573 Hits in 5.1 sec

MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval

Donglin Zhang, Xiao-Jun Wu, He-Feng Yin, Josef Kittler
2021 Pattern Recognition Letters  
To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval.  ...  Besides, to enhance the underlying discrimination, we combine the clues from the multimodal data, semantic labels and learned hash codes for hash learning.  ...  Scalable matrix factorization hashing (SCARATCH) (Li et al., 2018b) , which learns a latent semantic subspace by adopting a matrix factorization scheme and generates hash codes discretely.  ... 
doi:10.1016/j.patrec.2021.07.018 fatcat:rtoisvhcxnav3jgbnk6alwqk5m

Table of contents

2020 IEEE Transactions on Cybernetics  
Zheng 4146 Bidirectional Discrete Matrix Factorization Hashing for Image Search . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Shen 4157 Optimal Filtered and Smoothed Estimators for Discrete-Time Linear Systems with Multiple Packet Dropouts Under Markovian Communication Constraints . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tcyb.2020.3016105 fatcat:uygvkuec2nfupdstm2dttiryqa

Baby-Step Giant-Step Algorithms for the Symmetric Group [article]

Eric Bach, Bryce Sandlund
2016 arXiv   pre-print
In this paper, we study the case where G = S_n, and develop analogs to the Shanks baby-step / giant-step procedure for ordinary discrete logarithms.  ...  We also analyze randomized "collision" algorithms for the same problem.  ...  Finally, we thank the anonymous reviewers for their constructive feedback during the review process.  ... 
arXiv:1612.03456v1 fatcat:a3r6u5vblzgmhaznqirxhynrui

Local Feature Hashing with Binary Autoencoder for Face Recognition

Jing Chen, Yunxiao Zu
2020 IEEE Access  
It attempts to exploit structure factors to well reconstruct the face image from binary codes.  ...  Lastly, we cluster and pool the obtained binary codes, and construct a histogram feature as the final face representation for each image.  ...  [29] present a bidirectional discrete matrix factorization hashing (BDMFH) model to force the hashing codes to inherit the latent structure of the raw data.  ... 
doi:10.1109/access.2020.2973472 fatcat:ip2ui5lmbbavnn7hetwwsdp4mi

Reflectance hashing for material recognition

Hang Zhang, Kristin Dana, Ko Nishino
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We demonstrate the effectiveness of reflectance hashing for material recognition with a number of realworld materials.  ...  We introduce a framework called reflectance hashing that models the reflectance disks with dictionary learning and binary hashing.  ...  Acknowledgement The authors would like to thank Felix Yu from lab of Shih-Fu Chang, Columbia University and Sanjiv Kumar from Google Research for supplying binary embedding codes.  ... 
doi:10.1109/cvpr.2015.7298926 dblp:conf/cvpr/ZhangDN15 fatcat:vxtotslyqzblvo6njlga4zafea

Reflectance Hashing for Material Recognition [article]

Hang Zhang, Kristin Dana, Ko Nishino
2015 arXiv   pre-print
We demonstrate the effectiveness of reflectance hashing for material recognition with a number of real-world materials.  ...  We introduce a framework called reflectance hashing that models the reflectance disks with dictionary learning and binary hashing.  ...  The goal of efficient recognition of images for large scale search has led to numerous methods for binary hash codes [16, 2, 41, 24, 25] .  ... 
arXiv:1502.02092v1 fatcat:mhdojjw5ujd7rmwsgv446ibc4i

Semi-supervised learning for scalable and robust visual search

Jun Wang
2011 ACM SIGMultimedia Records  
for the bivariate optimization procedure; c) novel applications of the proposed techniques, such as interactive image retrieval, automatic re-ranking for text based image search, and a brain computer  ...  interface (BCI) for image retrieval. 2.  ...  hash codes for searching large-scale image and video databases.  ... 
doi:10.1145/2069210.2069213 fatcat:hblb5ncrprcrlgi6ugph6naucy

A Fast Searching Algorithm of Symmetrical Period Modulation Pattern Based on Accumulative Transformation Technique [chapter]

FuHua Fan, Ying Tan
2005 Lecture Notes in Computer Science  
S -Matrix theory: Scattering matrix and its properties, Scattering matrix of transmission lines, Scattering matrix representation of multi port network. 2.  ...  , security of hash functions and MAC's.  ...  Subject Code : R 50854 BIOMEDICAL SIGNAL PROCESSING UNIT-I Discrete and continuous Random variables, Probability distribution and density functions.  ... 
doi:10.1007/11539117_71 fatcat:7rghuykmvrhkdnl4fblp2zi3fu

