Filters








15,259 Hits in 6.6 sec

Discriminability Distillation in Group Representation Learning [article]

Manyuan Zhang, Guanglu Song, Hang Zhou, Yu Liu
<span title="2020-09-01">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The whole procedure is denoted as discriminability distillation learning (DDL).  ...  The proposed DDL can be flexibly plugged into many group-based recognition tasks without influencing the original training procedures.  ...  In this paper, we care for three group representation learning tasks including set-to-set face recognition, video-based person re-identification, and action recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.10850v2">arXiv:2008.10850v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q5uht37akrgx7eit2wmhaw2vhm">fatcat:q5uht37akrgx7eit2wmhaw2vhm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200909232119/https://arxiv.org/pdf/2008.10850v2.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/2008.10850v2" 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>

PA-GAN: A Patch-Attention based Aggregation Network for Face Recognition in Surveillance

Ming Liu, Jinjin Liu, Ping Zhang, Qingbao Li
<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;
There have been varieties of efforts about video-based face recognition [2, 3, 4] .  ...  Video actually consists of many frames, so video-based face recognition can be treated as set-based recognition. This work was pioneered by Phillips [9] in 1996.  ...  Author Name: Preparation of Papers for IEEE Access (February 2017) VOLUME XX, 2017  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3017779">doi:10.1109/access.2020.3017779</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z62ycxblifdydoshfte6nka6le">fatcat:z62ycxblifdydoshfte6nka6le</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200820121809/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09171297.pdf?tp=&amp;arnumber=9171297&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/6a/f6/6af6a610a4ad205540a2b54ebbc376edee68dbf3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3017779"> <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>

Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN) [article]

Sixue Gong, Yichun Shi, Anil K. Jain
<span title="2019-07-02">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The whole network is trained in two steps: (i) train a base CNN for still image face recognition; (ii) add an aggregation module to the base network to learn the quality value for each feature component  ...  We propose a new approach to video face recognition.  ...  Although the ubiquity of deep learning algorithms has advanced face recognition technology for static face images, video-based face recognition still poses a significant research challenge.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.07327v3">arXiv:1902.07327v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ohgh3rsfhvbm3omrxrpfnss6h4">fatcat:ohgh3rsfhvbm3omrxrpfnss6h4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827183133/https://arxiv.org/pdf/1902.07327v2.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/7c/4a/7c4a74fe4801257e2326f79e42811f8744328ffb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.07327v3" 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>

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/753trptklbb4nj6jquqadzwwdu" style="color: black;">2017 IEEE International Conference on Computer Vision (ICCV)</a> </i> &nbsp;
Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual  ...  We demonstrate qualitatively that the network learns to suppress diverse artifacts in videos such as pose, illumination or occlusion without being explicitly trained for them.  ...  Evalutation Protocol The standard application of image-based face recognition engine for video face recognition is to first apply the face recognition engine to each frame and then aggregate extracted  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2017.630">doi:10.1109/iccv.2017.630</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccv/SohnLZY0C17.html">dblp:conf/iccv/SohnLZY0C17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vmlbvljov5hpjeuwn4w5cdy5ai">fatcat:vmlbvljov5hpjeuwn4w5cdy5ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170909152726/http://faculty.ucmerced.edu/mhyang/papers/iccv2017_video_face_recognition.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/55/1e/551eab6d5ecfbc26d89e5bb3910a918d393d7e64.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2017.630"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Low Quality Video Face Recognition: Multi-Mode Aggregation Recurrent Network (MARN)

Sixue Gong, Yichun Shi, Anil Jain
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6s36fqp6q5hgpdq2scjq3sfu6a" style="color: black;">2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)</a> </i> &nbsp;
We propose a Multi-mode Aggregation Recurrent Network (MARN) for real-world low-quality video face recognition.  ...  For low quality video sequences, however, more discriminative features can be obtained by aggregating the information in video frames.  ...  weights to aggregate image-based feature vectors instead of directly learning an aggregated representation), resulting in discriminative video face representations. • The attention scores of one video  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2019.00132">doi:10.1109/iccvw.2019.00132</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccvw/GongSJ19.html">dblp:conf/iccvw/GongSJ19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hk27qw4tz5d4hkiecoyiblmbrq">fatcat:hk27qw4tz5d4hkiecoyiblmbrq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710063828/https://openaccess.thecvf.com/content_ICCVW_2019/papers/RLQ/Gong_Low_Quality_Video_Face_Recognition_Multi-Mode_Aggregation_Recurrent_Network_MARN_ICCVW_2019_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/09/eb/09eb1b9c53a7fc293a06f0a283713fb652f53743.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2019.00132"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Attention-Set based Metric Learning for Video Face Recognition [article]

