Filters








4,831 Hits in 3.4 sec

Scalable Multimedia Retrieval by Deep Learning Hashing with Relative Similarity Learning

Lianli Gao, Jingkuan Song, Fuhao Zou, Dongxiang Zhang, Jie Shao
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
In this paper, we propose a semi-supervised deep learning hashing (DLH) method for fast multimedia retrieval.  ...  Learning-based hashing methods are becoming the mainstream for approximate scalable multimedia retrieval.  ...  CONCLUSIONS In this paper, we propose a general framework for semi-supervised deep learning hashing (DLH) method for fast multimedia retrieval.  ... 
doi:10.1145/2733373.2806360 dblp:conf/mm/GaoSZZS15 fatcat:5zajocetcffl3jovhrzbrsy2vq

Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization [article]

Shifeng Zhang, Jianmin Li, Jinma Guo, Bo Zhang
2016 arXiv   pre-print
To address these issues, we propose a novel discrete supervised hash learning framework which can be scalable to large-scale datasets.  ...  Hashing method maps similar data to binary hashcodes with smaller hamming distance, and it has received a broad attention due to its low storage cost and fast retrieval speed.  ...  CONCLUSION In this paper, we propose a novel discrete supervised hashing framework for supervised hashing problem.  ... 
arXiv:1609.08740v1 fatcat:dpbs4eayefarxpqwjxkaxiiaf4

Towards Large-Scale Histopathological Image Analysis: Hashing-Based Image Retrieval

Xiaofan Zhang, Wei Liu, Murat Dundar, Sunil Badve, Shaoting Zhang
2015 IEEE Transactions on Medical Imaging  
We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues  ...  Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens  ...  Representative methods include, but are not limited to, weakly-supervised hashing in kernel space [45] , semi-supervised hashing [46] supervised hashing [24] , and compact kernel hashing with multiple  ... 
doi:10.1109/tmi.2014.2361481 pmid:25314696 fatcat:frt22wzviraffm7zjex5wgzlau

Deep learning of binary hash codes for fast image retrieval

Kevin Lin, Huei-Fang Yang, Jen-Hao Hsiao, Chu-Song Chen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Encouraged by the recent advances in convolutional neural networks (CNNs), we propose an effective deep learning framework to generate binary hash codes for fast image retrieval.  ...  Unlike other supervised methods that require pair-wised inputs for binary code learning, our method learns hash codes and image representations in a point-wised manner, making it suitable for large-scale  ...  [30] propose a supervised hashing approach to learn binary hashing codes for fast image retrieval through deep learning and demonstrate state-of-the-art retrieval performance on public datasets.  ... 
doi:10.1109/cvprw.2015.7301269 dblp:conf/cvpr/LinYHC15 fatcat:ldzjg37xlvg3tchpjfvvdpdhvm

Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization

Dongqing Zhang, Wu-Jun Li
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Due to its low storage cost and fast query speed, hashing has been widely adopted for similarity search in multimedia data.  ...  Hence, many supervised multimodal hashing~(SMH) methods have been proposed to utilize such semantic labels to further improve the search accuracy.  ...  Conclusion Most existing supervised multimodal hashing methods are not scalable.  ... 
doi:10.1609/aaai.v28i1.8995 fatcat:3iwq26o3wzglbexonclrq73q4i

Online Hashing for Scalable Remote Sensing Image Retrieval

Peng Li, Xiaoyu Zhang, Xiaobin Zhu, Peng Ren
2018 Remote Sensing  
Supervised hashing approaches, such as kernel-based supervised hashing [25], supervised discrete hashing [27] and deep hashing methods [29], incorporate the label information to learn semantic hashing  ...  Many new hashing algorithms have been developed and successfully applied to fast RS image retrieval tasks.  ...  To overcome the above problems, we propose a novel online hashing method for fast and scalable RS image retrieval in this paper.  ... 
doi:10.3390/rs10050709 fatcat:2dbb6rhsb5agha4ve5e6t7dmj4

An Efficient Image Indexing Method Based on Spectral Hashing with Semantically Consistent Sparcified Graph Laplacian Approach
English

M.Preme sudha, P Kavitha
2014 International Journal of Computer Trends and Technology  
Earlier work used Spectral hashing with pair wise similarity in the hash function learning process. This can be optimized by graph Laplacian.  ...  The learned graph with sparcification represents improved similarity between samples, is then applied to Spectral Hashing for generation of efficient binary codes.  ...  RELATED WORK In [9] Yadong Mu.et.al presented a novel hashing algorithm named LAMP, which produces high-quality hash functions with kernel conjuring and weak supervision.  ... 
doi:10.14445/22312803/ijctt-v15p106 fatcat:wfpnwzkr6jhffpu2dxjnfjg6ua

