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
Deep Kernel Supervised Hashing for Node Classification in Structural Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
To address the above problems, in this paper, we propose a novel Deep Kernel Supervised Hashing (DKSH) method to learn the hashing representations of nodes for node classification. ...
Node classification in structural networks has been proven to be useful in many real world applications. ...
Conclusions In this paper, we propose a novel Deep Kernel Supervised Hashing (DKSH) method to learn the hashing representations of nodes for node classification in structural networks. ...
arXiv:2010.13582v2
fatcat:af5jeidhufannao6h2d5v7cibq
ForestHash: Semantic Hashing with Shallow Random Forests and Tiny Convolutional Networks
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests. ...
We propose to first randomly group arriving classes at each tree split node into two groups, obtaining a significantly simplified two-class classification problem that can be a handled with a light-weight ...
general deep networks, where Φ denotes the mapping from a deep network. ...
doi:10.1007/978-3-030-01216-8_27
fatcat:axo5i4mrmzb7znzuh3ma7isbmu
ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We start with a simple hashing scheme, where random trees in a forest act as hashing functions by setting '1' for the visited tree leaf, and '0' for the rest. ...
In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation ...
general deep networks, where Φ denotes the mapping from a deep network. ...
arXiv:1711.08364v2
fatcat:zqop3ofdpfflpjjijir6pd7d24
Deep Discriminative Supervised Hashing via Siamese Network
2017
IEICE transactions on information and systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this letter, we propose a novel deep discriminative supervised hashing method, called DDSH, which directly learns hash codes based on a new combined loss function. ...
The latest deep hashing methods perform hash codes learning and image feature learning simultaneously by using pairwise or triplet labels. ...
) [8] , latent factor hashing (LFH) [9] , supervised hashing with kernels (KSH) [10] , fast supervised hashing (FastH) [11] , etc. ...
doi:10.1587/transinf.2017edl8126
fatcat:7k4ljo4fbjdj3eafyhjybtdyna
Binarized attributed network embedding
2018
2018 IEEE International Conference on Data Mining (ICDM)
Preserved Fulltext
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.
To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. ...
nodes to a given target node in a layer-wise manner. ...
The process can be taken as using the random walk kernel (supervised by node attributes) on graphs for node representation. ...
doi:10.1109/icdm.2018.8626170
dblp:conf/icdm/YangP00LZ18
fatcat:m3f5vb4iqrbunc33bczk3wxl5u
Deep Hashing for Semi-supervised Content Based Image Retrieval
2018
KSII Transactions on Internet and Information Systems
Preserved Fulltext
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.
Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. ...
Proposed activation and loss functions helped to minimize classification error and produce better hash codes. ...
Due to real contributions of deep networks for feature extraction in image classification [7] , [10] , [13, p.] , [14] has proposed some deep hashing methods. ...
doi:10.3837/tiis.2018.08.013
fatcat:lessznvvsva65ip743jbfu425q
Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
2018
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2015 pre-print arXiv:1507.00101v1 fatcat:vkzfcvpvyffllhlfp35l24ewnaOther Versions
Based on this assumption, our approach, dubbed supervised semantics-preserving deep hashing (SSDH), constructs hash functions as a latent layer in a deep network and the binary codes are learned by minimizing ...
This paper presents a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search. ...
Supervised Learning of Semantics-Preserving Hashing via Deep Neural Networks for Large-Scale Image Search Huei-Fang Yang, Kevin Lin, Chu-Song Chen Abstract-This paper presents a supervised deep hashing ...
doi:10.1109/tpami.2017.2666812
pmid:28207384
fatcat:5u3nhd73qndkpllfcxnjb6m5bi
Deep hashing using an extreme learning machine with convolutional networks
2017
Communications in Information and Systems
Preserved Fulltext
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.
In this paper, we present a deep hashing approach for large scale image search. ...
In contrast to existing deep hashing approaches, our method leads to faster and more accurate feature learning. Meanwhile, it improves the generalization ability of deep hashing. ...
