Filters








4,432 Hits in 6.2 sec

Object and Text-guided Semantics for CNN-based Activity Recognition [article]

Sungmin Eum, Christopher Reale, Heesung Kwon, Claire Bonial, Clare Voss
<span title="2018-05-04">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods have harvested the power  ...  We further improve upon the multitask learning approach by exploiting a text-guided semantic space to select the most relevant objects with respect to the target activities.  ...  CONCLUSION We have introduced a novel way of constructing an objectincorporated and text-guided CNN to better handle the task of video-based human activity recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01818v1">arXiv:1805.01818v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/br5ida3bybgqxkn7sh7p5desai">fatcat:br5ida3bybgqxkn7sh7p5desai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825130121/https://arxiv.org/pdf/1805.01818v1.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/b0/82/b08203fca1af7b95fda8aa3d29dcacd182375385.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01818v1" 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>

Guide Me: Interacting with Deep Networks

Christian Rupprecht, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
We evaluate the method on two datasets, showing that guiding a pre-trained network can improve performance, and provide extensive insights into the interaction between the guide and the CNN.  ...  We do so by inserting a layer that acts as a spatio-semantic guide into the network.  ...  Bear, Helisa Dhamo, Nicola Rieke, Oliver Scheel and Salvatore Virga for proofreading the manuscript and their valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00892">doi:10.1109/cvpr.2018.00892</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/RupprechtLNHT18.html">dblp:conf/cvpr/RupprechtLNHT18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rmcu7vi2drdkro7lm6xtwyihfy">fatcat:rmcu7vi2drdkro7lm6xtwyihfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319102401/http://openaccess.thecvf.com/content_cvpr_2018/papers/Rupprecht_Guide_Me_Interacting_CVPR_2018_paper.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/82/18/821864bf264f924ac7d63c02ad3fdfff3cefd990.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00892"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Topic Learning Pipeline for Curating Brain Cognitive Researches

Ying Sheng, Jianhui Chen, Xiaobo He, Zhe Xu, Jiangfan Gao, Shaofu Lin
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
It is a basic work in text semantic analysis [33] and text mining [34] .  ...  Fig. 6 gives the comparison between the candidate topic recognition layer of proposed model, which is based on CNN-BiLSTM, and baseline methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3032173">doi:10.1109/access.2020.3032173</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vn2pfypjkndxnlzccdhzyoptiy">fatcat:vn2pfypjkndxnlzccdhzyoptiy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023202431/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09229383.pdf?tp=&amp;arnumber=9229383&amp;isnumber=6514899&amp;ref=" 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/b2/d8/b2d8707bf408b16d14452d84c7c867b7ba1393af.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3032173"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Guide Me: Interacting with Deep Networks [article]

Christian Rupprecht, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari
<span title="2018-03-30">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We evaluate the method on two datasets, showing that guiding a pre-trained network can improve performance, and provide extensive insights into the interaction between the guide and the CNN.  ...  We do so by inserting a layer that acts as a spatio-semantic guide into the network.  ...  Bear, Helisa Dhamo, Nicola Rieke, Oliver Scheel and Salvatore Virga for proofreading the manuscript and their valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.11544v1">arXiv:1803.11544v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/czxjztoozvajtppn74vhuildii">fatcat:czxjztoozvajtppn74vhuildii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001052920/https://arxiv.org/pdf/1803.11544v1.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/6d/74/6d7405df661ae9257ea63f2b1b6de5827a687ca6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.11544v1" 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>

SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition [article]

Zhi Qiao, Yu Zhou, Dongbao Yang, Yucan Zhou, Weiping Wang
<span title="2020-05-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape.  ...  The semantic information is used both in the encoder module for supervision and in the decoder module for initializing.  ...  In addition, we sincerely thank Mingkun Yang for his help.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.10977v1">arXiv:2005.10977v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7ik6bxivyrfuzeiwnvcoqk5azq">fatcat:7ik6bxivyrfuzeiwnvcoqk5azq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528175758/https://arxiv.org/pdf/2005.10977v1.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/13/fa/13fa9c90c7b1ffde2233099eb2ffb51b81ce7621.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.10977v1" 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>

Scene Text Detection with Supervised Pyramid Context Network

Enze Xie, Yuhang Zang, Shuai Shao, Gang Yu, Cong Yao, Guangyao Li
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
To tackle this issue, mainly inspired by Mask R-CNN, we propose in this paper an effective model for scene text detection, which is based on Feature Pyramid Network (FPN) and instance segmentation.  ...  We propose a supervised pyramid context network (SPCNET) to precisely locate text regions while suppressing false positives.Benefited from the guidance of semantic information and sharing FPN, SPCNET obtains  ...  Mengxiao Lin in Megvii base-model group for all his kindness and great help to us.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33019038">doi:10.1609/aaai.v33i01.33019038</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3n5hzzpnxncc7bnjqrvmmglup4">fatcat:3n5hzzpnxncc7bnjqrvmmglup4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306053531/https://aaai.org/ojs/index.php/AAAI/article/download/4935/4808" 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/05/78/0578e70bd86164ea1ec65277c3e48cfb1dfd9595.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33019038"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Scene Text Detection with Supervised Pyramid Context Network [article]