Yibo Hu, Xiang Wu, Ran He
<span title="2017-08-28">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Most existing CNN-based VFR methods only obtain a feature vector from a single image and simply aggregate the features in a video, which less consider the correlations of face images in one video.  ...  Face recognition has made great progress with the development of deep learning.  ...  In this paper, we propose an Attention-Set based Metric Learning (ASML) approach for video face recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.03805v3">arXiv:1704.03805v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sewqamsrovbiparxvsoge3eywe">fatcat:sewqamsrovbiparxvsoge3eywe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200916053901/https://arxiv.org/pdf/1704.03805v2.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/35/5e/355e46a02324ee41b9abde42aa6974896cd975cb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.03805v3" 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>

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos [article]

Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker
<span title="2017-08-07">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual  ...  We demonstrate qualitatively that the network learns to suppress diverse artifacts in videos such as pose, illumination or occlusion without being explicitly trained for them.  ...  , we learn domain-invariant discriminative representations for video face recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.02191v1">arXiv:1708.02191v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s4uclmrsjrh4rnitafez5fofki">fatcat:s4uclmrsjrh4rnitafez5fofki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826055319/https://arxiv.org/pdf/1708.02191v1.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/23/ed/23ed7f909e30ad2ec598b49169b669a5f0c8abe1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.02191v1" 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>

Recurrent Embedding Aggregation Network for Video Face Recognition [article]

Sixue Gong, Yichun Shi, Anil K. Jain
<span title="2019-06-25">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features, using Long Short-Term Memory (LSTM), a popular recurrent network, for feature  ...  We propose a Recurrent Embedding Aggregation Network (REAN) for set to set face recognition.  ...  In this paper, we propose a Recurrent Embedding Aggregation Network (REAN) for video face recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.12019v2">arXiv:1904.12019v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zifkv7msuzai7ae6gxhcwacwyq">fatcat:zifkv7msuzai7ae6gxhcwacwyq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200905160627/https://arxiv.org/pdf/1904.12019v1.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/c8/81/c88119be59f9d57a4e3d8f1c04b5b44b7c12de4a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.12019v2" 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>

Neural Aggregation Network for Video Face Recognition [article]

Jiaolong Yang, Peiran Ren, Dongqing Zhang, Dong Chen, Fang Wen, Hongdong Li, Gang Hua
<span title="2017-08-02">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a Neural Aggregation Network (NAN) for video face recognition.  ...  The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition.  ...  HL's work was supported in part by Australia ARC Centre of Excellence for Robotic Vision (CE140100016) and by CSIRO Data61.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.05474v4">arXiv:1603.05474v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z2626u6r3ballourbfoxmzwa6q">fatcat:z2626u6r3ballourbfoxmzwa6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018021657/https://arxiv.org/pdf/1603.05474v4.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/50/31/50316ccec5021aa0a4ec3b89c50bf360452bd837.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.05474v4" 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>

Feature Aggregation Network for Video Face Recognition [article]

Zhaoxiang Liu, Huan Hu, Jinqiang Bai, Shaohua Li, Shiguo Lian
<span title="2019-09-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper aims to learn a compact representation of a video for video face recognition task.  ...  It makes the best to exploit the valuable or discriminative part of each frame to promote the performance of face recognition, without discarding or despising low quality frames as usual methods do.  ...  Conclusion We introduced a new feature aggregation network for video face recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.01796v2">arXiv:1905.01796v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/efkm2cbysbcj3haziicjhsfn2e">fatcat:efkm2cbysbcj3haziicjhsfn2e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930201221/https://arxiv.org/pdf/1905.01796v2.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/f1/4ff19ee0fbead0bc4b568b3a463a672a31e52c49.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.01796v2" 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>

