Filters








5,639 Hits in 6.9 sec

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval [article]

Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Franca Debole, Fabrizio Falchi, Claudio Gennaro, Lucia Vadicamo, Claudio Vairo
2021 arXiv   pre-print
in a single text retrieval engine.  ...  In this paper, we describe in details VISIONE, a video search system that allows users to search for videos using textual keywords, occurrence of objects and their spatial relationships, occurrence of  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
arXiv:2008.02749v2 fatcat:whagjaayibhd5dwbz5gkos7kf4

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval

Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Franca Debole, Fabrizio Falchi, Claudio Gennaro, Lucia Vadicamo, Claudio Vairo
2021 Journal of Imaging  
is indexed in a single text retrieval engine.  ...  This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of  ...  Acknowledgments: We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
doi:10.3390/jimaging7050076 pmid:34460672 pmcid:PMC8321359 fatcat:gld5cjmiyvbcvfsw7eoolhhpgq

Content-based Image Retrieval using Tesseract OCR Engine and Levenshtein Algorithm

Charles Adjetey, Kofi Sarpong Adu-Manu
2021 International Journal of Advanced Computer Science and Applications  
The Tesseract OCR engine and Levenshtein Algorithm was integrated to perform the image search. The extracted text is compared to the text stored in the database.  ...  This paper provides a technique for obtaining full image document given that the user has some portions of the document under search.  ...  ACKNOWLEDGMENT The authors would like to thank colleagues who supported us in diverse ways to get this manuscript ready for publication.  ... 
doi:10.14569/ijacsa.2021.0120776 fatcat:et5s6emedvctjg77m3xi7rwd5q

YFCC100M HybridNet fc6 Deep Features for Content-Based Image Retrieval

Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro, Fausto Rabitti
2016 Proceedings of the 2016 ACM Workshop on Multimedia COMMONS - MMCommons '16  
This set of results is ground truth for evaluating Content-Based Image Retrieval (CBIR) systems that use approximate similarity search methods for efficient and scalable indexing.  ...  This paper presents a corpus of deep features extracted from the YFCC100M images considering the fc6 hidden layer activation of the HybridNet deep convolutional neural network.  ...  However, LuQ is simpler and use of standard text search engine (i.e., Lucene).  ... 
doi:10.1145/2983554.2983557 fatcat:ayqkkrvufbgmxoicy35iogneju

Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment [article]

Kan Wu, Guanbin Li, Haofeng Li, Jianjun Zhang, Yizhou Yu
2019 arXiv   pre-print
A novel deep convolutional neural network is designed for the inference of proposal objectness, the probability of a proposal containing optimally-located foreground object.  ...  In our work, the objectness is quantitatively measured in regard of completeness and fullness, reflecting two complementary features of an optimal proposal: a complete foreground and relatively small background  ...  The completeness score and fullness score are computed based on previously obtained completeness index and fullness index, by using "transfer functions" to control the contribution of each index to the  ... 
arXiv:1904.00641v1 fatcat:dpjrrapr6rekhfybn6yjvvr6iy

The Multimedia Sentiment Model Based on Online Homestay Reviews

Wenguang Song, School of Computer Science, Yangtze University, Hanyu Li, Qian Yu, Zhigang Liu, School of Computer Science, Yangtze University, School of Computer Science, University of Regina, Control Technology Institute, Wuxi Institute of Technology
2020 International Journal of Engineering and Manufacturing  
For text datasets, first use Word2vec to build a topic clustering model, then find the corresponding topic attribute dictionary through the topic center words, use Bayesian classifier is used for sentiment  ...  Index Terms: homestay; online review; image-text fusion; user score; CNN. 14 The Multimedia Sentiment Model Based on Online Homestay Reviews Copyright © 2020 MECS I.J.  ...  2020D01A132): Research and implementation of horizontal well inversion optimization interpretation method.  ... 
doi:10.5815/ijem.2020.04.02 fatcat:6ue3bkdt3rcgbedqxj3sk5j4ey

Construction of the Open Oral Evaluation Model Based on the Neural Network

Zhixin Chen, Xu Zhang, Zhiyuan Li, Anchu Li, Bai Yuan Ding
2021 Scientific Programming  
into the speech scoring model and text scoring model and makes a specific implementation of two scoring models, respectively.  ...  According to the problem of low efficiency and low scoring accuracy of the traditional oral language scoring system, this study builds an open oral language evaluation model based on the basic principles  ...  Conflicts of Interest e authors declare that they have no conflicts of interest regarding this work.  ... 
doi:10.1155/2021/3928246 fatcat:lqmjkp2m55barcica5pm3hlscm

Deep Learning the Indus Script [article]

Satish Palaniappan, Ronojoy Adhikari
2017 arXiv   pre-print
The image is first decomposed into regions using Selective Search and these regions are classified as containing textual and/or graphical information using a convolutional neural network.  ...  Regions classified as potentially containing text are hierarchically merged and trimmed to remove non-textual information.  ...  We thank Harappa.com [24] for their kind permission to use an image of the Indus seal in this paper.  ... 
arXiv:1702.00523v1 fatcat:w5biiiorx5cwxc3l73nqiutzby

