Filters








177 Hits in 2.7 sec

Learning to Hash With Optimized Anchor Embedding for Scalable Retrieval

Yuchen Guo, Guiguang Ding, Li Liu, Jungong Han, Ling Shao
2017 IEEE Transactions on Image Processing  
Sparse representation and image hashing are 1 powerful tools for data representation and image retrieval respec-2 tively.  ...  The combinations of these two tools for scalable image 3 retrieval, i.e., sparse hashing (SH) methods, have been proposed 4 in recent years and the preliminary results are promising.  ...  , we proposed a novel Sparse Hashing method, 640 namely SHODE, for scalable retrieval.  ... 
doi:10.1109/tip.2017.2652730 pmid:28092559 fatcat:fadjluci5fcuniqrmjpcnkw4kq

Guest Editors' Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis

Trevor Darrell, Christoph Lampert, Nicu Sebe, Ying Wu, Yan Yan
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
The paper "Hetero-manifold Regularisation for Crossmodal Hashing" by F. Zheng, Y. Tang, and L.  ...  The paper "Collaborative Index Embedding for Image Retrieval" by W. Zhou, H. Li, J. Sun, and Q.  ... 
doi:10.1109/tpami.2018.2804998 fatcat:urin3tvgy5f7ng5djfvlm4mop4

Guest editorial: web multimedia semantic inference using multi-cues

Yahong Han, Yi Yang, Xiaofang Zhou
2015 World wide web (Bussum)  
A multi-modal semantic graph is constructed to find the embedded manifold cross-media correlations. The proposed method shows good performance in cross-media retrieval for image-audio dataset.  ...  The correlations provide abundant context information for web multimedia semantic analysis.  ... 
doi:10.1007/s11280-015-0360-2 fatcat:vc4plge5qvg7hfmza3dffmawki

A Sparse Embedding and Least Variance Encoding Approach to Hashing

Xiaofeng Zhu, Lei Zhang, Zi Huang
2014 IEEE Transactions on Image Processing  
Index Terms-hashing, manifold learning, image retrieval, dictionary learning.  ...  This actually embeds each sample sparsely in the sample space. The sparse embedding vector is employed as the feature of each sample for hashing.  ...  Linear spectral Sparse embedding Least variance encoding Binarization Sparse embedding 0 0 0.28 0.11 0.61 0 (a) Joint learning of hash functions and binarization threshold (b) Retrieval  ... 
doi:10.1109/tip.2014.2332764 pmid:24968174 fatcat:gpmxmttdkve4xefdnvrhqnf42a

Unsupervised Multi-modal Hashing for Cross-modal retrieval [article]

Jun Yu, Xiao-Jun Wu
2020 arXiv   pre-print
In this paper, we propose a novel unsupervised hashing learning method to cope with this open problem to directly preserve the manifold structure by hashing.  ...  Besides, the '2;1-norm constraint is imposed on the projection matrices to learn the discriminative hash function for each modality.  ...  The sparse constraint is imposed on our model to learn discriminative hash functions for multimodal data.  ... 
arXiv:1904.00726v4 fatcat:6vupsinllvfh7ivzg2gozz7ffa

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).  ...  However, they neglect the fact that the high-dimensional data often exists on a low-dimensional manifold embedded in the ambient space and the relative proximity between the neighbors is also important  ...  Related Work Hashing with Manifold Learning Recent studies have demonstrated that it is beneficial for a retrieval model to exploit the non-linear manifold structure of multimedia data [Yang et al.,  ... 
doi:10.24963/ijcai.2018/349 dblp:conf/ijcai/LuoYNSWX18 fatcat:v6embsbtu5akrp4ncn2tfezkkq

Hashing with Non-Linear Manifold Learning

Yanzhen Liu, Xiao Bai, Cheng Yan, Jing Wang, Jun Zhou
2016 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)  
The amount of data is exploding with the development of Internet and multimedia technology. Rapid retrieval of mass data is becoming more and more important.  ...  In this paper, we propose to use Isometric Mapping for dimensional reduction and utilize iterative quantization to reduce quantization loss during hashing process.  ...  But for non-linear manifold such as Swiss Roll, further exploration is needed to catch the manifold structure in hash codes.  ... 
doi:10.1109/dicta.2016.7797046 dblp:conf/dicta/Liu0YWZ16 fatcat:ksvnur5ca5bd3p7ydhiidyeldy

The heterogeneous feature selection with structural sparsity for multimedia annotation and hashing: a survey

Fei Wu, Yahong Han, Xiang Liu, Jian Shao, Yueting Zhuang, Zhongfei Zhang
2012 International Journal of Multimedia Information Retrieval  
Furthermore, the effective utilization of intrinsic embedding structures in various features can boost the performance of multimedia retrieval. As a result, the appropriate This work was done when Z.  ...  This paper introduces many of the recent efforts in sparsitybased heterogenous feature selection, the representation of the intrinsic latent structure embedded in multimedia, and the related hashing index  ...  The feature selection and hashing of multimedia are the basis for image and video annotation and retrieval.  ... 
doi:10.1007/s13735-012-0001-9 fatcat:4ihorofn6zbg3mzqnifihgcydm

