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
.
Filters
Cross-domain recognition by identifying compact joint subspaces
2015
2015 IEEE International Conference on Image Processing (ICIP)
We propose to solves the problem by finding the compact joint subspaces of source and target domain. ...
This paper introduces a new method to solve the cross-domain recognition problem. ...
Based on the above assumption, we propose a new method that solves the crossdomain recognition by finding the compact joint subspaces of source and target domain. ...
doi:10.1109/icip.2015.7351447
dblp:conf/icip/LinCCZZW15
fatcat:53im3b2kyvew7bccqkjfbicj2i
Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
[article]
2015
arXiv
pre-print
the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain. ...
The corresponding class label is then assigned by minimizing a cost function which reflects the overlap and topological structure consistency between subspaces across source and target domains, and within ...
Based on the above assumption, we propose a new method that solves the cross-domain recognition by finding the compact joint subspaces of source and target domain. ...
arXiv:1509.01719v1
fatcat:ajhj2ugnqfa7rm5373d36xvwsa
Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Specifically, we learn two coupled projections that project the source domain and target domain data into lowdimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously ...
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. ...
is maximized, 2) the discriminative information of source domain is preserved, 3) the divergence of source and target distributions is small, and 4) the divergence between source and target subspaces is ...
doi:10.1109/cvpr.2017.547
dblp:conf/cvpr/ZhangLO17
fatcat:ddz5bmxq4rghjpaxpnloey3xvy
Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
[article]
2017
arXiv
pre-print
Specifically, we learn two coupled projections that project the source domain and target domain data into low dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously ...
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. ...
is maximized, 2) the discriminative information of source domain is preserved, 3) the divergence of source and target distributions is small, and 4) the divergence between source and target subspaces is ...
arXiv:1705.05498v1
fatcat:nzjek4t4unehrbmtmvi6zgikbi
Transfer EEG Emotion Recognition by Combining Semi-Supervised Regression with Bipartite Graph Label Propagation
2022
Systems
bands and channels for cross-subject EEG emotion recognition are achieved by investigating the learned subspace, which provides more insights into the study of EEG emotion activation patterns. ...
However, most of the existing methods have focused only on domain adaptation and failed to achieve effective collaboration with label estimation. ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/systems10040111
fatcat:dqss5hso5nh5vgs4hscrfffppu
Joint cross-domain classification and subspace learning for unsupervised adaptation
2015
Pattern Recognition Letters
Specifically we learn the source subspace that best matches the target subspace while at the same time minimizing a regularized misclassification loss. ...
Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. ...
Acknowledgments The authors acknowledge the support of the FP7 EC project AXES and of the FP7 ERC Starting Grant 240530 COGNIMUND. ...
doi:10.1016/j.patrec.2015.07.009
fatcat:wbzdteqxfjdk3phzzazsw2esj4
Cross-corpus speech emotion recognition using subspace learning and domain adaption
2022
EURASIP Journal on Audio, Speech, and Music Processing
Then, the Hessian matrix is introduced to obtain the subspace for the extracted features in both source and target domains. ...
Specifically, training set data and the test set data are used to form the source domain and target domain, respectively. ...
The mapping relationship between the source domain subspace and the target domain subspace is acquired, which is described by a common space. ...
doi:10.1186/s13636-022-00264-5
fatcat:yolbjsyqlzhwpe7id4cnqc3x5i
Coupled Projection Transfer Metric Learning for Cross-Session Emotion Recognition from EEG
2022
Systems
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY ...
Conflicts of Interest: The authors declare no conflict of interest. ...
As shown in Figure 4 , we project the source and target domain data into respective subspaces by two matrices, and then minimize the discrepancies between projected data of the two domains. ...
doi:10.3390/systems10020047
dblp:journals/systems/ShenPDLK22
fatcat:gm4paddxrzgibe3oqfmyna3pxq
Joint cross-domain classification and subspace learning for unsupervised adaptation
[article]
2015
arXiv
pre-print
Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. ...
