A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Video Face Recognition using Deep Learning based Representation
2019
International Journal for Research in Applied Science and Engineering Technology
Preserved Fulltext
We proposed to design a novel video face verification algorithm that uses discrete wavelet transform and entropy computation to select feature-rich frames from a video sequence. ...
The proposed algorithm yields accuracy of verification about 97% at equal error rate on the database of YouTube faces. ...
After obtaining feature rich frames, the features exaction from rich frames is carried out using deep learning architecture. ...
doi:10.22214/ijraset.2019.3009
fatcat:lpfco63myrbqli3lfwov7j6elu
MDLFace: Memorability augmented deep learning for video face recognition
2014
IEEE International Joint Conference on Biometrics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Videos have ample amount of information in the form of frames that can be utilized for feature extraction and matching. However, face images in not all of the frames are "memorable" and useful. ...
The proposed algorithm, termed as MDLFace, is evaluated on two publicly available video face databases, Youtube Faces and Point and Shoot Challenge. ...
Besides memorability based frame selection, this research also proposes a deep learning based algorithm for feature extraction and face verification. ...
doi:10.1109/btas.2014.6996299
dblp:conf/icb/GoswamiBSV14
fatcat:pu5ijtoivnev5f2umhkqqhib7a
Unsupervised Learning of Face Representations
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We train our CNNs with the relatively low resolution faces extracted from video frames collected, and achieve a higher verification accuracy on the benchmark LFW dataset cf. hand-crafted features such ...
We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. ...
We then used this pre-trained network to obtain the representations of novel features for face verification on novel datasets. ...
arXiv:1803.01260v1
fatcat:t5r43re4xfhntofdayim26ttam
Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This work explores, for the first time, the use of this contextual information, as people with wearable cameras walk across different neighborhoods of a city, in order to learn a rich feature representation ...
By tracking the faces of casual walkers on more than 40 hours of egocentric video, we are able to cover tens of thousands of different identities and automatically extract nearly 5 million pairs of images ...
[42] used multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences, combining auto-encoders and prediction of future video frames. ...
arXiv:1604.06433v3
fatcat:6txunxggp5b6nievr7obm7du6m
Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
This work explores, for the first time, the use of this contextual information, as people with wearable cameras walk across different neighborhoods of a city, in order to learn a rich feature representation ...
By tracking the faces of casual walkers on more than 40 hours of egocentric video, we are able to cover tens of thousands of different identities and automatically extract nearly 5 million pairs of images ...
[40] used multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences, combining auto-encoders and prediction of future video frames. ...
doi:10.1109/cvpr.2016.252
dblp:conf/cvpr/WangCF16
fatcat:mh266al54fem7k3tpjngw5jv6m
Face Identification through Learned Image High Feature Video Frame Works
2018
International Journal of Scientific Research in Computer Sciences and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The choice of frames is followed by drawing features based on the representation of learning ,where three hand-outs are represented 1) Deep learning architecture, which is a mixture of low stacking automatic ...
The affluence and possibility of video taking devices, such as mobiles and security cameras have inspired the search for video on face recognition which is very relevant in police applications. ...
The projected deep learning structural design which unites SDAE joint representation with DBM is worn to take out features from the choosed frames. ...
doi:10.26438/ijsrcse/v6i4.2429
fatcat:eoljxbzjizhydgihvgxqs5xo6u
Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition
2018
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2016 pre-print arXiv:1607.05427v1 fatcat:id2w7kivwbdidcoxov6gzzxqt4Other Versions
First, to learn blur-robust face representations, we artificially blur training data composed of clear still images to account for a shortfall in real-world video training data. ...
Most impressively, TBE-CNN achieves state-of-the-art performance on three popular video face databases: PaSC, COX Face, and YouTube Faces. ...
The 512-dimensional feature vector is utilized as the final face representation of one video frame. ...
doi:10.1109/tpami.2017.2700390
pmid:28475048
fatcat:upxmdoqzo5dnri5zn6sdm7xnmi
Feature Aggregation Network for Video Face Recognition
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper aims to learn a compact representation of a video for video face recognition task. ...