Graph PCA Hashing for Similarity Search

Xiaofeng Zhu, Xuelong Li, Shichao Zhang, Zongben Xu, Litao Yu, Can Wang
2017 IEEE transactions on multimedia  
Third, PCA is integrated with manifold learning to lean the hash functions using the probability representations of all representative data points.  ...  of the big dataset; second, using the landmarks to generate a probability representation for each data point.  ...  Both PCA and manifold based hashing methods achieve significant hashing performance, but are with inefficient retrieval speed, i.e., at least quadratic time complexity for the training stage.  ... 
doi:10.1109/tmm.2017.2703636 fatcat:ptlzaq75xjfcndtd6nmfcdb3ty

Hashing Cross-Modal Manifold for Scalable Sketch-Based 3D Model Retrieval

Takahiko Furuya, Ryutarou Ohbuchi
2014 2014 2nd International Conference on 3D Vision  
Experiments show that our proposed algorithm is more accurate and much faster than previous sketch-based 3D model retrieval algorithms. 3D shape retrieval; content-based multimedia retrieval; hashing;  ...  The embedding is performed by a combination of spectral embedding and hashing into compact binary codes.  ...  ACKNOWLEDGMENT This research is supported by JSPS Grant-in-Aid for Scientific Research on Innovative Areas #26120517 and JSPS Grants-in-Aid for Scientific Research (C) #26330133.  ... 
doi:10.1109/3dv.2014.72 dblp:conf/3dim/FuruyaO14 fatcat:xemh7wmb7fg5vj5askteke4zxm

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  ...  Index Terms-Cross-modal hashing, multimedia retrieval, collective matrix factorization, label consistency, local geometric consistency. Jun Tang is currently a Professor with the  ...  INTRODUCTION ITH the explosive growth of multimedia data, it is of particular interest to develop algorithms for scalable retrieval of similar visual content in large-scale datasets.  ... 
doi:10.1109/tip.2016.2564638 pmid:27168597 fatcat:ihinkjn3hraj7hljppsqci7pja

Zero-Shot Hashing via Transferring Supervised Knowledge [article]

Yang Yang, Weilun Chen, Yadan Luo, Fumin Shen, Jie Shao, Heng Tao Shen
2016 arXiv   pre-print
Hashing has shown its efficiency and effectiveness in facilitating large-scale multimedia applications.  ...  Extensive experiments conducted on various real-life datasets show the superior zero-shot image retrieval performance of ZSH as compared to several state-of-the-art hashing methods.  ...  INTRODUCTION Hashing [30] is a powerful indexing technique for enabling efficient retrieval on large-scale multimedia data, such as image [25, 24, 38] and video [1] .  ... 
arXiv:1606.05032v1 fatcat:prm5zg5hrveedaizb466hq5kqu

Maximum Variance Hashing via Column Generation

Lei Luo, Chao Zhang, Yongrui Qin, Chunyuan Zhang
2013 Mathematical Problems in Engineering  
With the explosive growth of the data volume in modern applications such as web search and multimedia retrieval, hashing is becoming increasingly important for efficient nearest neighbor (similar item)  ...  Recently, a number of data-dependent methods have been developed, reflecting the great potential of learning for hashing.  ...  Introduction Nearest neighbor search is a fundamental problem in many applications concerned with information retrieval, including content-based multimedia retrieval [1] [2] [3] , object and scene recognition  ... 
doi:10.1155/2013/379718 fatcat:ztdc6jjmfnbtjpy2ftrw3cprky

Learning Decorrelated Hashing Codes for Multimodal Retrieval [article]

Dayong Tian
2019 arXiv   pre-print
When the hashing code length becomes longer, the retrieval performance improvement becomes slower. In this paper, we propose a minimum correlation regularization (MCR) for multimodal hashing.  ...  Hashing is expected to be an efficient solution, since it represents data as binary codes. As the bit-wise XOR operations can be fast handled, the retrieval time is greatly reduced.  ...  INTRODUCTION Multimodal hashing which embeds data to binary codes is an efficient tool for retrieving heterogeneous but correlated multimedia data, such as image-text pairs in Facebook and video-tag pairs  ... 
arXiv:1803.00682v2 fatcat:rogmcujiu5hkhnkwgpqlepo2du

2020 Index IEEE Transactions on Multimedia Vol. 22

2020 IEEE transactions on multimedia  
., +, TMM Dec. 2020 3180-3195 Deep Manifold-to-Manifold Transforming Network for Skeleton-Based Action Recognition.  ...  ., +, TMM Aug. 2020 2061-2073 Efficient Supervised Discrete Multi-View Hashing for Large-Scale Multimedia Search.  ...  Image watermarking Blind Watermarking for 3-D Printed Objects by Locally Modifying Layer Thickness. 2780 -2791 Low-Light Image Enhancement With Semi-Decoupled Decomposition.  ... 
doi:10.1109/tmm.2020.3047236 fatcat:llha6qbaandfvkhrzpe5gek6mq
« Previous Showing results 1 — 15 out of 177 results