A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Self-supervised asymmetric deep hashing with margin-scalable constraint
[article]
2021
arXiv
pre-print
Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. ...
By further exploiting semantic dictionaries, a new margin-scalable constraint is employed for both precise similarity searching and robust hash code generation. ...
Program for Chongqing Overseas Returnees (CX2018075). ...
arXiv:2012.03820v3
fatcat:fscm4ggdyrct3o6kso53mmriou
Discrete Binary Coding based Label Distribution Learning
2019
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
However, the training time complexity of most existing LDL algorithms is too high, which makes them unapplicable to large-scale LDL. ...
Specifically, we design an efficiently discrete coding framework to learn binary codes for 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 ...
doi:10.24963/ijcai.2019/518
dblp:conf/ijcai/WangG19a
fatcat:rztfxb2odvctfooludvlqfdxa4
Exploring Consistent Preferences
2017
Proceedings of the 2017 ACM on Multimedia Conference - MM '17
In this paper, we propose a novel discrete hashing with pair-exemplar (DHPE) to support scalable and e cient large-scale CBVLS. ...
Motivated by the characteristic of landmark, we explore the consistent preferences of tourists on landmark as pair-exemplars for scalable discrete hashing learning. ...
Developing e ective indexing methods to facilitate large-scale content-based visual landmark search (CBVLS) [44] enjoys great importance in real practice. ...
doi:10.1145/3123266.3123301
dblp:conf/mm/ZhuHCSS17
fatcat:macfoja72naytapxfzcmn6rz64
An Efficient Image Indexing Method Based on Spectral Hashing with Semantically Consistent Sparcified Graph Laplacian Approach
English
2014
International Journal of Computer Trends and Technology
English
The ability of rapid similarity search in a large-scale dataset is of huge significance to several multimedia applications. ...
Semantic hashing (SH) is a challenging way to accelerate similarity search, which plans flexible binary codes for a huge number of images with the intention that semantically similar images are planned ...
Even if these hashing methods have exposed success in large-scale image search, there is a problem that is seldom developed. II. ...
doi:10.14445/22312803/ijctt-v15p106
fatcat:wfpnwzkr6jhffpu2dxjnfjg6ua
Efficient Discrete Supervised Hashing for Large-scale Cross-modal Retrieval
[article]
2019
arXiv
pre-print
Supervised cross-modal hashing has gained increasing research interest on large-scale retrieval task owning to its satisfactory performance and efficiency. ...
In this paper, to address above issues, we propose a supervised cross-modal hashing method based on matrix factorization dubbed Efficient Discrete Supervised Hashing (EDSH). ...
supervised cross-modal hashing method is proposed to preserve both of them in hash codes, which makes hash codes more discriminative. 2) To enable large-scale applications, we develop an efficient discrete ...
arXiv:1905.01304v1
fatcat:envxs5ylgvei3ifm4bec7lvqme
Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval
[article]
2019
arXiv
pre-print
Unsupervised hashing can desirably support scalable content-based image retrieval (SCBIR) for its appealing advantages of semantic label independence, memory and search efficiency. ...
To address the problem, in this paper, we propose a novel hashing approach, dubbed as Discrete Semantic Transfer Hashing (DSTH). ...
It validates the linear scalability of DSTH and demonstrates that it is suitable for large-scale datasets.
I. ...
arXiv:1904.11207v1
fatcat:j3myydxqkza5tntcaidmonzneq
Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
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. ...
approach that constructs binary hash codes from labeled data for large-scale image search. ...
doi:10.1109/tpami.2017.2666812
pmid:28207384
fatcat:5u3nhd73qndkpllfcxnjb6m5bi
Semantics-Reconstructing Hashing for Cross-Modal Retrieval
[chapter]
2020
Lecture Notes in Computer Science
As one of the typical techniques for cross-model searching, hashing methods project features with high dimension into short-length hash codes, thus effectively improving storage and retrieval efficiency ...
