Filters








41,572 Hits in 5.5 sec

Person-specific domain adaptation with applications to heterogeneous face recognition

Yao-Hung Tsai, Hung-Ming Hsu, Cheng-An Hou, Yu-Chiang Frank Wang
2014 2014 IEEE International Conference on Image Processing (ICIP)  
In this paper, we present a person-specific domain adaptation framework for HFR.  ...  To generalize our feature space for representing and recognizing the subjects of interest, we advocate the construction of person-specific domain adaptation model in this space, so that the classifiers  ...  Thus, how to solve such cross-domain recognition problems becomes a very challenging task. Heterogeneous face recognition (HFR) is an example of cross-domain recognition problems (e.g., [1, 2, 3] ).  ... 
doi:10.1109/icip.2014.7025067 dblp:conf/icip/TsaiHHW14 fatcat:6ykilmeeqzfmxalzbkeugvw4i4

Domain Adaptive Self-Taught Learning for Heterogeneous Face Recognition

Cheng-An Hou, Min-Chun Yang, Yu-Chiang Frank Wang
2014 2014 22nd International Conference on Pattern Recognition  
For biometrics, heterogeneous face recognition (HFR) deals with recognition problems in which training/gallery images are collected in terms of one modality (e.g., photos), while test/probe images are  ...  In our experiments, we consider sketch-to-photo and near-infrared (NIR) to visible spectrum (VIS) face recognition problems for evaluating the performance of our proposed approach.  ...  Illustration of domain adaptation for heterogeneous face recognition.  ... 
doi:10.1109/icpr.2014.529 dblp:conf/icpr/HouYW14 fatcat:7y2qgmtbergqngzpwydzw7hlfi

DAIL: Dataset-Aware and Invariant Learning for Face Recognition [article]

Gaoang Wang, Lin Chen, Tianqiang Liu, Mingwei He, Jiebo Luo
2021 arXiv   pre-print
To solve the second issue, domain adaptation with gradient reversal layers is employed for dataset invariant learning.  ...  To achieve good performance in face recognition, a large scale training dataset is usually required.  ...  Domain Adaptation face recognition.  ... 
arXiv:2101.05419v1 fatcat:l7n4rr3r5ravrdlg5byhjho57u

SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person [article]

Sungeun Hong, Woobin Im, Jongbin Ryu, Hyun S. Yang
2018 arXiv   pre-print
Real-world face recognition using a single sample per person (SSPP) is a challenging task.  ...  To overcome this shortage, we generate synthetic images with varying poses using a 3D face model.  ...  To address this issue, we approach SSPP face recognition from the perspective of domain adaptation (DA).  ... 
arXiv:1702.04069v4 fatcat:s3fiyylt2vav3k5ontcdvnscj4

Special issue on content-based multimedia indexing in the era of artificial intelligence

Stevan Rudinac, Jenny Benois-Pineau, Stephane Marchand-Maillet
2021 Multimedia tools and applications  
Modeling the properties of increasingly heterogeneous multimedia items and their complex relations in parallel to indexing is a challenging task.  ...  This special issue aims at gathering and presenting new advances in the tasks related to the applications of AI in content-based multimedia indexing. in Dublin, Ireland.  ...  The authors tackle the problem of domain adaptation in object recognition tasks by proposing an efficient approach to learning and evaluating the quality of intermediate subspace features, designed to  ... 
doi:10.1007/s11042-021-10923-y fatcat:3pb4xekvuvatdifm33dkbw7bzy

Problem Definition on Face Recognition: A Review

Akshaya Kumar Sharma, Amit Shrivastava
2019 Asian Journal Of Advanced Basic Sciences  
With the event of deep learning technique, several vision Related issues enter into a replacement era. Some tries have been created with relation to heterogeneous face recognition. J. Ngiam et al.  ...  Face recognition system which is a very popular now days, has very useful applications such as forensic, person identification, bank card identification [3] , access control [4] and surveillance [5  ... 
doi:10.33980/ajabs.2019.v07i01.002 fatcat:uoqwawpoanh43eo4stdlglnyfy

Adversarial Discriminative Heterogeneous Face Recognition [article]

Lingxiao Song and Man Zhang and Xiang Wu and Ran He
2017 arXiv   pre-print
The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR).  ...  In the pixel space, we make use of generative adversarial networks to perform cross-spectral face hallucination.  ...  A key effort for face recognition is to alleviate intra-personal differences while enlarge inter-personal differences.  ... 
arXiv:1709.03675v1 fatcat:gnjwnkszrfgnlikmla6vgqnqhm

Deep Visual Domain Adaptation: A Survey [article]

