dictionary hashing generates a coupled dictionary for each  ... 
doi:10.23883/ijrter.2017.3365.aeikk fatcat:6dmfmfsmtbaejale6t63ts7may

Ranking on Cross-Domain Manifold for Sketch-Based 3D Model Retrieval

Takahiko Furuya, Ryutarou Ohbuchi
2013 2013 International Conference on Cyberworlds  
Sketch-based 3D model retrieval algorithms compare a query, a line drawing sketch, and 3D models for similarity by rendering the 3D models into line drawing-like images.  ...  Then, the two feature manifolds are interrelated to form a unified Cross-Domain Manifold (CDM) by using both feature similarity and semantic label correspondence across the domains.  ...  Querying modality is an issue central to 3D model retrieval. Query-by-3D model has been the most popular modality so far, but a user often does not have a 3D model to be used as a query.  ... 
doi:10.1109/cw.2013.60 dblp:conf/cw/FuruyaO13 fatcat:ubho53um2rg47kxo7nal5gea3e

Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval

Chao Li, Cheng Deng, Lei Wang, De Xie, Xianglong Liu
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing networks (UCH), for cross-modal retrieval, where outer-cycle network is used to learn powerful common representation  ...  Benefiting from deep leaning, continuously compelling results in cross-modal retrieval community have been achieved.  ...  In this paper, we propose a novel unsupervised coupled cycle generative adversarial hashing network called UCH, for cross-modal retrieval.  ... 
doi:10.1609/aaai.v33i01.3301176 fatcat:e3lcl673orauxflr5vs7wu2eoi

Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval [article]

Chao Li, Cheng Deng, Lei Wang, De Xie, Xianglong Liu
2019 arXiv   pre-print
In this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing networks (UCH), for cross-modal retrieval, where outer-cycle network is used to learn powerful common representation  ...  Benefiting from deep leaning, continuously compelling results in cross-modal retrieval community have been achieved.  ...  In this paper, we propose a novel unsupervised coupled cycle generative adversarial hashing network called UCH, for cross-modal retrieval.  ... 
arXiv:1903.02149v1 fatcat:lcsq6enrmrgqrfcwtwlqwr6iba

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  
We propose a discriminative coupled dictionary hashing (DCDH) method in this paper. In DCDH, the coupled dictionary for each modality is learned with side information (e.g., categories).  ...  To perform fast cross-media retrieval, we learn hash functions which map data from the dictionary space to a low-dimensional Hamming space.  ...  end for 12: end for Unified Hash Function Learning As the coupled dictionary for each modality is learned, the data from each modality can be encoded as sparse codes using its corresponding learned dictionary  ... 
doi:10.1145/2600428.2609563 dblp:conf/sigir/YuWYTLZ14 fatcat:igpcpkocsrggvmldkcboj2ofly

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

Fengling Li, Tong Wang, Lei Zhu, Zheng Zhang, Xinhua Wang
2022 arXiv   pre-print
However, existing researches equally handle the different tasks of cross-modal retrieval, and simply learn the same couple of hash functions in a symmetric way for them.  ...  It can learn task-adaptive hash functions for two sub-retrieval tasks via simultaneous modality representation and asymmetric hash learning.  ...  learn the same couple of hash functions for them.  ... 
arXiv:2004.00197v2 fatcat:osykjo375jdy5hkpo6kbhxnbsq

Multimodal Similarity-Preserving Hashing

Jonathan Masci, Michael M. Bronstein, Alexander M. Bronstein, Jurgen Schmidhuber
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra-and inter-modality similarity learning.  ...  We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable.  ...  Furthermore, it accounts only for the similarity across modalities, completely ignoring the data similarity within each modality.  ... 
doi:10.1109/tpami.2013.225 pmid:26353203 fatcat:biaqx2ztzjeyhi2n35ry7updra

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  Considering the underlying manifold structure across multi-modal data, Zhang et al.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Multimodal kernel learning for image retrieval

Yen-Yu Lin, Chiou-Shann Fuh
2010 2010 International Conference on System Science and Engineering  
each modality; 3) The adopted optimization criterion in boosting is to align with a target kernel matrix accounting for relevance feedback, and the learned multimodal kernel matrix can be used for training  ...  We propose a semi-supervised learning technique to address the problem of fusing multimodal information sources for CBIR.  ...  Another recent trend of designing semi-supervised algorithms for retrieval is based on manifold learning [9] , [10] , [15] .  ... 
doi:10.1109/icsse.2010.5551790 fatcat:mxoes5xy75fulnt6mh77dqgus4

Multimodal similarity-preserving hashing [article]

Jonathan Masci and Michael M. Bronstein and Alexander A. Bronstein and Jürgen Schmidhuber
2012 arXiv   pre-print
The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning.  ...  We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable.  ...  Two pairs of nets, one for modality X and one for modality Y are coupled together by a cross-modal loss. The system learns two set of parameters. et al. (2010) .  ... 
arXiv:1207.1522v1 fatcat:6kd7jaaoqvgwhabrkqdqawsnnq

Methodologies for Cross-Domain Data Fusion: An Overview

Yu Zheng
2015 IEEE Transactions on Big Data  
This calls for advanced techniques that can fuse the knowledge from various datasets organically in a machine learning and data mining task.  ...  These datasets consist of multiple modalities, each of which has a different representation, distribution, scale, and density.  ...  As a result, fusing data across modalities becomes a new challenge in big data research, calling for advanced data fusion technology.  ... 
doi:10.1109/tbdata.2015.2465959 fatcat:flm37ozmhzcrfbrzeuagxm4l6a
« Previous Showing results 1 — 15 out of 2,903 results