Filters








117,218 Hits in 3.5 sec

Deep Architectures for Face Attributes [article]

Tobi Baumgartner, Jack Culpepper
2016 arXiv   pre-print
We train a deep convolutional neural network to perform identity classification using a new dataset of public figures annotated with age, gender, ethnicity and emotion labels, and then fine-tune it for  ...  Rather than fine-tune by relearning weights in one additional layer after the penultimate layer of the identity network, we try several different depths for each attribute.  ...  Acknowledgments We would like to thank Neil O'Hare for collaborating with us on the search engine query logs, and the entire Yahoo Vision and Machine Learning Team.  ... 
arXiv:1609.09018v1 fatcat:mpuhb6cnebgl7c2jc46gnzf52e

A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild [article]

Keke He, Yanwei Fu, Xiangyang Xue
2017 arXiv   pre-print
To address this problem, we present a novel jointly learned deep architecture for both facial attribute analysis and face detection.  ...  Existing works of analyzing face attributes are mostly based on the cropped and aligned face images.  ...  Conclusion In this paper, we propose a novel joint deep architecture for facial attribute prediction and face detection.  ... 
arXiv:1707.08705v1 fatcat:outvmhsrirhlfpfqkuoiovgoxm

Face Attribute Prediction Using Off-the-Shelf CNN Features [article]

Yang Zhong, Josephine Sullivan, Haibo Li
2016 arXiv   pre-print
Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors.  ...  As a typical classification problem, face attribute prediction has been addressed using deep learning.  ...  Acknowledgments We gratefully acknowledge the support from NVIDIA Corporation for GPU donations. We have enjoyed discussions with Ali Sharif Razavian and Atsuto Maki.  ... 
arXiv:1602.03935v2 fatcat:pej7c6pinndrxiwm2bsgrvzweq

Wavelength overprovisioning strategies for enhanced optical path restoration

Meiqian Wang, Marija Furdek, Lena Wosinska, Paolo Monti
2016 2016 18th International Conference on Transparent Optical Networks (ICTON)  
Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors.  ...  As a typical classification problem, face attribute prediction has been addressed using deep learning.  ...  Acknowledgments We gratefully acknowledge the support from NVIDIA Corporation for GPU donations. We have enjoyed discussion with Ali Sharif Razavian. We thank Dr. Anders Hedman for proofreading.  ... 
doi:10.1109/icton.2016.7550595 fatcat:eiov73gzn5hvfazk7ipwik36ne

AI-based BMI Inference from Facial Images: An Application to Weight Monitoring [article]

Hera Siddiqui, Ajita Rattani, Dakshina Ranjan Kisku, Tanner Dean
2020 arXiv   pre-print
the deep learning methods in BMI inference from face images with minimum Mean Absolute Error (MAE) of 1.04 obtained using ResNet50.  ...  To promote further research and development in this area, we evaluate and compare the performance of five different deep-learning based Convolutional Neural Network (CNN) architectures i.e., VGG19, ResNet50  ...  and comparative analysis of deep features from different CNN architectures for BMI prediction from facial images.  ... 
arXiv:2010.07442v1 fatcat:huuye2ncnve7xlbcfjh3g4ytp4

Multi-Task Learning Using Task Dependencies for Face Attributes Prediction

Di Fan, Hyunwoo Kim, Jummo Kim, Yunhui Liu, Qiang Huang
2019 Applied Sciences  
In this paper, we propose a multi-task learning using task dependencies architecture for face attributes prediction and evaluate the performance with the tasks of smile and gender prediction.  ...  Various studies show that dependencies exist in face attributes. Multi-task learning architecture can build a synergy among the correlated tasks by parameter sharing in the shared layers.  ...  A multi-task learning using task dependencies architecture for face attributes prediction in end-to-end manner.  ... 
doi:10.3390/app9122535 fatcat:txg2m4u2ajcn7pj53otj4anwfm

Leveraging Mid-Level Deep Representations For Predicting Face Attributes in the Wild [article]

Yang Zhong, Josephine Sullivan, Haibo Li
2016 arXiv   pre-print
Our investigations also show that by utilizing the mid-level representations one can employ a single deep network to achieve both face recognition and attribute prediction.  ...  In this paper, however, we consider the mid-level CNN features as an alternative to the high-level ones for attribute prediction.  ...  We employ publicly available data, architecture and a deep learning framework to train a face classification CNN.  ... 
arXiv:1602.01827v3 fatcat:d633vqzcbfcs3ijnsiwimyyume

Physical Attribute Prediction Using Deep Residual Neural Networks [article]

Rashidedin Jahandideh, Alireza Tavakoli Targhi, Maryam Tahmasbi
2018 arXiv   pre-print
This network was pretrained for the task of face recognition by using the VGG-Face dataset, and we finetune it by using our own dataset to predict physical attributes.  ...  We crawled around 61, 000 images from the web, then use face detection to crop faces from these real world images. We choose ResNet-50 as our base network architecture.  ...  Paper Number Year Title 1 2015 Deep Learning Face Attributes in the Wild 2 2016 Leveraging Mid-Level Deep Representations for Predicting Face Attributes in the Wild 3 2016 Attributes for  ... 
arXiv:1812.07857v1 fatcat:tpgwxog5ojd6nim2lnauclnxn4

