Filters








1,478 Hits in 2.3 sec

Adversarial Occlusion-aware Face Detection [article]

Yujia Chen, Lingxiao Song, Ran He
<span title="2018-09-29">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper introduces an Adversarial Occlusion-aware Face Detector (AOFD) by simultaneously detecting occluded faces and segmenting occluded areas.  ...  Specifically, we employ an adversarial training strategy to generate occlusion-like face features that are difficult for a face detector to recognize.  ...  Overall Architecture In order to detect faces with heavy occlusion, Adversarial Occlusion-aware Face Detector (AOFD) is designed with the view of (1) effectively utilizing the exposed facial areas, and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.05188v6">arXiv:1709.05188v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oa5o73jsizd5vckd7rjpjpb7zi">fatcat:oa5o73jsizd5vckd7rjpjpb7zi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823075818/https://arxiv.org/pdf/1709.05188v6.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/95/40/9540deae19e100078d39371b01895d98387698ae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.05188v6" 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 of face recognition techniques under occlusion [article]

Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers
<span title="2020-06-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
aware face recognition approaches, and 3) occlusion recovery based face recognition approaches.  ...  As a part of this review, we introduce face detection under occlusion, a preliminary step in face recognition.  ...  Adversarial occlusion-aware face detection (AOFD) [18] is proposed to detect occluded faces and segment the occlusion area simultaneously.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.11366v1">arXiv:2006.11366v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pttwdep5zbellldwricxfzgzki">fatcat:pttwdep5zbellldwricxfzgzki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200701131354/https://arxiv.org/pdf/2006.11366v1.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/fd/fe/fdfef78d9c74394562fcb5b0d9d5ba2b80c12ed4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.11366v1" 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 of face recognition techniques under occlusion

Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers
<span title="2021-04-05">2021</span> <i title="Institution of Engineering and Technology (IET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/amv24lmzarcebbfkxvuo6hhnpq" style="color: black;">IET Biometrics</a> </i> &nbsp;
As a part of this review, face detection under occlusion, a preliminary step in face recognition.  ...  approaches, 2) occlusion aware face recognition approaches, and 3) occlusion recovery based face recognition approaches.  ...  Adversarial occlusion-aware face detection (AOFD) [69] is proposed to detect occluded faces and segment the occlusion area simultaneously.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/bme2.12029">doi:10.1049/bme2.12029</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bkks2gmblfabhgte4snl4x54eu">fatcat:bkks2gmblfabhgte4snl4x54eu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716201213/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/bme2.12029" 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/8e/64/8e64866306cd89745230036b114661d5c59834d3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/bme2.12029"> <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>

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Wenyan Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, Qiang Zhou
<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 present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation.  ...  Moreover, we propose a new dataset WFLW to unify training and testing across different factors, including poses, expressions, illuminations, makeups, occlusions, and blurriness.  ...  Introduction Face alignment, which refers to facial landmark detection in this work, serves as a key step for many face applications, e.g., face recognition [75] , face verification [48, 49] and face  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00227">doi:10.1109/cvpr.2018.00227</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/Wu0YWC018.html">dblp:conf/cvpr/Wu0YWC018</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5figilislvdqxbklhu3rstaaya">fatcat:5figilislvdqxbklhu3rstaaya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190623133855/http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Look_at_Boundary_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/84/a2/84a20d0a47c0d826b77f73075530d618ba7573d2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00227"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization [article]

Yu Chen, Chunhua Shen, Hao Chen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
<span title="2019-02-24">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs).  ...  It remains a challenging task when input images severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced.  ...  For body parts without occlusions, our method improves the baseline by about 0.8% of detection rate.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.00253v5">arXiv:1711.00253v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3laenudkwjbqleiszofe6paxja">fatcat:3laenudkwjbqleiszofe6paxja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823202450/https://arxiv.org/pdf/1711.00253v5.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/9d/80/9d80643c7e2ad9d78aa886630cef47171e58e926.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.00253v5" 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>

Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion

Hongzhe Liu, Weicheng Zheng, Cheng Xu, Teng Liu, Min Zuo, Mariko Nakano-Miyatake
<span title="2020-11-26">2020</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wpareqynwbgqdfodcyhh36aqaq" style="color: black;">Mathematical Problems in Engineering</a> </i> &nbsp;
In this paper, we present an effective framework with the objective of addressing the occlusion problem for facial landmark detection, which includes a generative adversarial network with improved autoencoders  ...  The performance of the facial landmark detection model will be in trouble when it is under occlusion condition.  ...  Most recently, LAB [23] proposed is a boundary-aware face alignment algorithm by utilizing boundary lines as the geometric structure of a human face to help facial landmark localization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2020/4589260">doi:10.1155/2020/4589260</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dl72cim6djgp3dhyt6es3j4xb4">fatcat:dl72cim6djgp3dhyt6es3j4xb4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201129190606/http://downloads.hindawi.com/journals/mpe/2020/4589260.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/d0/51/d05119a65c68215b22095ebbd127c6c00c7892b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2020/4589260"> <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>

Look at Boundary: A Boundary-Aware Face Alignment Algorithm [article]

Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, Qiang Zhou
<span title="2018-05-26">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation.  ...  Our boundary- aware face alignment algorithm achieves 3.49% mean error on 300-W Fullset, which outperforms state-of-the-art methods by a large margin.  ...  Introduction Face alignment, which refers to facial landmark detection in this work, serves as a key step for many face applications, e.g., face recognition [75] , face verification [48, 49] and face  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.10483v1">arXiv:1805.10483v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ycbcr6lbzzfq3bghg4dcrzwthm">fatcat:ycbcr6lbzzfq3bghg4dcrzwthm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929225112/https://arxiv.org/pdf/1805.10483v1.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/5b/4c/5b4cf56e58368d3f0874a39a6fcd1d43e9de4c0c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.10483v1" 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>

Robust LSTM-Autoencoders for Face De-Occlusion in the Wild [article]

Fang Zhao, Jiashi Feng, Jian Zhao, Wenhan Yang, Shuicheng Yan
<span title="2016-12-27">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Receiving the representation learned by the encoder, the LSTM decoder with a dual channel architecture reconstructs the overall face and detects occlusion simultaneously, and by feat of LSTM, the decoder  ...  Moreover, to minimize identify information loss and guarantee face recognition accuracy over recovered faces, we introduce an identity-preserving adversarial training scheme to further improve RLA.  ...  Finally, the reconstructed face is integrated with the occluded face in an occlusion-aware manner to produce the recovered occlusion-free face.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.08534v1">arXiv:1612.08534v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zntfg5hgbzdtbleolce3kdg2fi">fatcat:zntfg5hgbzdtbleolce3kdg2fi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022175624/https://arxiv.org/pdf/1612.08534v1.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/20/e5/20e504782951e0c2979d9aec88c76334f7505393.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.08534v1" 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>

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization

Yu Chen, Chunhua Shen, Hao Chen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
<span title="2019-02-26">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs).  ...  It remains a challenging task when input images come with severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced.  ...  For body parts without occlusions, our method improves the baseline by about 0.8% of detection rate.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2019.2901875">doi:10.1109/tpami.2019.2901875</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30835211">pmid:30835211</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bwcawevazfcp3dlk5qcg4j3ube">fatcat:bwcawevazfcp3dlk5qcg4j3ube</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427213352/https://digital.library.adelaide.edu.au/dspace/bitstream/2440/126991/3/hdl_126991.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/1b/18/1b1862b1710e5c4afc26df7a3c95964ea5e6a015.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2019.2901875"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
<span title="2021-01-29">2021</span> <i title="Springer (Biomed Central Ltd.)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pkhnkszyprhb3orbf6g7tqmgiu" style="color: black;">Journal of Big Data</a> </i> &nbsp;
, metallic surface defect detection, disaster prediction, etc., are inevitable.  ...  Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection  ...  [217] . proposed Adversarial Occlusion Aware Face Detection (AOFD) to overcome the problem of limited occluded face image in training dataset. As opposed to cropping or erasing, Dwibedi et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s40537-021-00414-0">doi:10.1186/s40537-021-00414-0</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33552840">pmid:33552840</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7845583/">pmcid:PMC7845583</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g3p6hbjuj5c5vbe23ms4g6ed6q">fatcat:g3p6hbjuj5c5vbe23ms4g6ed6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210209074224/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC7845583&amp;blobtype=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/96/c6/96c6e99504f50375f741848e1f7d89fe11c61e3f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s40537-021-00414-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7845583" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Depth-Aware Generative Adversarial Network for Talking Head Video Generation [article]