Specifically we learn the source subspace that best matches the target subspace while at the same time minimizing a regularized misclassification loss. ...
Acknowledgments The authors acknowledge the support of the FP7 EC project AXES. ...
arXiv:1411.4491v3
fatcat:44tdhll6qfc5zg6gkksxuv3zxa
Robust Multi-view Representation: A Unified Perspective from Multi-view Learning to Domain Adaption
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
learning, and domain adaption. ...
First of all, we formulate a unified learning framework which is able to model most existing multi-view learning and domain adaptation in this line. ...
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ...
doi:10.24963/ijcai.2018/767
dblp:conf/ijcai/DingSF18
fatcat:s2cwblwxnbgavaeirobiyyfk6e
A Survey of Unsupervised Domain Adaptation for Visual Recognition
[article]
2021
arXiv
pre-print
Unsupervised DA (UDA) deals with a labeled source domain and an unlabeled target domain. ...
The principal objective of UDA is to reduce the domain discrepancy between the labeled source data and unlabeled target data and to learn domain-invariant representations across the two domains during ...
It can identify the domain-specific and
target domain via PCA with a lower subspace dimensionality domain-independent features in different domains and then
d, which is determined by the ...
arXiv:2112.06745v1
fatcat:65ey4xuygrh4fphb5cqwvqi5fq
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation ...
In other words, for HDA, data from source and target domains are observed in separate feature spaces and thus exhibit distinct distributions. ...
Acknowledgements This work was supported in part by the Ministry of Science and Technology of Taiwan under Grants MOST103-2221-E-001-021-MY2, MOST104-2221-E-017-016, and MOST104-2119-M-002-039. ...
doi:10.1109/cvpr.2016.549
dblp:conf/cvpr/TsaiYW16
fatcat:3b33il2enzfovdkghngcmhdwue
Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data
2015
2015 IEEE International Conference on Computer Vision (ICCV)
For standard unsupervised domain adaptation, one typically obtains labeled data in the source domain and only observes unlabeled data in the target domain. ...
However, most existing works do not consider the scenarios in which either the label numbers across domains are different, or the data in the source and/or target domains might be collected from multiple ...
This work was supported in part by the Ministry of Science and Technology of Taiwan under Grants MOST103-2221-E-001-021-MY2 and MOST104-2221-E-017-016. ...
doi:10.1109/iccv.2015.469
dblp:conf/iccv/HsuCHTYW15
fatcat:peyg4gxotzc7tpowtakoxgvhmu
Investigation of Heterogeneity Sources for Occupational Task Recognition via Transfer Learning
2021
Sensors
This study aims to investigate the impact of four heterogeneity sources, cross-sensor, cross-subject, joint cross-sensor and cross-subject, and cross-scenario heterogeneities, on classification performance ...
Our results demonstrated that the support vector machine equipped with domain adaptation outperformed the baseline for cross-sensor, joint cross-subject and cross-sensor, and cross-subject cases, while ...
Data Availability Statement: To encourage future research and/or adoption of our work, we have made our MATLAB code available at https://github.com/sahand-hajifar/Occupational-Task-Recognition-via-Domain-Adaptation ...
doi:10.3390/s21196677
pmid:34641001
pmcid:PMC8512259
fatcat:7lf5ryt2zbeqfnmey4llcghnku
Person-specific domain adaptation with applications to heterogeneous face recognition
2014
2014 IEEE International Conference on Image Processing (ICIP)
By utilizing the subjects not of interest (i.e., those not to be recognized), we first derive a common feature space using their cross-domain face images, with the goal of eliminating differences between ...
(trained by the gallery images) are able to achieve satisfactory recognition performance. ...
Now, for the ith dimension in the PCA subspace (i.e., projected by w i ), we measure the distance between the means of the projected data from source and target domains: d(w i ) = k 1 n s X xj 2Ds w > ...
doi:10.1109/icip.2014.7025067
dblp:conf/icip/TsaiHHW14
fatcat:6ykilmeeqzfmxalzbkeugvw4i4
« Previous
Showing results 1 — 15 out of 3,789 results