Facemask Detection Algorithm on COVID Community Spread Control using EfficientNet Algorithm

Vivekanadam Balasubramaniam
2021 Journal of Soft Computing Paradigm  
Henceforth, this paper proposes a deep learning based facemask detection process for automating the human effort involved in monitoring process.  ...  This work utilizes an openly available facemask detection dataset with 7553 images for the training and verification process, which is based on CNN driven EfficientNet architecture with an accuracy of  ...  Several soft computing techniques are mostly employed in such cases for estimating the optimum attributes to train the deep learning model.  ... 
doi:10.36548/jscp.2021.2.005 fatcat:zfpiz4zbmzevpp6s2s2bmcj6vq

Deep or Shallow Facial Descriptors? A Case for Facial Attribute Classification and Face Retrieval [chapter]

Rasoul Banaeeyan, Mohd Haris Lye, Mohammad Faizal Ahmad Fauzi, Hezerul Abdul Karim, John See
2017 Lecture Notes in Computer Science  
attribute classification as well as constructing deep attributedriven feature vectors for face retrieval.  ...  In this study, we compare the performance of shallow and deep facial descriptors in the two mentioned applications by proposing to exploit distinctive facial features from a very deep pre-trained CNN for  ...  Finally, the attribute scores calculated for each face image are concatenated to construct a deep attribute-driven facial feature vector for that face.  ... 
doi:10.1007/978-3-319-54427-4_32 fatcat:5hptxjn43nbmvfn4dzqcuqqp5u

Feature Level Fusion from Facial Attributes for Face Recognition [article]

Mohammad Rasool Izadi
2021 arXiv   pre-print
We introduce a deep convolutional neural networks (CNN) architecture to classify facial attributes and recognize face images simultaneously via a shared learning paradigm to improve the accuracy for facial  ...  Specifically, we use a shared CNN architecture that jointly predicts facial attributes and recognize face images simultaneously via a shared learning parameters, and then we use facial attribute features  ...  Facial Attributes for Face Recognition The proposed architecture predicts attributes and uses them as an auxiliary modality to recognize face images. The model is created from two networks.  ... 
arXiv:1909.13126v2 fatcat:avbyxyrrb5bcvdqnyzwupsbt7a

Leveraging mid-level deep representations for predicting face attributes in the wild

Yang Zhong, Josephine Sullivan, Haibo Li
2016 2016 IEEE International Conference on Image Processing (ICIP)  
Our investigations also show that by utilizing the mid-level representations one can employ a single deep network to achieve both face recognition and attribute prediction.  ...  In this paper, however, we consider the mid-level CNN features as an alternative to the high-level ones for attribute prediction.  ...  We employ publicly available data, architecture and a deep learning framework to train a face classification CNN.  ... 
doi:10.1109/icip.2016.7532958 dblp:conf/icip/ZhongSL16 fatcat:q3ez4pzenvau7jjoj3h3rqar7m

Facial attribute-controlled sketch-to-image translation with generative adversarial networks

Mingming Hu, Jingtao Guo
2020 EURASIP Journal on Image and Video Processing  
To achieve this goal, first, we propose a new attribute classification loss to ensure that the synthesized face image with the facial attributes, which the users desire to have.  ...  Due to the rapid development of the generative adversarial networks (GANs) and convolution neural networks (CNN), increasing attention is being paid to face synthesis.  ...  Acknowledgements Thanks to my colleagues and classmates for their help in writing the paper; it is with their encouragement and guidance that I can finally complete this paper.  ... 
doi:10.1186/s13640-020-0489-5 fatcat:h3nnm7qg2ffirdhkqphfuahvmi

A Deep Face Identification Network Enhanced by Facial Attributes Prediction [article]

Fariborz Taherkhani, Nasser M. Nasrabadi, Jeremy Dawson
2018 arXiv   pre-print
In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance.  ...  We tested our model on two standard datasets annotated by identities and face attributes.  ...  Deep Joint Facial Attributes Prediction and Face Identification Model The proposed architecture predicts facial attributes and uses them as an auxiliary modality to recognize face images.  ... 
arXiv:1805.00324v1 fatcat:dd4c64zjczfflj6uhal5tf7qe4

A Deep Sum-Product Architecture for Robust Facial Attributes Analysis

Ping Luo, Xiaogang Wang, Xiaoou Tang
2013 2013 IEEE International Conference on Computer Vision  
between different attributes, which makes it more robust to occlusions and misdetection of face regions.  ...  Recent works have shown that facial attributes are useful in a number of applications such as face recognition and retrieval.  ...  We propose a new deep SPN architecture for robust estimation of facial attributes.  ... 
doi:10.1109/iccv.2013.356 dblp:conf/iccv/LuoWT13a fatcat:gduz7aeztbf6bltozwmc62d65u
« Previous Showing results 1 — 15 out of 117,218 results