To tackle these problems, we propose a shallow supervised hash learning method -Semantics-reconstructing Cross-modal Hashing (SCH), which reconstructs semantic representation and learns the hash codes ...
Therefore, the overall training cost is O(n), scalable for large-scale datasets. ...
doi:10.1007/978-3-030-47436-2_24
fatcat:yohnp4ufzzc5ncc5ybceeu2ocq
SADIH: Semantic-Aware DIscrete Hashing
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Extensive experimental results on multiple large-scale datasets demonstrate that our SADIH can clearly outperform the state-of-the-art baselines with the additional benefit of lower computational costs ...
Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in largescale multimedia retrieval applications. ...
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
Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
[article]
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. ...
However, the existing limitations make the present algorithms difficult to deal with large-scale datasets: (1) discrete constraints are involved in the learning of the hash function; (2) pairwise or triplet ...
With the compact binary codes, we are able to compress data into very small storage space, and conduct efficient nearest neighbor search on large-scale datasets. ...
arXiv:1609.08740v1
fatcat:dpbs4eayefarxpqwjxkaxiiaf4
Scalable Multimedia Retrieval by Deep Learning Hashing with Relative Similarity Learning
2015
Proceedings of the 23rd ACM international conference on Multimedia - MM '15
Learning-based hashing methods are becoming the mainstream for approximate scalable multimedia retrieval. ...
Tremendous efforts have been devoted to designing novel methods for these two components, i.e., supervised and unsupervised methods for learning hash codes, and different models for inferring hashing functions ...
This motivates us to investigate how to find a more robust feature and an unified searching scheme for larger scale image retrieval. ...
doi:10.1145/2733373.2806360
dblp:conf/mm/GaoSZZS15
fatcat:5zajocetcffl3jovhrzbrsy2vq
A Survey on Big IoT Data Indexing: Potential Solutions, Recent Advancements, and Open Issues
2021
Future Internet
The purpose of this paper is to examine and review existing indexing techniques for large-scale data. ...
Open problems and research challenges, e.g., privacy and large-scale data mining, are also discussed. ...
Thus, several challenging areas of research can serve as a basis for possible future research directions for the indexing of large IoT data. ...
doi:10.3390/fi14010019
fatcat:xnlzg7cs2fb3lgng65ha5ucf5m
A survey on deep hashing for image retrieval
[article]
2020
arXiv
pre-print
Hashing has been widely used in approximate nearest search for large-scale database retrieval for its computation and storage efficiency. ...
In this survey, several deep supervised hashing methods for image retrieval are evaluated and I conclude three main different directions for deep supervised hashing methods. ...
As a result, we avoid the inconvenience of dealing with all pairs as a whole, thus my method can be scalable to large-scale datasets. ...
arXiv:2006.05627v1
fatcat:3366dvigizai7kohqq3mfikcke
Hadamard Coding for Supervised Discrete Hashing
2018
IEEE Transactions on Image Processing
Binary hashing is widely used for large-scale image retrieval as well as video and document searches, because the compact binary code representation is essential for data storage and reasonable for query ...
In this paper, we propose a learning-based supervised discrete hashing (SDH) method. ...
SUPERVISED DISCRETE HASHING (SDH) MODEL In this section, we introduce the supervised discrete hashing (SDH) model. ...
doi:10.1109/tip.2018.2855427
pmid:30010571
fatcat:k5mzrtixr5efdaqf24afxqusfm
AMVH: Asymmetric Multi-Valued hashing
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Most existing hashing methods resort to binary codes for similarity search, owing to the high efficiency of computation and storage. ...
To perform meaningful asymmetric similarity computation for efficient semantic search, these embeddings are jointly learnt by preserving the label-based similarity. ...
scalable to deal with large-scale datasets. ...
doi:10.1109/cvpr.2017.102
dblp:conf/cvpr/DaXDMXP17
fatcat:mwm4b6cm5bhufeboe74yafv32e
« Previous
Showing results 1 — 15 out of 2,010 results