Filters








13,645 Hits in 4.3 sec

Discriminative Paired Dictionary Learning for Visual Recognition

Hui-Hung Wang, Yi-Ling Chen, Chen-Kuo Chiang
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
A Paired Discriminative K-SVD (PD-KSVD) dictionary learning method is presented in this paper for visual recognition.  ...  To achieve high discrimination and low reconstruction errors simultaneously for sparse coding, we propose to learn class-specific sub-dictionaries from pairs of positive and negative classes to jointly  ...  We argue that the discrimination of dictionary can be also achieved through learning from pairs of classes.  ... 
doi:10.1145/2964284.2967184 dblp:conf/mm/WangCC16 fatcat:j2fzfolgb5ejnm2gleibnrkk3e

Active Discriminative Dictionary Learning for Weather Recognition

Caixia Zheng, Fan Zhang, Huirong Hou, Chao Bi, Ming Zhang, Baoxue Zhang
2016 Mathematical Problems in Engineering  
Secondly, unlike other methods which used the traditional classifiers (e.g., SVM andK-NN), we use discriminative dictionary learning as the classification model for weather, which could address the limitations  ...  Moreover, the active learning procedure is introduced into dictionary learning to avoid requiring a large number of labeled samples to train the classification model for achieving good performance of weather  ...  dictionary pair for obtaining good results.  ... 
doi:10.1155/2016/8272859 fatcat:lcntodjirjaxpbw7nuqtujy5jq

Person Re-Identification Based on Weighted Indexing Structures [chapter]

Cristianne R. S. Dutra, Matheus Castro Rocha, William Robson Schwartz
2014 Lecture Notes in Computer Science  
The results shown in Figure 4 (b) indicate that the predominance filter is more discriminative achieving better recognition rates. Visual Dictionaries.  ...  Other works focus on data scalability of transference learning, dealing with the ability of learning a model obtained from an initial pair of cameras to adapt to a new pair of target cameras [15, 16]  ... 
doi:10.1007/978-3-319-12568-8_44 fatcat:zyprrmkxgvb5hfmdgxlpzbt2bi

Class-Specific Sparse Principal Component Analysis for Visual Classification

Fei Pan, Zai-Xu Zhang, Bao-Di Liu, Ji-Jun Xie
2020 IEEE Access  
First, we propose a class-specific sparse PCA approach to extend the conventional dictionary learning to dictionary pair learning for visual classification.  ...  In this paper, we focus on designing capable dictionary learning architecture for the visual classification task with few-shot training samples.  ...  Class-specific dictionary learning based classification method learns a dictionary for each class and the learned dictionary is discriminative.  ... 
doi:10.1109/access.2020.3001202 fatcat:rp6xkm5ilre4jpkvxqqq4l2s44

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)  
favorable to visual recognition.  ...  We claim that a shared dictionary joining discriminative power with representative ability is more conductive to cross-domain visual recognition.  ... 
doi:10.1109/icme.2016.7552896 dblp:conf/icmcs/WuJYZYY16 fatcat:trhrhyk22feifnnxcqpaegteri

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning [article]

Yulin Sun, Zhao Zhang, Weiming Jiang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang
2019 arXiv   pre-print
In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning.  ...  Specifically, RA-DPL improves existing projective dictionary pair learning in four perspectives.  ...  Foundation of China (61672365, 61732008, 61725203, 61622305, 61871444, 61806035), High-Level Talent of the "Six Talent Peak" Project of Jiangsu Province (XYDXX-055) and the Fundamental Research Funds for  ... 
arXiv:1911.08680v1 fatcat:edcgg2flgfgurgj5wmef47vbn4

Object categorization by learned universal visual dictionary

J. Winn, A. Criminisi, T. Minka
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
The main contribution of this paper is two fold: i) an optimally compact visual dictionary is learned by pair-wise merging of visual words from an initially large dictionary.  ...  Abstract This paper presents a new algorithm for the automatic recognition of object classes from images (categorization).  ...  Textons pairs which do not contribute to class discriminability are merged together by our learning algorithm (the pair ab in the figure).  ... 
doi:10.1109/iccv.2005.171 dblp:conf/iccv/WinnCM05 fatcat:v33h7mdf6zgypitt2jmz5dqaq4

Projective dictionary pair learning for pattern classification

Shuhang Gu, Lei Zhang, Wangmeng Zuo, Xiangchu Feng
2014 Neural Information Processing Systems  
We propose a new discriminative DL framework, namely projective dictionary pair learning (DPL), which learns a synthesis dictionary and an analysis dictionary jointly to achieve the goal of signal representation  ...  Discriminative dictionary learning (DL) has been widely studied in various pattern classification problems.  ...  First, we introduce a new DL framework, which extends the conventional discriminative synthesis dictionary learning to discriminative synthesis and analysis dictionary pair learning (DPL).  ... 
dblp:conf/nips/GuZZF14 fatcat:tfddi3x3ofds5hew2v5revghuy

Convolutional Dictionary Pair Learning Network for Image Representation Learning [article]

