Filters








1,189 Hits in 5.6 sec

Learning Object Detection from Captions via Textual Scene Attributes [article]

Achiya Jerbi, Roei Herzig, Jonathan Berant, Gal Chechik, Amir Globerson
<span title="2020-09-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we argue that captions contain much richer information about the image, including attributes of objects and their relations.  ...  Recent work has begun to explore image captions as a source for weak supervision, but to date, in the context of object detection, captions have only been used to infer the categories of the objects in  ...  Acknowledgements This work was supported by the Israeli Innovation Authority MAGNETON program, and the Israel Science Foundation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14558v1">arXiv:2009.14558v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vfcl2hkbhnhfjipkfavjxyra74">fatcat:vfcl2hkbhnhfjipkfavjxyra74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201002235921/https://arxiv.org/pdf/2009.14558v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14558v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A SURVEY ON RECENT METHODOLOGIES IN MULTILINGUAL CHARACTER DETECTION AND RECOGNITION

Snehal S Gaikwad ., S. L. Nalbalwar .
<span title="2019-07-31">2019</span> <i title="IJEAST"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/namhphsg6rdvtofp27o3scimoy" style="color: black;">International Journal of Engineering Applied Sciences and Technology</a> </i> &nbsp;
Content discovery and recognition has risen as a significant issue in the previous couple of years.  ...  Multilingual character detection and recognition from video subtitles, scenes and documents is additionally getting high consideration on this subject.  ...  Limitation of their work is, the quality of generated captions is much lower for news illustration task compared to another dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33564/ijeast.2019.v04i03.062">doi:10.33564/ijeast.2019.v04i03.062</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6tswkhkmwbcfnne6tk6z2jm6jm">fatcat:6tswkhkmwbcfnne6tk6z2jm6jm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320063313/https://www.ijeast.com/papers/382-390,Tesma403,IJEAST.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/12/f7/12f7f536ec5d0dff75457ff31431e327b9f46d9c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33564/ijeast.2019.v04i03.062"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

From Show to Tell: A Survey on Deep Learning-based Image Captioning [article]

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Silvia Cascianelli, Giuseppe Fiameni, Rita Cucchiara
<span title="2021-11-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This work aims at providing a comprehensive overview of image captioning approaches, from visual encoding and text generation to training strategies, datasets, and evaluation metrics.  ...  However, regardless of the impressive results, research in image captioning has not reached a conclusive answer yet.  ...  We also want to thank the authors who provided us with the captions and model weights for some of the surveyed approaches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06912v3">arXiv:2107.06912v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ezhutcovnvh4reiweedfmxjlve">fatcat:ezhutcovnvh4reiweedfmxjlve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210803222116/https://arxiv.org/pdf/2107.06912v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/52/9e/529e35113f102d5ae53ac6c0f311a559b7b3bead.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06912v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

AACR: Feature Fusion Effects of Algebraic Amalgamation Composed Representation on (De)Compositional Network for Caption Generation for Images

Chiranjib Sur
<span title="">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yzo2wjv2bbh2zo3zo5p7scalee" style="color: black;">SN Computer Science</a> </i> &nbsp;
structuring the linguistic attributes (related to grammar and parts of speech of language) which will provide a much better structure and grammatically correct sentence.  ...  A large part of the different ways of defining and improving these AACR are discussed and their performance concerning the traditional procedures and feature representations are evaluated for image captioning  ...  The author acknowledges University of Florida Research Computing for providing computational resources and support that have contributed to the research results reported in this publication.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42979-020-00238-4">doi:10.1007/s42979-020-00238-4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vmeamdy6dzf23hhzmmpakbe34u">fatcat:vmeamdy6dzf23hhzmmpakbe34u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108113432/https://link.springer.com/content/pdf/10.1007/s42979-020-00238-4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/81/2a/812a146dd76708f0e23e592cc18e104c640792b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42979-020-00238-4"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao Zhou, XinYu Ye, HuiLing Lu, Xiaomin Zheng, Shi Qiu, YunCan Liu, Chen Li
<span title="2022-04-25">2022</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/icbhosh775h7bgzgot6avm3cua" style="color: black;">BioMed Research International</a> </i> &nbsp;
unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image  ...  First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense  ...  Fifth, for performance improvement, network structure improves from simple to complex, but simple stacking of capsule layers does not improve performance; too much stacking will lead to too small coupling  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/2384830">doi:10.1155/2022/2384830</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35509707">pmid:35509707</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC9060995/">pmcid:PMC9060995</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7jp3tmtph5hk5gthgcomeccnte">fatcat:7jp3tmtph5hk5gthgcomeccnte</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220430005326/https://downloads.hindawi.com/journals/bmri/2022/2384830.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cb/87/cb874efb710a156d7aec2ccea7b861bd686e0a75.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/2384830"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9060995" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