Neural Aggregation Network for Video Face Recognition

Jiaolong Yang, Peiran Ren, Dongqing Zhang, Dong Chen, Fang Wen, Hongdong Li, Gang Hua
<span title="">2017</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
This paper presents a Neural Aggregation Network (NAN) for video face recognition.  ...  The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition.  ...  HL's work was supported in part by Australia ARC Centre of Excellence for Robotic Vision (CE140100016) and by CSIRO Data61.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2017.554">doi:10.1109/cvpr.2017.554</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/YangRZCWLH17.html">dblp:conf/cvpr/YangRZCWLH17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gqalohdicrdv3ozh3sumzq3wze">fatcat:gqalohdicrdv3ozh3sumzq3wze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171215091354/http://openaccess.thecvf.com:80/content_cvpr_2017/papers/Yang_Neural_Aggregation_Network_CVPR_2017_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/47/9d/479d0365dd48fc01c654eadff1e751447445579a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2017.554"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Input Aggregated Network for Face Video Representation [article]

Zhen Dong, Su Jia, Chi Zhang, Mingtao Pei
<span title="2016-03-22">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To sufficiently discover the useful information contained in face videos, we present a novel network architecture called input aggregated network which is able to learn fixed-length representations for  ...  Recently, deep neural network has shown promising performance in face image recognition.  ...  ., the frame feature and the model of a face video might not be discriminative enough for the final recognition task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.06655v1">arXiv:1603.06655v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k6aboararzgmxifgfy2kax55ay">fatcat:k6aboararzgmxifgfy2kax55ay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014095830/https://arxiv.org/pdf/1603.06655v1.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/f5/9d/f59d123933c3681aa3c33668515fab06507f79e7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.06655v1" 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>

Frame attention networks for facial expression recognition in videos [article]

Debin Meng, Xiaojiang Peng, Kai Wang, Yu Qiao
<span title="2019-09-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The video-based facial expression recognition aims to classify a given video into several basic emotions. How to integrate facial features of individual frames is crucial for this task.  ...  The frame attention module learns multiple attention weights which are used to adaptively aggregate the feature vectors to form a single discriminative video representation.  ...  In this paper, inspired by the attention mechanism [14] of machine translation and the neural aggregation networks [15] of video face recognition, we propose the Frame Attention Networks (FAN) to adaptively  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.00193v2">arXiv:1907.00193v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/332b43zlufhkxhccw5n52sxvyq">fatcat:332b43zlufhkxhccw5n52sxvyq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824060346/https://arxiv.org/pdf/1907.00193v2.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/5e/6c/5e6cde094010d1dd32d3a532f6e846f5a9720f7a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.00193v2" 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>

Emotion Recognition with Spatial Attention and Temporal Softmax Pooling [chapter]

Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal, Eric Granger
<span title="">2019</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;
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences  ...  for a given emotion, and (2) temporal softmax pooling, to select the most important frames of the given video.  ...  Introduction Designing a system capable of encoding discriminant features for video-based emotion recognition is challenging because the appearance of faces may vary considerably according to the specific  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-27202-9_29">doi:10.1007/978-3-030-27202-9_29</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/go2eaekbavd4xgnf5y7o3t7ao4">fatcat:go2eaekbavd4xgnf5y7o3t7ao4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824172511/https://arxiv.org/pdf/1910.01254v1.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/c6/16/c616faa4b2758b18c259969e30603cf55adfeac4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-27202-9_29"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Table of contents

<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jqw2pm7kwvhchpdxpcm5ryoic4" style="color: black;">IEEE transactions on circuits and systems for video technology (Print)</a> </i> &nbsp;
Cheng 2288 Orthogonality Loss: Learning Discriminative Representations for Face Recognition ....................................... .....................................................................  ...  Lu 2415 Image/Video Storage and Retrieval CMPD: Using Cross Memory Network With Pair Discrimination for Image-Text Retrieval .............................. .............................................  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2021.3080805">doi:10.1109/tcsvt.2021.3080805</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bmy7voimtzdjbn5qpk4o2xoseu">fatcat:bmy7voimtzdjbn5qpk4o2xoseu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716173112/https://ieeexplore.ieee.org/ielx7/76/9446657/09446658.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/d4/52/d452a9dff9803a5aa8a997e33ae2d8ab1503ced5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2021.3080805"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 15,259 results