Filters








15,014 Hits in 5.8 sec

Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation

Jie Ni, Qiang Qiu, Rama Chellappa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
These subspaces are able to capture the intrinsic domain shift and form a shared feature representation for cross domain recognition.  ...  We present experiments on face recognition across pose, illumination and blur variations, cross dataset object recognition, and report improved performance over the state of the art.  ...  The method in [10] designed a cross-domain classifier based on multiple base kernels.  ... 
doi:10.1109/cvpr.2013.95 dblp:conf/cvpr/NiQC13 fatcat:3yqb2pe42bal5jrkzmt5rzqvii

Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces [chapter]

Qiang Qiu, Jie Ni, Rama Chellappa
2014 Person Re-Identification  
In particular, we discuss the adaptation of dictionary-based methods for re-identification of faces.  ...  These subspaces are able to capture the intrinsic domain shift and form a shared feature representation for cross domain identification.  ...  Recognition Under Domain Shift To this end, we have learned a transition path which is encoded with the underlying domain shift.  ... 
doi:10.1007/978-1-4471-6296-4_13 dblp:series/acvpr/QiuNC14 fatcat:w5ggcnr4kzglzfgpip37iamjsq

Unsupervised visual domain adaptation via dictionary evolution

Songsong Wu, Xiao-Yuan Jing, Dong Yue, Jian Zhang, K Jian Yang, Jingyu Yang
2016 2016 IEEE International Conference on Multimedia and Expo (ICME)  
This problem, known as domain shift, always happens in real world visual applications, e.g. training and test faces in a face recognition task are captured by different lighting conditions and viewing  ...  can be widely applied to cross domain object classification, cross dataset digit recognition, face recognition across pose, and report the improved performance of DE over existing methods for unsupervised  ... 
doi:10.1109/icme.2016.7552896 dblp:conf/icmcs/WuJYZYY16 fatcat:trhrhyk22feifnnxcqpaegteri

Domain-Specific Face Synthesis for Video Face Recognition From a Single Sample Per Person

Fania Mokhayeri, Eric Granger, Guillaume-Alexandre Bilodeau
2019 IEEE Transactions on Information Forensics and Security  
In a particular implementation based on sparse representation classification, the synthetic faces generated with the DSFS are employed to form a cross-domain dictionary that account for structured sparsity  ...  The domain-specific variations of these face images are projected onto the reference stills by integrating an image-based face relighting technique inside the 3D reconstruction framework.  ...  Accordingly, the cross-domain dictionary designed by the synthetic ROIs generated via the DSFS method is most suitable to reduce visual domain shifts and potentially achieve a higher level of accuracy.  ... 
doi:10.1109/tifs.2018.2866295 fatcat:ixus2jv5hzenfmh5r2rbkyfg7q

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 3091 Multi-View Video Synopsis via Simultaneous Object-Shifting and View-Switching Optimization.  ...  Muthu, S., +, TIP 2020 5557-5570 Multi-View Video Synopsis via Simultaneous Object-Shifting and View-Switching Optimization.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

A Dictionary Approach to Domain-Invariant Learning in Deep Networks [article]

Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
2020 arXiv   pre-print
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN).  ...  , that domain shifts can be effectively handled by decomposing a convolutional layer into a domain-specific atom layer and a domain-shared coefficient layer, while both remain convolutional.  ...  Supervised simultaneous cross-domain face recognition.  ... 
arXiv:1909.11285v2 fatcat:4ucz7cnm4nbtvbu2z7xbgpszyy

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.  ...  domain 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  ...  This poses an additional challenge of domain shift [120] (photo/viewed→photo/unviewed), to be solved.  ... 
doi:10.1016/j.imavis.2016.09.001 fatcat:hy666szkk5bgfoazyxgwy6hli4

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
TAL aims to build models that can perform tasks of target domain by learning knowledge from a semantic related but distribution different source domain.  ...  Domain is referred to as the state of the world at a certain moment.  ...  ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

Dictionary Learning-Based Feature-Level Domain Adaptation for Cross-Scene Hyperspectral Image Classification