Minimal residual ordinal loss hashing with an adaptive optimization mechanism

Zhen Wang, Fuzhen Sun, Longbo Zhang, Pingping Liu
2020 EURASIP Journal on Image and Video Processing  
Traditional hashing algorithms treat binary bits equally, which usually causes an ambiguous ranking.  ...  To solve this issue, we propose an innovative bitwise weight method dubbed minimal residual ordinal loss hashing (MROLH).  ...  Acknowledgements The authors would like to thank the editor and anonymous reviewers for their helpful comments and valuable suggestions. 1  ... 
doi:10.1186/s13640-020-00497-4 fatcat:w2bbtzk2pjhyxgkf7hlix4zmuq

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 7845-7860 Binary codes Deep Collaborative Multi-View Hashing for Large-Scale Image Search.  ...  Zhao, Z., +, TIP 2020 6069-6081 Cryptography Deep Collaborative Multi-View Hashing for Large-Scale Image Search.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Discrete Semantics-Guided Asymmetric Hashing for Large-Scale Multimedia Retrieval

Jun Long, Longzhi Sun, Liujie Hua, Zhan Yang
2021 Applied Sciences  
of matrix to solve the problem of the inevitable noise and subjective factors in labels.  ...  Cross-modal hashing technology is a key technology for real-time retrieval of large-scale multimedia data in real-world applications.  ...  Scalable Discrete Matrix Factorization Hashing (SCRATCH) [38] is a two-step hashing method, which first generates the hash codes, and then learns the hash functions based on the learned hash codes.  ... 
doi:10.3390/app11188769 fatcat:cp2bnipljjcevm4e26lfzvijsy

Measurement of Text Similarity: A Survey

Jiapeng Wang, Yihong Dong
2020 Information  
With the aim of providing reference for related research and application, the text similarity measurement method is described by two aspects: text distance and text representation.  ...  Matrix Factorization Methods Matrix factorization methods for generating low-dimensional word representations have roots stretching as far back as LSA (latent semantic analysis).  ...  After that, the model regards the matching problem as an image recognition problem on this twodimensional matching matrix.  ... 
doi:10.3390/info11090421 fatcat:wmixtnd7fjfw5nnx6u3vpdktji

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., Reference Trajectory Reshaping Optimi-zation and Control of Robotic Exoskeletons for Human-Robot Co-Manipulation; TCYB Aug. 2020 3740-3751 Wu, X., Jiang, B., Yu, K., Miao, c., and Chen, H  ...  ., +, TCYB Oct. 2020 4530-4543 Bidirectional Discrete Matrix Factorization Hashing for Image Search.  ...  Shen, Y., +, TCYB Nov. 2020 4722-4734 Bidirectional Discrete Matrix Factorization Hashing for Image Search.  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Multi-modal Deep Analysis for Multimedia

Wenwu Zhu, Xin Wang, Hongzhi Li
2019 IEEE transactions on circuits and systems for video technology (Print)  
Multi-modal data consist of a mixture of various types of data from different modalities such as texts, images, videos, audios etc.  ...  specifically, on data-driven correlational representation, we highlight three important categories of methods, such as multi-modal deep representation, multi-modal transfer learning, and multi-modal hashing  ...  ACKNOWLEDGMENT We thank Guohao Li, Shengze Yu and Yitian Yuan for providing relevant materials and valuable opinions. This work will never be accomplished without their useful suggestions.  ... 
doi:10.1109/tcsvt.2019.2940647 fatcat:l4tchrkgrnaeradvc4nhfan2w4

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation [article]

Sunwoo Kim, Haici Yang, Minje Kim
2020 arXiv   pre-print
Our proposed learning algorithm differs from AdaBoost in the sense that the projections are trained to minimize the distances between the self-similarity matrix of the hash codes and that of the original  ...  We use the learned hash codes for single-channel speech denoising tasks as an alternative to a complex machine learning model, particularly to address the resource-constrained environments.  ...  of the original self-similarity matrix with shorter hash strings.  ... 
arXiv:2002.06239v1 fatcat:6uj2e72vdfhubdvu3qoolldyna
« Previous Showing results 1 — 15 out of 573 results