High-level event recognition in unconstrained videos

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah
<span title="2012-11-13">2012</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/prsrkwgmmjas7elf5ki2xrsyvm" style="color: black;">International Journal of Multimedia Information Retrieval</a> </i> &nbsp;
The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence.  ...  While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features  ...  Yu-Gang Jiang was partially supported by grants from the National Natural Science Foundation of China (#61201387 and #61228205).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-012-0024-2">doi:10.1007/s13735-012-0024-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mfzttic3svb4tho2xb6aczgp4y">fatcat:mfzttic3svb4tho2xb6aczgp4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808122243/http://www.yugangjiang.info/publication/IJMIR-EventSurvey.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6a/72/6a720e2bf71cbb3c037919e84f78734349020622.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-012-0024-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Topic-Oriented Text Features Can Match Visual Deep Models of Video Memorability

Ricardo Kleinlein, Cristina Luna-Jiménez, David Arias-Cuadrado, Javier Ferreiros, Fernando Fernández-Martínez
<span title="2021-08-12">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
In this paper, we deepen the study of short captions as a means to convey in natural language the visual semantics of a video.  ...  We believe that short textual descriptions encapsulate most of these relationships among the elements of a video, and thus they represent a rich yet concise source of information to tackle the problem  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app11167406">doi:10.3390/app11167406</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mltshpchxfbonmz3c5bcxjzkoa">fatcat:mltshpchxfbonmz3c5bcxjzkoa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210814172630/https://res.mdpi.com/d_attachment/applsci/applsci-11-07406/article_deploy/applsci-11-07406.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/6d/a06dc8181d7e593112064ba713451a8d22f8c181.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app11167406"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision [article]

Andrew Shin, Masato Ishii, Takuya Narihira
<span title="2021-11-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, we discuss its current limitations and speculate upon some of the prospects that we find imminent.  ...  Its success also implies drastic changes in cross-modal tasks with language and vision, and many researchers have already tackled the issue.  ...  If such memory efficiency is coupled with distillation models, the costperformance issues described above will be further alleviated to a substantial extent, and architectural transitions in much wider  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04037v2">arXiv:2103.04037v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ws2djb722bat7nc53uodjqi7ki">fatcat:ws2djb722bat7nc53uodjqi7ki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211112072010/https://arxiv.org/pdf/2103.04037v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/36/c2/36c2039c886c222cd7afbb8a72b16f6cfc5d335b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04037v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

D2.1 Libraries and tools for multimodal content analysis

Doukhan; David, Danny Francis, Benoit Huet, Sami Keronen, Mikko Kurimo, Jorma Laaksonen, Tiina Lindh-Knuutila, Bernard Merialdo, Mats Sjöberg, Umut Sulubacak, Jörg Tiedemann, Kim Viljanen
<span title="2018-12-31">2018</span> <i title="Zenodo"> Zenodo </i> &nbsp;
These tools have been further improved and developed during the first year of the project.  ...  The description of the components is divided into the visual and auditory domain, and these are further subdivided into differ- ent themes.  ...  1 Acknowledgements Computational resources were provided by the Aalto Science-IT project and the CSC -IT Center for Science, Finland.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3697989">doi:10.5281/zenodo.3697989</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bde5x3yggzb2jk2fh2mu6t5wxy">fatcat:bde5x3yggzb2jk2fh2mu6t5wxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306112439/https://zenodo.org/record/3697989/files/D2.1-Libraries_and_tools_for_multimodal_content_analysis.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/b5/4fb565b251e4bfb5e588691b03ab33db07f72d8e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3697989"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods

Aditya Mogadala, Marimuthu Kalimuthu, Dietrich Klakow
<span title="2021-08-30">2021</span> <i title="AI Access Foundation"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4ax4efcwajcgvidb6hcg6mwx4a" style="color: black;">The Journal of Artificial Intelligence Research</a> </i> &nbsp;
Much of the growth in these fields has been made possible with deep learning, a sub-area of machine learning that uses artificial neural networks.  ...  This has created significant interest in the integration of vision and language.  ...  We extend our special thanks to Matthew Kuhn and Stephanie Lund for painstakingly proofing the whole manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.1.11688">doi:10.1613/jair.1.11688</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvfdrg3bwrh35fns4z67adqp6i">fatcat:kvfdrg3bwrh35fns4z67adqp6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210901050102/https://www.jair.org/index.php/jair/article/download/11688/26714" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/44/00445a5552bcf036b8b0a337550a5e11e84c2292.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.1.11688"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Fast and accurate surface alignment through an isometry-enforcing game