Minchao Ye, Yuntao Qian, Jun Zhou, Yuan Yan Tang
2017 IEEE Transactions on Geoscience and Remote Sensing  
To solve this problem, we propose a dictionary learning based feature level domain adaptation technique, which aligns the spectral distributions between source and target scenes by projecting their spectral  ...  The basis atoms in the learned dictionary represent the common spectral components, which span a cross-scene feature space to minimize the effect of spectral shift.  ...  Cross-scene feature extraction via multitask NMF based dictionary learning A general assumption for unsupervised domain adaptation is that there exist certain discriminative features shared by both domains  ... 
doi:10.1109/tgrs.2016.2627042 fatcat:jk5dgw325jd4beo3ijbv6bdwbq

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective [article]

Jing Zhang and Wanqing Li and Philip Ogunbona and Dong Xu
2019 arXiv   pre-print
Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes.  ...  This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.  ...  Problem-oriented Taxonomy of Cross-dataset Recognition In cross-dataset recognition, there are often two datasets.  ... 
arXiv:1705.04396v3 fatcat:iknfmppi5zca7ljovdlwvdwluu

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Jing Zhang, Wanqing Li, Philip Ogunbona, Dong Xu
2019 ACM Computing Surveys  
Specifically, it categorises the cross-dataset recognition into 17 problems based on a set of carefully chosen data and label attributes.  ...  Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes.  ...  Problem-oriented Taxonomy of Cross-dataset Recognition In cross-dataset recognition, there are often two datasets.  ... 
doi:10.1145/3291124 fatcat:thjzho3xsnfalprmkquldhwpvm

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
., +, TIP 2021 4371-4383 2021 2734-2744 DASGIL: Domain Adaptation for Semantic and Geometric-Aware Image-Multi-View Gait Image Generation for Cross-View Gait Recognition. Chen, Based Localization.  ...  ., +, TIP 2021 5600-5612 Multi-View Face Synthesis via Progressive Face Flow.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

A Survey on Heterogeneous Face Recognition: Sketch, Infra-red, 3D and Low-resolution [article]

Shuxin Ouyang, Timothy Hospedales, Yi-Zhe Song, Xueming Li
2014 arXiv   pre-print
Heterogeneous face recognition (HFR) refers to matching face imagery across different domains.  ...  A wide variety of new invariant features, cross-modality matching models and heterogeneous datasets being established in recent years.  ...  Exploiting Face Structure. The methods reviewed in this survey varied in how much face-specific information is exploited; as opposed to generic cross-domain methods.  ... 
arXiv:1409.5114v2 fatcat:pytctlmtonf6bhb4z3pszxoove

Generalized Domain-Adaptive Dictionaries

Sumit Shekhar, Vishal M. Patel, Hien V. Nguyen, Rama Chellappa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Specifically, we describe a technique which jointly learns projections of data in the two domains, and a latent dictionary which can succinctly represent both the domains in the projected low-dimensional  ...  Various recognition experiments show that the method performs on par or better than competitive stateof-the-art methods.  ...  First, we demonstrate some synthesis and recognition results on the CMU Multi-Pie dataset for face recognition across pose and illumination variations.  ... 
doi:10.1109/cvpr.2013.53 dblp:conf/cvpr/ShekharPNC13 fatcat:c4wsyo6gjfhflj2s7mncpkkzhi

Sparse Representation Classification with Structured Dictionary Design Strategy for Rotating Machinery Fault Diagnosis

Yun Kong, Tianyang Wang, Zhaoye Qin, Fulei Chu
2020 IEEE Access  
The proposed structured dictionary design strategy can enhance the representation power of dictionaries and thus promote the recognition performance of the sparsity-based diagnosis strategy.  ...  ., the structured dictionary design stage and the sparsity-based intelligent diagnosis stage.  ...  via (15) .  ... 
doi:10.1109/access.2020.3036250 fatcat:2hkimzs77jhlnkymdw6jmesyzi
« Previous Showing results 1 — 15 out of 15,014 results