Fa-Ting Hong, Longhao Zhang, Li Shen, Dan Xu
<span title="2022-03-15">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
All these contributions compose a novel depth-aware generative adversarial network (DaGAN) for talking head generation.  ...  Extensive experiments conducted demonstrate that our proposed method can generate highly realistic faces, and achieve significant results on the unseen human faces.  ...  Conclusions In this work, we proposed a depth-aware generative adversarial network (DaGAN) for talking head generation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.06605v2">arXiv:2203.06605v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5xzosxgqwretre4md7e6z22jrm">fatcat:5xzosxgqwretre4md7e6z22jrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220316015734/https://arxiv.org/pdf/2203.06605v2.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/ff/f6/fff60ef90f7ebfcc48999da55866c79b9ee68549.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.06605v2" 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>

Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation [article]

Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
<span title="2017-05-02">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions.  ...  To address the problem by incorporating priors about the structure of human bodies, we propose a novel structure-aware convolutional network to implicitly take such priors into account during training  ...  The method developed here can be immediately applied to other shape estimation problems such as face landmark detection using DCNNs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.00389v2">arXiv:1705.00389v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bjf4re2cujgu7bddjpkdenbzea">fatcat:bjf4re2cujgu7bddjpkdenbzea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901155109/https://arxiv.org/pdf/1705.00389v2.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/17/32/17322dc449d363bb2e02c9eac045c2373c5b0f94.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.00389v2" 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>

2021 16TH IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)

<span title="2021-12-15">2021</span> <i title="IEEE"> 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021) </i> &nbsp;
Unknown Aware Feature Learning for Face Forgery Detection Liang Shi; Jie Zhang; Chenyue Liang; Shiguang Shan 45.  ...  Explainable Thermal to Visible Face Recognition Using Latent-Guided Generative Adversarial Network David Anghelone; Cunjian Chen; Philippe Faure; Arun Ross; Antitza Dantcheva 40.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/fg52635.2021.9667043">doi:10.1109/fg52635.2021.9667043</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q67llypbybbrbacdiyia6hs2pe">fatcat:q67llypbybbrbacdiyia6hs2pe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220202175455/https://ieeexplore.ieee.org/ielx7/9666787/9666788/09667043.pdf?tp=&amp;arnumber=9667043&amp;isnumber=9666788&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/7e/de/7ede49da23005d85faaf2cfefd02d9665f45a510.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/fg52635.2021.9667043"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Tracking by Joint Local and Global Search: A Target-aware Attention based Approach [article]

Xiao Wang, Jin Tang, Bin Luo, Yaowei Wang, Yonghong Tian, Feng Wu
<span title="2021-06-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
More importantly, we resort to adversarial training for better attention prediction.  ...  In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking  ...  Many trackers are proposed in recent years, but visual tracking still faces many challenges including heavy occlusion, abrupt changing, and large deformation, etc.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04840v1">arXiv:2106.04840v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3pktzebc6vfzrmr7ueu7l7qpd4">fatcat:3pktzebc6vfzrmr7ueu7l7qpd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210612030213/https://arxiv.org/pdf/2106.04840v1.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/27/84/27849a90109b93ec80d190d570041722fb2b0576.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04840v1" 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>

FD-StackGAN: Face De-occlusion Using Stacked Generative Adversarial Networks

<span title="2021-07-31">2021</span> <i title="Korean Society for Internet Information (KSII)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hupfbobgkvepdnt5g32qxkypsy" style="color: black;">KSII Transactions on Internet and Information Systems</a> </i> &nbsp;
In the proposed model, Face De-occlusion using Stacked Generative Adversarial Network (FD-StackGAN), a divide-and-conquer scheme is used to divide the mask de-occlusion process into two key stages.  ...  Keywords: Generative adversarial network (GAN), image restoration, image reconstruction, occlusions mask removal.  ...  [17] proposed a two-stage network to perform a face completion task called Geometry Aware Face Completion (GAFC) model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2021.07.014">doi:10.3837/tiis.2021.07.014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fmr64k5vfjdfvg66sekt43mima">fatcat:fmr64k5vfjdfvg66sekt43mima</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210805010950/http://itiis.org/digital-library/manuscript/file/24812/TIIS%20Vol%2015,%20No%207-14.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/85/4f85b3fc24aa7616a8217a5ea107b8411d1dda21.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2021.07.014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,478 results