CRH: A simple benchmark approach to continuous hashing

Miao Cheng, Ah Chung Tsoi
2015 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)  
In this work, a continuous hashing method, termed continuous random hashing (CRH), is proposed to encode sequential data stream, while ignorance of previously hashing knowledge is possible.  ...  Experimental results demonstrate our method is able to provide outstanding performance, as a benchmark approach to continuous hashing.  ...  Most existing methods: Handling: Conduct encode and decode procedures separately . -> Easily scalable (Almost impractical X) Supervised information is required every once time.  ... 
doi:10.1109/globalsip.2015.7418363 dblp:conf/globalsip/ChengT15 fatcat:5xxrtee37rf75dczxubdgzg2oa

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Huei-Fang Yang, Kevin Lin, Chu-Song Chen
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper presents a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search.  ...  Moreover, SSDH performs joint learning of image representations, hash codes, and classification in a point-wised manner, and thus is scalable to large-scale datasets.  ...  optimization efficient and scalable.  ... 
doi:10.1109/tpami.2017.2666812 pmid:28207384 fatcat:5u3nhd73qndkpllfcxnjb6m5bi

2020 Index IEEE Transactions on Knowledge and Data Engineering Vol. 32

2021 IEEE Transactions on Knowledge and Data Engineering  
., +, TKDE Feb. 2020 288-301 Fast Discrete Collaborative Multi-Modal Hashing for Large-Scale Multimedia Retrieval.  ...  Tang, J., +, TKDE May 2020 855-867 Fast Discrete Collaborative Multi-Modal Hashing for Large-Scale Multimedia Retrieval.  ... 
doi:10.1109/tkde.2020.3038549 fatcat:75f5fmdrpjcwrasjylewyivtmu

Joint Kernel-Based Supervised Hashing for Scalable Histopathological Image Analysis [chapter]

Menglin Jiang, Shaoting Zhang, Junzhou Huang, Lin Yang, Dimitris N. Metaxas
2015 Lecture Notes in Computer Science  
The obtained hashing functions compress high-dimensional features into tens of binary bits, enabling fast retrieval from a large database.  ...  Recently, with the rapid growth of histopathological images, hashing-based retrieval approaches are gaining popularity due to their exceptional scalability.  ...  To overcome the above drawbacks, we employ joint kernel-based supervised hashing (JKSH) [6, 8, 9] to incorporate feature fusion into the supervised hashing framework, and apply it to scalable analysis  ... 
doi:10.1007/978-3-319-24574-4_44 fatcat:jjfua4knpba7tia7wimwmekznu

Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval [article]

Lei Zhu, Hui Cui, Zhiyong Cheng, Jingjing Li, Zheng Zhang
2020 arXiv   pre-print
Particularly, unsupervised deep hashing has well scalability as it does not require any manually labelled data for training.  ...  Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed and low storage cost.  ...  Compared with supervised hashing, it has more desirable scalability, because most images in real-world large-scale retrieval scenarios may have no or limited manually annotated labels.  ... 
arXiv:2006.05586v1 fatcat:whuawurklfbinl7fs6mg5kqw4q

Fast content-based image retrieval using convolutional neural network and hash function

Domonkos Varga, Tamas Sziranyi
2016 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)  
The main advantage of our novel hashing scheme that it is able to reduce the computational cost of retrieval significantly at the state-of-the-art efficiency level.  ...  The main contribution of our work is a novel endto-end supervised learning framework that learns probabilitybased semantic-level similarity and feature-level similarity simultaneously.  ...  An efficient end-to-end supervised learning framework is presented for fast image retrieval that learns probability-based semanticlevel similarity and feature-level similarity simultaneously.  ... 
doi:10.1109/smc.2016.7844637 dblp:conf/smc/VargaS16 fatcat:vj5wgjkarzcxddfypouse3s6i4

SADIH: Semantic-Aware DIscrete Hashing

Zheng Zhang, Guo-sen Xie, Yang Li, Sheng Li, Zi Huang
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in largescale multimedia retrieval applications.  ...  Particularly, supervised hashing has recently received considerable research attention by leveraging the label information to preserve the pairwise similarities of data points in the Hamming space.  ...  To address the aforementioned problems, we propose a novel discriminative binary code learning framework, dubbed Semantic-Aware DIscrete Hashing (SADIH), for fast scalable supervised hashing.  ... 
doi:10.1609/aaai.v33i01.33015853 fatcat:6ypjbpi2nbcqbpf3anfpfmhts4

Discrete Binary Coding based Label Distribution Learning

Ke Wang, Xin Geng
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In addition, a fast approximate nearest neighbor (ANN) search strategy is utilized to predict label distributions for testing instances.  ...  discrete graph hashing (ADGH) [Shi et al., 2017] , fast supervised discrete hashing (FSDH) [Gui et al., 2018] , fast scalable supervised hashing (FSSH) [Luo et al., 2018a] , scalable supervised discrete  ...  Representative supervised discrete hashing methods include supervised discrete hashing (SDH) [Shen et al., 2015] , column sampling based discrete supervised hashing (COSDISH) [Kang et al., 2016] , asymmetric  ... 
doi:10.24963/ijcai.2019/518 dblp:conf/ijcai/WangG19a fatcat:rztfxb2odvctfooludvlqfdxa4
« Previous Showing results 1 — 15 out of 4,831 results