Enze Xie, Yuhang Zang, Shuai Shao, Gang Yu, Cong Yao, Guangyao Li
<span title="2018-11-21">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To tackle this issue, mainly inspired by Mask R-CNN, we propose in this paper an effective model for scene text detection, which is based on Feature Pyramid Network (FPN) and instance segmentation.  ...  Scene text detection methods based on deep learning have achieved remarkable results over the past years.  ...  However, Mask R-CNN distinguishes object in a single region of interest, which lacks global semantic information guide.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.08605v1">arXiv:1811.08605v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/36sn4oi3erbmxflp7pn3tggroy">fatcat:36sn4oi3erbmxflp7pn3tggroy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912084026/https://arxiv.org/pdf/1811.08605v1.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/88/56/885696e5c978d9067fde24dfc66ae53559612836.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.08605v1" 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>

Deep Semantic Mapping for Cross-Modal Retrieval

Cheng Wang, Haojin Yang, Christoph Meinel
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jsqaafbrfneh7jtfvpjfzhs3ni" style="color: black;">2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI)</a> </i> &nbsp;
With images and texts mapped to a feature embedding space, class labels are used to guide the embedding learning, so that the embedding space has a semantic meaning common for both images and texts.  ...  In this paper, a deep architecture called Deep Semantic Embedding (DSE) is proposed, which is trained in an end-to-end manner for image-text cross-modal retrieval.  ...  With a stack of CNNs, FCs and nonlinear activations, both images and texts are mapped to a feature embedding space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ictai.2015.45">doi:10.1109/ictai.2015.45</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ictai/WangYM15.html">dblp:conf/ictai/WangYM15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/whu3bkap3nexxg7dlsqkiysbqu">fatcat:whu3bkap3nexxg7dlsqkiysbqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320063609/http://proceedings.mlr.press/v77/kang17a/kang17a.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/f0/a0/f0a0f341fa1f91ee58a5020297bea02f8863cb26.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ictai.2015.45"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Review on Methods and Applications in Multimodal Deep Learning [article]

Jabeen Summaira, Xi Li, Amin Muhammad Shoib, Jabbar Abdul
<span title="2022-02-18">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
., image, video, text, audio, body gestures, facial expressions, and physiological signals.  ...  Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning.  ...  [118] proposed a semantic guided visual attention mechanism based image captioning model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09195v1">arXiv:2202.09195v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wwxrmrwmerfabbenleylwmmj7y">fatcat:wwxrmrwmerfabbenleylwmmj7y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220508045925/https://arxiv.org/pdf/2202.09195v1.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/65/a0/65a01b760850d82505c2a04faf84a3e8c50398fe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.09195v1" 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>

Systematic Review of Computer Vision Semantic Analysis in Socially Assistive Robotics

Antonio Victor Alencar Lundgren, Matheus Albert Oliveira dos Santos, Byron Leite Dantas Bezerra, Carmelo José Albanez Bastos-Filho
<span title="2022-03-17">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bnh6csa7wfcb7fmvahv2ahfq2u" style="color: black;">AI</a> </i> &nbsp;
The merging of these fields creates demand for more complex and autonomous solutions, often struggling with the lack of contextual understanding of tasks that semantic analysis can provide and hardware  ...  This work aimed to understand the current scope of science in the merging fields of computer vision and semantic analysis in lightweight models for robotic assistance.  ...  For text and object detection and recognition, for instance, CNNs show extreme accuracy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ai3010014">doi:10.3390/ai3010014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fplfxt2kdfbafhvxeye6odzsha">fatcat:fplfxt2kdfbafhvxeye6odzsha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220505064628/https://mdpi-res.com/d_attachment/ai/ai-03-00014/article_deploy/ai-03-00014-v2.pdf?version=1647936805" 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/97/28/9728b30a4772ced6125249eeb6195521d1afbbe7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ai3010014"> <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 Rapid Review of Image Captioning