Andrea Albarelli, Emanuele Rodolà, Andrea Torsello
<span title="">2015</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jm6w2xclfzguxnhmnmq5omebpi" style="color: black;">Pattern Recognition</a> </i> &nbsp;
The practical effectiveness of the approach is confirmed by an extensive set of experiments and comparisons with state-of-the-art techniques.  ...  a mutual rigidity constraint to thrive, eliminating all the other correspondences.  ...  Acknowledgments We thankfully acknowledge Dror Aiger and Nicolas Mellado for their technical support and for making the 4PCS/Super4PCS code available.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2015.01.020">doi:10.1016/j.patcog.2015.01.020</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7w4c777iwrhjrkxjfdac5abrxm">fatcat:7w4c777iwrhjrkxjfdac5abrxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706051105/http://vision.in.tum.de/_media/spezial/bib/albarelli-pr15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/15/c9/15c9f1b36faca437c42113aba28be3440d34f42e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2015.01.020"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network

Zakaria Laskar, Iaroslav Melekhov, Surya Kalia, Juho Kannala
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6s36fqp6q5hgpdq2scjq3sfu6a" style="color: black;">2017 IEEE International Conference on Computer Vision Workshops (ICCVW)</a> </i> &nbsp;
Localization Pipeline The key limitation of end-to-end CNN based localization approaches is that the learning process is strongly coupled with the coordinate frame of the scene.  ...  In addition, the matches should be mutually consistent in both forward and backward direction.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2017.113">doi:10.1109/iccvw.2017.113</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccvw/LaskarMKK17.html">dblp:conf/iccvw/LaskarMKK17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qhms7distnf2zprw3r6oqeouqa">fatcat:qhms7distnf2zprw3r6oqeouqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428045117/https://aaltodoc.aalto.fi/bitstream/handle/123456789/47626/isbn9789526401461.pdf;jsessionid=AE3EEEA6731A48169CE8518B647D5B07?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/77/a3/77a378980de98b86831792b34d6571dd8db49dbc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2017.113"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
<span title="2020-10-19">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4d3elkqvznfzho6ki7a35bt47u" style="color: black;">Entropy</a> </i> &nbsp;
The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia.  ...  Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision.  ...  The image caption subnet that is further coupled with a textual attention generator to produce the caption embedding feature vector. This vector is vital for saliency refinement.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e22101174">doi:10.3390/e22101174</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33286942">pmid:33286942</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7597345/">pmcid:PMC7597345</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3p5d2nal4vhxbi2via3g7oicga">fatcat:3p5d2nal4vhxbi2via3g7oicga</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029221456/https://res.mdpi.com/d_attachment/entropy/entropy-22-01174/article_deploy/entropy-22-01174-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fe/c6/fec6834e5d29b064ef4313f288e2112a053a8922.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e22101174"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7597345" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Semantics Extraction from Images [chapter]

Ioannis Pratikakis, Anastasia Bolovinou, Bassilios Gatos, Stavros Perantonis
<span title="">2011</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
For each combination of knowledge and image representation, a detailed discussion is addressed that leads to fruitful conclusions for the impact of each approach.  ...  An overview of the state-of-the-art on semantics extraction from images is presented.  ...  In this section, there will be a discussion about methodologies which address a coupling of bottom-up and top-down approaches that is translated to an interplay between image segmentation and recognition  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20795-2_3">doi:10.1007/978-3-642-20795-2_3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h3xh2fmryfgj5hwn5k5fjsximy">fatcat:h3xh2fmryfgj5hwn5k5fjsximy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190304215444/http://pdfs.semanticscholar.org/c1bd/75dd43ad483e93a0c915d754b15e42eeec04.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/bd/c1bd75dd43ad483e93a0c915d754b15e42eeec04.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20795-2_3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Instance search retrospective with focus on TRECVID

George Awad, Wessel Kraaij, Paul Over, Shin'ichi Satoh
<span title="2017-02-22">2017</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/prsrkwgmmjas7elf5ki2xrsyvm" style="color: black;">International Journal of Multimedia Information Retrieval</a> </i> &nbsp;
The main contributions of the paper include i) an examination of the evolving design of the evaluation framework and its components (system tasks, data, measures); ii) an analysis of the influence of topic  ...  The Instance Search (INS) benchmark worked with a variety of large collections of data including Sound & Vision, Flickr, BBC (British Broadcasting Corporation) Rushes for the first 3 pilot years and with  ...  In the early years, search performance was dominated by taking advantage of the textual elements associated to news video, such as open captions, metadata and automatic speech recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-017-0121-3">doi:10.1007/s13735-017-0121-3</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28758054">pmid:28758054</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5531298/">pmcid:PMC5531298</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3khp2cscmbhohipfx246gspqlq">fatcat:3khp2cscmbhohipfx246gspqlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322092214/https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=922566" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b0/c6/b0c6021ce4849d5e9c89fea191e2fd74c99541a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-017-0121-3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5531298" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,189 results