Experiments on publicly available datasets, such as YouTube face dataset and IJB-A dataset, show the effectiveness of our method, and it achieves competitive performances on both the verification and identification ...
The method in [12] utilizes discrete wavelet transform and entropy computation to select feature-rich frames from a video sequence and learns a joint feature from them. ...
arXiv:1905.01796v2
fatcat:efkm2cbysbcj3haziicjhsfn2e
Discriminability Distillation in Group Representation Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Learning group representation is a commonly concerned issue in tasks where the basic unit is a group, set, or sequence. ...
We claim the most significant indicator to show whether the group representation can be benefited from one of its element is not the quality or an inexplicable score, but the discriminability w.r.t. the ...
Evaluation on YouTube Face. The YouTube Face [57] dataset includes 3425 videos of 1595 identities with an average of 2.15 videos per identity. The videos vary from 48 frames to 6,070 frames. ...
arXiv:2008.10850v2
fatcat:q5uht37akrgx7eit2wmhaw2vhm
A Fast and Accurate System for Face Detection, Identification, and Verification
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we describe the details of a deep learning pipeline for unconstrained face identification and verification which achieves state-of-the-art performance on several benchmark datasets. ...
CNNs are able to detect faces, locate facial landmarks, estimate pose, and recognize faces in unconstrained images and videos. ...
ACKNOWLEDGMENTS This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract ...
arXiv:1809.07586v1
fatcat:chihrnjh3nehnij6ipgf3q6yni
Attention Control with Metric Learning Alignment for Image Set-based Recognition
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper considers the problem of image set-based face verification and identification. ...
Extensive evaluations on IJB-A/B/C, YTF, Celebrity-1000 datasets demonstrate that our method outperforms many state-of-art approaches on the set-based as well as video-based face recognition databases. ...
Results on YouTube Face dataset The YouTube Face (YTF) dataset [68] is a widely used video face verif ication dataset, which contains 3,425 videos of 1,595 different subjects. ...
arXiv:1908.01872v1
fatcat:w7votkkj2ngt3b42ecl3fokuuu
Face Video Retrieval via Deep Learning of Binary Hash Representations
2016
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we develop a new deep convolutional neural network (deep CNN) to learn discriminative and compact binary representations of faces for face video retrieval. ...
Retrieving faces from large mess of videos is an attractive research topic with wide range of applications. ...
We model the face video as a set of face images. Given a face video, each frame is inputted into the deep CNN to obtain a binary representation. ...
doi:10.1609/aaai.v30i1.10445
fatcat:2ml4jbnsmffa3n6gdt3a3fp46q
Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
similarity score given a pair of face images or videos. ...
In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. ...
ACKNOWLEDGMENTS This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract ...
arXiv:1804.01159v2
fatcat:oqbzrmbmhzd5tmce3e7x3igh6a
Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2006.15473v1 fatcat:vnluuuh6uzhyzfoq6ryjz32d4m
Currently, most state-of-the-art deepfake detections are based on black-box models that process videos frame-by-frame for inference, and few closely examine their temporal inconsistencies. ...
In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations. ...
Feature encoder f (·): The feature encoder f encodes a processed video input x i ∈ R 224×224×S into a hidden representation z ∈ R H×W ×C . ...
arXiv:2006.15473v2
fatcat:75abohimmfdtdnqplt5pwj5hbq
Is Lip Region-of-Interest Sufficient for Lipreading?
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we propose to adopt the entire face for lipreading with self-supervised learning. ...
We argue that such information might benefit visual speech recognition if a powerful feature extractor employing the entire face is trained. ...
For video frames f 𝑣 are channel-wise concatenated to form the audio-visual representation f 𝑎𝑣 . ...
arXiv:2205.14295v2
fatcat:iyrtwsucijaw3oez6ikzot7qgm
« Previous
Showing results 1 — 15 out of 9,307 results