Zhao Zhang, Yulin Sun, Yang Wang, Zhengjun Zha, Shuicheng Yan, Meng Wang
2020 arXiv   pre-print
learning schemes of the CNN and dictionary pair learning into a unified framework.  ...  Generally, the architecture of CDPL-Net includes two convolutional/pooling layers and two dictionary pair learn-ing (DPL) layers in the representation learning module.  ...  ACKNOWLEDGEMENTS This paper is partially supported by the National Natural Science Foundation of China (61672365, 61732008, 61725203, 61622305, 61871444 and 61806035) and the Fundamental Research Funds for  ... 
arXiv:1912.12138v3 fatcat:xqueqykknjfq7kemsk5eaweiiy

Color object recognition via cross-domain learning on RGB-D images

Yawen Huang, Fan Zhu, Ling Shao, Alejandro F. Frangi
2016 2016 IEEE International Conference on Robotics and Automation (ICRA)  
We present a novel approach that utilizes labeled RGB-D data in the training stage, where depth features are extracted for enhancing the discriminative capability of the original learning system that only  ...  In order to alleviate cross-domain discrepancy, we employ a state-of-the-art domain-adaptive dictionary learning algorithm that updates image representations in both domains and the classifier parameters  ...  The cross-domain dictionary learning is then performed through learning a discriminative dictionary pair and the corresponding classifier simultaneously. by jointly learning the dictionary and the classification  ... 
doi:10.1109/icra.2016.7487308 dblp:conf/icra/HuangZSF16 fatcat:5g6qde5snbbbngbrbykoxt2vjq

Indoor Scene Recognition from RGB-D Images by Learning Scene Bases

Shaohua Wan, Changbo Hu, J.K. Aggarwal
2014 2014 22nd International Conference on Pattern Recognition  
Second, we learn class-specific sub-dictionaries that capture the high-order couplings between the objects and attributes.  ...  In particular, elastic net regularization and geometric similarity constraint is imposed to increase the discriminative power of the sub-dictionaries.  ...  Instead of learning one overcomplete dictionary for all classes, we learn class-specific sub-dictionaries to increase the discrimination.  ... 
doi:10.1109/icpr.2014.588 dblp:conf/icpr/WanHA14 fatcat:xz7zvhdbtrctxjpuhtw6ahuque

Robust Audio-Visual Instance Discrimination via Active Contrastive Set Mining [article]

Hanyu Xuan, Yihong Xu, Shuo Chen, Zhiliang Wu, Jian Yang, Yan Yan, Xavier Alameda-Pineda
2022 arXiv   pre-print
As a state-of-the-art solution, Audio-Visual Instance Discrimination (AVID) extends instance discrimination to the audio-visual realm.  ...  The recent success of audio-visual representation learning can be largely attributed to their pervasive property of audio-visual synchronization, which can be used as self-annotated supervision.  ...  Minimising NCE loss means maximising a lower bound on the MI between audio-visual pairs, which allows the model to learn to discriminate whether audio-visual pairs are "similar" or "dissimilar".  ... 
arXiv:2204.12366v1 fatcat:ixrdqdv4zjdknfpcyllv3yoqyq

Discriminative Dictionary Learning with Pairwise Constraints [chapter]

Huimin Guo, Zhuolin Jiang, Larry S. Davis
2013 Lecture Notes in Computer Science  
We propose a unified discriminative dictionary learning approach for both pair matching and multiclass classification tasks.  ...  The learned dictionary encourages feature points from a similar pair (or the same class) to have similar sparse codes.  ...  As it shows, compared to KSVD, higher similarity scores for the 'same pairs' and lower similarity scores for 'different' pairs are obtained by our discriminative dictionary learning.  ... 
doi:10.1007/978-3-642-37331-2_25 fatcat:wt7sxuoozffa5fixnn73zdg2nq

Enhancing Action Recognition by Cross-Domain Dictionary Learning

Fan Zhu, Ling Shao
2013 Procedings of the British Machine Vision Conference 2013  
through which a reconstructive, discriminative and domain-adaptive dictionary-pair can be learned.  ...  We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain.  ...  discriminative and domain-adaptive dictionary pair for data under different distributions.  ... 
doi:10.5244/c.27.52 dblp:conf/bmvc/ZhuS13 fatcat:p3cg4bbnfbdpro3bgkgpygfccu

DISCRIMINATIVE DICTIONARY PAIR LEARNING FOR IMAGE CLASSIFICATION

Nguyen Hoang Vu, Tran Quoc Cuong, Tran Thanh Phong
2020 Journal of Computer Science and Cybernetics  
In this paper, to improve the discriminability of the popular dictionary pair learning (DPL) algorithm, we propose a new method called discriminative dictionary pair learning (DDPL) for image classification  ...  Dictionary learning (DL) for sparse coding has been widely applied in the field of computer vision.  ...  [4] proposed discriminative dictionary pair learning method based on differentiable support vector function (DPL-SV) for visual recognition. Li et al.  ... 
doi:10.15625/1813-9663/36/4/15105 fatcat:2ucd3cubzbdt5ebmioobyjd7yi
« Previous Showing results 1 — 15 out of 13,645 results