Adriyendi Adriyendi
<span title="2021-09-03">2021</span> <i title="Fakultas Ilmu Komputer Universitas Brawijaya"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ymwq4qbbrjembbj2dvxcunaiz4" style="color: black;">Journal of Information Technology and Computer Science</a> </i> &nbsp;
Image captioning is an automatic process for generating text based on the content observed in an image. We do review, create framework, and build application model.  ...  We review image captioning into 4 categories based on input model, process model, output model, and lingual image caption. Input model is based on criteria caption, method, and dataset.  ...  COCO (Microsoft Common Object in Context) is a very large data set for image recognition, object segmentation, and text writing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25126/jitecs.202162316">doi:10.25126/jitecs.202162316</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jebopkpe65gr3puusjzr4yzegy">fatcat:jebopkpe65gr3puusjzr4yzegy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210909134106/https://jitecs.ub.ac.id/index.php/jitecs/article/download/316/153" 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/9a/17/9a17239b5f928b62f355bf53b4283aa2da708fb6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25126/jitecs.202162316"> <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>

A Survey on Deep Visual Semantic Alignments for Generating Image Descriptions

Ms. Malge Shraddha V.
<span title="2020-01-31">2020</span> <i title="International Journal for Research in Applied Science and Engineering Technology (IJRASET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hsp44774azcezeyiq4kuzpfh5a" style="color: black;">International Journal for Research in Applied Science and Engineering Technology</a> </i> &nbsp;
As a human being it is easy for us to look at a scene/image and describe it in depth with all the details needed to be mentioned and spatial connectivity between the objects and entities.  ...  For a machine to deal with images is itself a huge task and to deal with all the fine details within an image needs lots of techniques to be dealt with.  ...  The RCNN stands for region based CNN is the CNN focusing on regions of objects within the image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.1059">doi:10.22214/ijraset.2020.1059</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c6v6btf3argivd5chirkkmcrfi">fatcat:c6v6btf3argivd5chirkkmcrfi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200215175825/http://ijraset.com/fileserve.php?FID=26357" 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/fb/0c/fb0cfedd83838bf1ebd070f85f8b87ed6b136f4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.1059"> <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>

A Survey on Content Based Image Retrieval Using Convolutional Neural Networks

<span title="2020-10-15">2020</span> <i title="The World Academy of Research in Science and Engineering"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/naqzxq5hurh2bp2pnvwitnnx44" style="color: black;">International Journal of Advanced Trends in Computer Science and Engineering</a> </i> &nbsp;
When an input image is given as a search query, its text content is processed to identify the semantics of the image, and the output will be based on the labels stored in it.  ...  This paper focuses on comparing various methods for reducing the semantic gap between low-dimensional and highdimensional features.  ...  The semantic text was based on attributes and relations among relevant text in the same cluster. The outcome of this became more effective and efficient in terms of performance and accuracy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.30534/ijatcse/2020/70952020">doi:10.30534/ijatcse/2020/70952020</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vjpq2j2pdza5di426baglhavai">fatcat:vjpq2j2pdza5di426baglhavai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201027124943/http://www.warse.org/IJATCSE/static/pdf/file/ijatcse70952020.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/c8/53/c853d4fe5163b086ba61b1e91129f1081671360b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.30534/ijatcse/2020/70952020"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition

Asish Bera, Zachary Wharton, Yonghuai Liu, Nik Bessis, Ardhendu Behera
<span title="2021-03-11">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
This paper presents a novel keypoints-based attention mechanism for visual recognition in still images.  ...  This framework applies to traditional and fine-grained image recognition tasks and does not require manually annotated regions (e.g. bounding-box of body parts, objects, etc.) for learning and prediction  ...  We thank the Associate Editor and three anonymous reviewers for their constructive comments that have improved the quality of the paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2021.3064256">doi:10.1109/tip.2021.3064256</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33705316">pmid:33705316</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ii6iozzjw5aptoeofoyq3yqeci">fatcat:ii6iozzjw5aptoeofoyq3yqeci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211109052123/https://arxiv.org/pdf/2110.12183v1.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/27/56/2756ea943da0ab7a8aba317d123e42a7589b7450.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2021.3064256"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Question Type Guided Attention in Visual Question Answering [chapter]

Yang Shi, Tommaso Furlanello, Sheng Zha, Animashree Anandkumar
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
type categories such as "Activity Recognition", "Utility" and "Counting" on TDIUC dataset compared to the state-of-art.  ...  It utilizes the information of question type to dynamically balance between bottom-up and top-down visual features, respectively extracted from ResNet and Faster R-CNN networks.  ...  Acknowledgements We thank Amazon AI for providing computing resources. Yang Shi is supported by Air Force Award FA9550-15-1-0221.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01225-0_10">doi:10.1007/978-3-030-01225-0_10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sknp2h7difdm7arhurjcyvqvju">fatcat:sknp2h7difdm7arhurjcyvqvju</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430033230/https://authors.library.caltech.edu/94175/3/1804.02088.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/2e/10/2e105974d58cdefcc866c5f6ca73ea033881ddd7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01225-0_10"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 4,432 results