Extracting Scientific Figures with Distantly Supervised Neural Networks

Noah Siegel, Nicholas Lourie, Russell Power, Waleed Ammar
2018 Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries - JCDL '18  
The model was successfully deployed in Semantic Scholar, a large-scale academic search engine, and used to extract figures in 13 million scientific documents.  ...  We use this dataset to train a deep neural network for end-to-end figure detection, yielding a model that can be more easily extended to new domains compared to previous work.  ...  Strides are 1 where not specified and all convolutional layers except those outputting predictions use ReLU activations. See [14] for the full ResNet-101 architecture. of 2 every 330,000 steps.  ... 
doi:10.1145/3197026.3197040 dblp:conf/jcdl/SiegelLPA18 fatcat:qzvg6w42vnebtnky3qx3cx7djy

LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis [article]

Zejiang Shen, Ruochen Zhang, Melissa Dell, Benjamin Charles Germain Lee, Jacob Carlson, Weining Li
2021 arXiv   pre-print
To promote extensibility, layoutparser also incorporates a community platform for sharing both pre-trained models and full document digitization pipelines.  ...  We demonstrate that layoutparser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io/.  ...  This measures the overlap between the detected and ground-truth characters, and the maximum is 1. 17 This measures the number of edits from the ground-truth text to the predicted text, and lower is better  ... 
arXiv:2103.15348v2 fatcat:7pz575jey5g63odk7axh7dpjzm

Automating Data Entry Forms for Banks Using OCR and CNN: Survey

Maithilee Vaidya
2019 International Journal for Research in Applied Science and Engineering Technology  
activity.  ...  To accurately digitize and transmit deposit slip information from smartphones to the bank, a scheme called "Automating Data Entry Forms for Banks Using OCR and CNN".  ...  [3] proposed an efficient and real-time cost beneficial method that enables international travelers to hear the text images of sign boards, routes in their own languages.  ... 
doi:10.22214/ijraset.2019.1144 fatcat:s7ul6ikqjjhqdf7nsjmmllpbyu

Object Specific Deep Feature for Face Detection

Xianxu HOU, Jiasong ZHU, Ke SUN, Linlin SHEN, Guoping QIU
2018 IEICE transactions on information and systems  
In this paper, we introduce a multi-scale approach to constructing robust face heatmaps based on OSC features for rapidly filtering out non-face regions thus significantly improving search efficiency for  ...  a CNN in which neurons are activated by the presence of specific objects in the input image.  ...  This work was also supported by the UK Engineering and Physical Sciences Research Council [grant number EP/L015463/1].  ... 
doi:10.1587/transinf.2017mvp0014 fatcat:qfgg246dxzefdfcxwtvc5uslv4

The Analysis of Public Opinion in Colleges and Universities Oriented to Wireless Networks under the Application of Intelligent Data Mining

WenNing Wu, ZhengHong Deng, Narasimhan Venkateswaran
2022 Wireless Communications and Mobile Computing  
Feature extraction of the text is done using Linear Discriminant Analysis (LDA).  ...  Convolutional neural network (CNN) is used for classification purpose.  ...  After the pooling operation, a full connection layer is used to classify the results of the convolutional neural network, which is a nonlinear activation function applied to the outcomes of the convolutional  ... 
doi:10.1155/2022/7597366 fatcat:l6fl33y6rna7pi4ivpjdlsytzi

Deep Features for Text Spotting [chapter]

Max Jaderberg, Andrea Vedaldi, Andrew Zisserman
2014 Lecture Notes in Computer Science  
The CNN has a novel architecture that enables efficient feature sharing (by using a number of layers in common) for text detection, character case-sensitive and insensitive classification, and bigram classification  ...  The goal of this work is text spotting in natural images. This is divided into two sequential tasks: detecting words regions in the image, and recognizing the words within these regions.  ...  and indexing large volumes of video data with text obtained by text spotting enables fast and accurate retrieval of video data from a text search [26] .  ... 
doi:10.1007/978-3-319-10593-2_34 fatcat:2qfohtp2zve7rl6x3f6ms6cufm

Non-technical Loss Detection in Power Grid Using Information Retrieval approaches: A Comparative Study

Agnaldo Aparecido Esmael, Hugo Helito Da Silva, Tuo Ji, Ricardo Da Silva Torres
2021 IEEE Access  
Next, these deep features are encoded into textual signatures and indexed using off-the-shelf solutions for posterior fraud searching.  ...  In this paper, we propose a new non-technical loss detection framework, which combines the effectiveness of convolutional neural network feature extractors with the efficiency of the Information Retrieval  ...  In this way, it is possible to index and search such signatures by using any available full-text search engine.  ... 
doi:10.1109/access.2021.3064858 fatcat:zhptfajpw5e4dammyenkpofd4q
« Previous Showing results 1 — 15 out of 5,639 results