Mei Wang, Weihong Deng
2018 arXiv   pre-print
Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection.  ...  In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions.  ...  (c) Some face images from LFW, BCS and CUFS databases. Realworld computer vision applications, such as face recognition, must learn to adapt to distributions specific to each domain.  ... 
arXiv:1802.03601v4 fatcat:d5hwwecipjfjzmh7725lmepzfe

Transfer Metric Learning: Algorithms, Applications and Outlooks [article]

Yong Luo, Yonggang Wen, Ling-Yu Duan, Dacheng Tao
2018 arXiv   pre-print
Transfer metric learning (TML) is able to mitigate this issue for DML in the domain of interest (target domain) by leveraging knowledge/information from other related domains (source domains).  ...  However, the label information may be insufficient in real-world applications due to the high-labeling cost, and DML may fail in this case.  ...  other important applications, such as face verification [4] and person re-identification [5] .  ... 
arXiv:1810.03944v3 fatcat:cngmqqfcm5dsphaukh6xuq4bf4

Guest Editors' Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis

Trevor Darrell, Christoph Lampert, Nicu Sebe, Ying Wu, Yan Yan
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Moreover, the authors have applied the above two methods to heterogeneous face matching by coupled learning methods (C-CA-LBFL and C-CA-LBMFL).  ...  DOMAIN ADAPTATION METHOD The second group of 3 papers are centered on domain adaptation methods for sharing information.  ... 
doi:10.1109/tpami.2018.2804998 fatcat:urin3tvgy5f7ng5djfvlm4mop4

A survey on heterogeneous face recognition: Sketch, infra-red, 3D and low-resolution

Shuxin Ouyang, Timothy Hospedales, Yi-Zhe Song, Xueming Li, Chen Change Loy, Xiaogang Wang
2016 Image and Vision Computing  
Heterogeneous face recognition (HFR) refers to matching face imagery across different domains.  ...  Feature-based LBP [32, 34] Eigenface [51] S 2 R 2 [18] Matching 31, 8, 33, 4, 9] NN [27, 52, 19, 20, 21 ] NN [16] NN with χ 2 [29, 30] NN with χ 2 [35, 41] NN with χ 2 [42] NN with HI [34] NN with Cosine  ...  Heterogeneous face recognition (HFR) refers to the problem of matching faces across different visual domains.  ... 
doi:10.1016/j.imavis.2016.09.001 fatcat:hy666szkk5bgfoazyxgwy6hli4

Designing Automated Deployment Strategies of Face Recognition Solutions in Heterogeneous IoT Platforms

Unai Elordi, Chiara Lunerti, Luis Unzueta, Jon Goenetxea, Nerea Aranjuelo, Alvaro Bertelsen, Ignacio Arganda-Carreras
2021 Information  
In this paper, we tackle the problem of deploying face recognition (FR) solutions in heterogeneous Internet of Things (IoT) platforms.  ...  We analyze different approaches to solving all these challenges and propose a knowledge-driven methodology for the automated deployment of DNN-based FR solutions in IoT devices, with the secure management  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable, the study does not report any data.  ... 
doi:10.3390/info12120532 fatcat:gfklv5jdtrdt3c3mb6qea4eziq

ALMARVI System Solution for Image and Video Processing in Healthcare, Surveillance and Mobile Applications

Zaid Al-Ars, Steven van der Vlugt, Pekka Jääskeläinen, Frank van der Linden
2018 Journal of Signal Processing Systems  
We illustrate the challenges faced within the project based on use cases from the three targeted application domains, and how these can address the 4 main project objectives addressing 4 challenges faced  ...  in image and video processing in 3 application domains: healthcare, surveillance and mobile.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1007/s11265-018-1423-2 fatcat:pbyyki7fbzcdxnyrmkbdpbxxxa

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
Next, we summarize some promising applications of AIoT that are likely to profoundly reshape our world. Finally, we highlight the challenges facing AIoT and some potential research opportunities.  ...  Specifically, we briefly present the AIoT architecture in the context of cloud computing, fog computing, and edge computing.  ...  domain adaptation [128] .  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4

Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework [article]

Qiong Wu and Kaiwen He and Xu Chen
2020 arXiv   pre-print
To cope with the heterogeneity issues in IoT environments, we investigate emerging personalized federated learning methods which are able to mitigate the negative effects caused by heterogeneity in different  ...  We finally provide a case study of IoT based human activity recognition to demonstrate the effectiveness of personalized federated learning for intelligent IoT applications.  ...  models adaptive to their application environments.  ... 
arXiv:2002.10671v3 fatcat:4hjdd5ledzhdppdkk3cpfhd7nm
« Previous Showing results 1 — 15 out of 41,572 results