These deep hashing methods execute feature learning and hash function learning with deep neural networks, which can well learn the nonlinear manifold structure of data and have achieved better results ...
doi:10.4310/cis.2017.v17.n3.a1
fatcat:blika3iojrfflkgyu4xlnq4lca
Hashed Binary Search Sampling for Convolutional Network Training with Large Overhead Image Patches
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
A novel binary search tree sampling scheme is fused with a kernel based hashing procedure that maps image patches into hash-buckets using binary codes generated from image content. ...
In addition, much of the computational cycles for large scale machine learning are poorly spent crunching through noisy and redundant image patches. ...
The authors would like to thank Jeanette Weaver for her contribution on selecting testing sites and preparing testing images. ...
arXiv:1707.05685v1
fatcat:a2264v5cpjaptdktpomgqhteom
Feature Hashing for Network Representation Learning
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a novel algorithm called node2hash based on feature hashing for generating node embeddings. This approach follows the encoder-decoder framework. ...
The goal of network representation learning is to embed nodes so as to encode the proximity structures of a graph into a continuous low-dimensional feature space. ...
was supported by the National Key Research and Development Program of China (Grant no. 2017YF B0802200), the National Natural Science Foundation of China (Grant no. 61772393), and the National Program for ...
doi:10.24963/ijcai.2018/390
dblp:conf/ijcai/WangWG018
fatcat:fvnu43y5nnbsdbhkyj6immusfe
A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection
2019
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Similar to other domains (e.g., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU. ...
As a fundamental and important task in remote sensing, remote sensing image scene understanding (RSISU) has attracted tremendous research interest in recent years. ...
to form a better deep network structure. ...
doi:10.3390/app9102110
fatcat:oj3acgbmwnhzppxvvjbsn5cfzq
Blockchain Model of Sensitive Information Identification in Social Online Games
2021
Academic Journal of Computing & Information Science
Preserved Fulltext
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.
A real-time data mining framework for sensitive information on online games in the blockchain mode is proposed. ...
The results show that the accuracy of TextCNN is over 5% higher than that of Naive Bayes and CNN models for short text recognition in online game context, so TextCNN model can meet the requirements for ...
It is worth noting that deep learning in artificial intelligence is widely used in text classification for network sensitive information mining [14, 15] . ...
doi:10.25236/ajcis.2021.040415
fatcat:ghdux3wg4zcere33boqlfvyzem
A Survey on Big IoT Data Indexing: Potential Solutions, Recent Advancements, and Open Issues
2021
Future Internet
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The real-world applications of the existing indexing techniques in different areas, such as health, business, scientific experiments, and social networks, are presented. ...
The purpose of this paper is to examine and review existing indexing techniques for large-scale data. ...
We hope that this survey will be useful for researchers interested in indexing large IoT data. ...
doi:10.3390/fi14010019
fatcat:xnlzg7cs2fb3lgng65ha5ucf5m
Deep Center Supervised Hash for Fast Image Retrieval
2017
DEStech Transactions on Computer Science and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In particular, we have designed a CNN architecture in which a hash layer is added to encourage the input image to approximate discrete value (e.g. +1/-1). ...
Firstly, the deep implicit relationship of the training image is extracted by using the robust learning ability of the CNN, and enhance the distinguishing and expressive ability of the image hash feature ...
In this paper, we design a binary code learning framework by exploiting CNN structure, named Deep Center Supervised Hashing (DCSH). ...
doi:10.12783/dtcse/aiea2017/15012
fatcat:c7y4gkxrvjezxmgly5ltm62zvi
Incorporation Of Semantic Segmentation Information In Deep Hashing Techniques For Image Retrieval
2017
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, a novel approach to deep hashing is proposed, which incorporates local-level information, in the form of image semantic segmentation masks, during the hash code learning step. ...
The proposed framework makes use of pixel-level classification labels, i.e. following a point-wise supervised learning methodology. ...
For example, Deep Pairwise-Supervised Hashing (DPSH) [16] learns hash codes in a pairwise manner within an end-to-end framework [16] . ...
doi:10.5281/zenodo.1076432
fatcat:uwqt7o4udbh75lygtlfevt7f6a
« Previous
Showing results 1 — 15 out of 1,645 results