Filters








85,183 Hits in 5.2 sec

Cross-database age estimation based on transfer learning

Ya Su, Yun Fu, Qi Tian, Xinbo Gao
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
In this paper, the cross-database age estimation problem is solved by a transfer learning framework.  ...  Experimental results for age estimation tasks on different datasets demonstrate the effectiveness and robustness of our proposed framework.  ...  Based on the proposed regularization subspace learning framework, we design a cross-domain age estimation method which can greatly improve the performance of the age estimation in the target database,  ... 
doi:10.1109/icassp.2010.5495414 dblp:conf/icassp/SuFTG10 fatcat:v33zga565jbblogps7uaewsoae

A Study on Cross-Population Age Estimation

Guodong Guo, Chao Zhang
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
Further, we study the amount of data needed in the target population to learn a cross-population age estimator. Finally, we study the feasibility of multi-source crosspopulation age estimation.  ...  Experiments are conducted on a large database of more than 21,000 face images selected from the MORPH.  ...  Comparison with Other Methods Our cross-population age estimation might be considered as a transfer learning problem [20] .  ... 
doi:10.1109/cvpr.2014.542 dblp:conf/cvpr/GuoZ14 fatcat:5ifb6s4glncm5lfkgyizc5nv3i

Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation

Kai Li, Junliang Xing, Chi Su, Weiming Hu, Yundong Zhang, Stephen Maybank
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
First, a novel cost-sensitive multitask loss function is designed to learn transferable aging features by training on the source population.  ...  In this work, we propose a Deep Cross-Population (DCP) age estimation model to achieve this goal. In particular, our DCP model develops a twostage training strategy.  ...  Since the DCP model is the first deep learning based model for cross-population age estimation.  ... 
doi:10.1109/cvpr.2018.00049 dblp:conf/cvpr/LiXSHZM18 fatcat:ofmqtgeiojcznoi7ndtn3xogyi

Understanding Kin Relationships in a Photo

Siyu Xia, Ming Shao, Jiebo Luo, Yun Fu
2012 IEEE transactions on multimedia  
Next, we develop a transfer subspace learning based algorithm in order to reduce the significant differences in the appearance distributions between children and old parents facial images.  ...  In addition, human subjects are used in a baseline study on both databases.  ...  This work has been applied to the cross-domain age estimation [43] and improved the accuracy on one data set by the knowledge transferred from the other data set.  ... 
doi:10.1109/tmm.2012.2187436 fatcat:ssjiktu7jrgvnh2bajlseo3m4a

Joint gender and age estimation based on speech signals using x-vectors and transfer learning [article]

Damian Kwasny, Daria Hemmerling
2020 arXiv   pre-print
We further propose a two-staged transfer learning scheme, utilizing large scale speech datasets: VoxCeleb and Common Voice, and usage of multitask learning to allow for joint age estimation and gender  ...  The proposed transfer learning scheme yields consecutive performance improvements in terms of both age estimation error and gender classification accuracy and the best performing system achieves new state-of-the-art  ...  Furthermore, we propose to use transfer learning from speaker recognition and age estimation/gender classification on different datasets.  ... 
arXiv:2012.01551v1 fatcat:kp2hasfnhnazzlomanxhcgrzxm

Detecting Smiles of Young Children via Deep Transfer Learning

Yu Xia, Di Huang, Yunhong Wang
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
However, the challenge caused by age variations has not been sufficiently focused on before.  ...  In this paper, we first highlight the impact of the discrepancy between infants and adults in a quantitative way on a newly collected database.  ...  Comparison of different configurations in DAN based on AlexNet. Table 4. Comparison of results with and without deep transfer learning on the BCS database.  ... 
doi:10.1109/iccvw.2017.196 dblp:conf/iccvw/Xia0W17 fatcat:i7rxm7sfynaq5hsyn7ximx6qde

Personalized prediction of live birth prior to the first in vitro fertilization treatment: a machine learning method

Jiahui Qiu, Pingping Li, Meng Dong, Xing Xin, Jichun Tan
2019 Journal of Translational Medicine  
Acknowledgements We would like to thank all the staff in the Reproductive Medical Center of Shengjing Hospital of China Medical University for their contributions to the database and Mr.  ...  A nested cross-validation procedure always provides an unbiased estimate error which is very close to that obtained on the new data in practical application.  ...  First, the study was performed based on data derived from a single center.  ... 
doi:10.1186/s12967-019-2062-5 pmid:31547822 pmcid:PMC6757430 fatcat:hfwpkn3zrfgwvitwbcpnccxb54

A Ranking Approach for Human Ages Estimation Based on Face Images

Kuang-Yu Chang, Chu-Song Chen, Yi-Ping Hung
2010 2010 20th International Conference on Pattern Recognition  
Experimental results show that our approach performs better than traditional multi-class-based and regression-based approaches for age estimation.  ...  When inferring a person's age, we may compare his or her face with many people whose ages are known, resulting in a series of comparative results, and then we conjecture the age based on the comparisons  ...  EXPERIMENTAL RESULTS The age estimation experiments are performed on two databases.  ... 
doi:10.1109/icpr.2010.829 dblp:conf/icpr/ChangCH10 fatcat:rsr24ydwxzebhfeglanlf2ncge

Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition

Jun Deng, Rui Xia, Zixing Zhang, Yang Liu, Bjorn Schuller
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this situation, a model is trained on one database while tested on another disjoint one.  ...  To exemplify effectiveness of our approach, we select the Interspeech Emotion Challenge's FAU Aibo Emotion Corpus as test database and two other publicly available databases as training set for extensive  ...  Based on the motivation of the 'sharing idea' in transfer learning, we propose an alternative structure of autoencoder that attempts to minimize the reconstruction error on both training set and test set  ... 
doi:10.1109/icassp.2014.6854517 dblp:conf/icassp/DengXZLS14 fatcat:c322hdq6uvg5lnnwkde4zmmzyq

Robust gender recognition by exploiting facial attributes dependencies

Juan Bekios-Calfa, José M. Buenaposada, Luis Baumela
2014 Pattern Recognition Letters  
Estimating human face gender from images is a problem that has been extensively studied because of its relevant applications.  ...  In the paper we study the dependencies among gender, age and pose facial attributes.  ...  Our proposal in this section is to transfer the alignment problem to the learning phase, avoiding the need for on-line alignment.  ... 
doi:10.1016/j.patrec.2013.04.028 fatcat:sonpqzthv5hw5piuwmc4gjr7fy

Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines

Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
FG-NET, Cross-Age Celebrity Dataset (CACD) and MORPH, and our collected large-scale aging database named AginG Faces in the Wild (AGFW).  ...  The Temporal Deep Restricted Boltzmann Machines based age progression model together with the prototype faces are then constructed to learn the aging transformation between faces in the sequence.  ...  of each age group, we propose a machine learning based approach to learn these aging rules, i.e. construct a set of RBMs based wrinkle models for every age group.  ... 
doi:10.1109/cvpr.2016.622 dblp:conf/cvpr/DuongLQB16 fatcat:ta2vyfe4u5aurjiffzlg3ti56a

Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines [article]

Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
2016 arXiv   pre-print
FG-NET, Cross-Age Celebrity Dataset (CACD) and MORPH, and our collected large-scale aging database named AginG Faces in the Wild (AGFW).  ...  The Temporal Deep Restricted Boltzmann Machines based age progression model together with the prototype faces are then constructed to learn the aging transformation between faces in the sequence.  ...  of each age group, we propose a machine learning based approach to learn these aging rules, i.e. construct a set of RBMs based wrinkle models for every age group.  ... 
arXiv:1606.02254v1 fatcat:vnk76svwubhabofy6h4fgebj3q

A Spatiotemporal Convolutional Neural Network for Automatic Pain Intensity Estimation from Facial Dynamics

Mohammad Tavakolian, Abdenour Hadid
2019 International Journal of Computer Vision  
Moreover, we introduce a cross-architecture knowledge transfer technique for training 3D convolutional neural networks using a pre-trained 2D architecture.  ...  In this paper, we focus on automatic pain intensity estimation from faces. This has a paramount potential diagnosis values in healthcare applications.  ...  After pre-training our SCN using the mentioned cross-architecture knowledge transfer tech- nique, we can fine-tune the model on the target database.  ... 
doi:10.1007/s11263-019-01191-3 fatcat:myk3dkggdngltkqyqv63rdjzki

Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition [article]

Chi Nhan Duong, Kha Gia Quach, Khoa Luu, T. Hoang Ngan le, Marios Savvides
2017 arXiv   pre-print
Our method is evaluated in both terms of synthesizing age-progressed faces and cross-age face verification and consistently shows the state-of-the-art results in various face aging databases, i.e.  ...  FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD).  ...  the face recognition model without re-train it on cross-age databases.  ... 
arXiv:1703.08617v1 fatcat:djiujaah2ncwtmbiylw5qtnjli

Not All Electrode Channels Are Needed: Knowledge Transfer From Only Stimulated Brain Regions for EEG Emotion Recognition

Hayford Perry Fordson, Xiaofen Xing, Kailing Guo, Xiangmin Xu
2022 Frontiers in Neuroscience  
BRADA is a new framework that works with the existing transfer learning method. We apply BRADA to both cross-subject and cross-database settings.  ...  The experimental results indicate that our proposed transfer learning method can improve valence-arousal emotion recognition tasks.  ...  Previous studies on EEG-based transfer learning do not investigate two real EEG databases with significantly related components.  ... 
doi:10.3389/fnins.2022.865201 pmid:35692430 pmcid:PMC9185168 fatcat:rdhflo3c2rcureo4znam5iobba
« Previous Showing results 1 — 15 out of 85,183 results