Filters








246 Hits in 3.0 sec

Image Classification via Semi-supervised pLSA

Liansheng Zhuang, Lanbo She, Yuning Jiang, Ketan Tang, Nenghai Yu
2009 2009 Fifth International Conference on Image and Graphics  
In this paper, we propose Semi-Supervised pLSA (SS-pLSA) for image classification.  ...  Compared with the classic non-supervised pLSA, our method overcomes the shortcoming of poor classification performance when the features of two categories are quite similar.  ...  Image classification via Semi-Supervised pLSA In this section we will detailedly introduce our Semi-Supervised pLSA algorithm.  ... 
doi:10.1109/icig.2009.153 dblp:conf/icig/ZhuangSJTY09 fatcat:yvnygnxklvaxnbmkzoa5t7cj3u

Latent topic based multi-instance learning method for localized content-based image retrieval

Da-xiang Li, Jiu-lun Fan, Dian-wei Wang, Ying Liu
2012 Computers and Mathematics with Applications  
Focusing on the problem of localized content-based image retrieval, based on probabilistic latent semantic analysis (PLSA) and transductive support vector machine (TSVM), a novel semi-supervised multi-instance  ...  Finally, in order to use the unlabeled images to improve retrieval accuracy, using semi-supervised TSVM to train classifiers.  ...  For the problem of small sample learning, we use semi-supervised TSVM to train classifiers, which can take advantage of large number of unlabeled images to improve the classification accuracy.  ... 
doi:10.1016/j.camwa.2011.12.030 fatcat:5qggbn6dljhxhkvduuozoslvjq

Scene Classification Using Cascaded Probabilistic Latent Semantic Analysis

Emrah ERGÜL, Nafiz ARICA
2009 Journal of Naval Science and Engineering  
In this paper we propose a novel approach of image representation for weakly supervised scene classification that mainly combine two popular methods in the literature: Bag-of-Words (BoW) modeling and probabilistic  ...  The new image representation scheme called Cascaded pLSA performs pLSA in a hierarchical sense after the BoW representation based on SIFT features is extracted.  ...  We compare the performance of our method to semi-supervised LDA of Fei-Fei et. al, [1] weakly supervised Spatial Pyramid of Lazebnik et. al [2] , and Spatial Pyramid pLSA of Bosch et. al [13] using  ... 
doaj:682322308de5448ea747fae942bd6c27 fatcat:3cl4dlkilrgunnrswct5grrs3y

Semi-Supervised Linear Discriminant Clustering

Chien-Liang Liu, Wen-Hoar Hsaio, Chia-Hoang Lee, Fu-Sheng Gou
2014 IEEE Transactions on Cybernetics  
This paper devises a semi-supervised learning method called semi-supervised linear discriminant clustering (Semi-LDC).  ...  The Semi-LDC uses the proposed algorithm, called constrained-PLSA, to estimate the soft labels of unlabeled examples.  ...  Semi-supervised Learning Semi-supervised learning methods can be further classified into semi-supervised classification and semi-supervised clustering methods.  ... 
doi:10.1109/tcyb.2013.2278466 pmid:23996591 fatcat:dpxxp6lcyraxhb2rzrbryy2pqa

Scene Classification Via pLSA [chapter]

Anna Bosch, Andrew Zisserman, Xavier Muñoz
2006 Lecture Notes in Computer Science  
Classification performance is compared to the supervised approaches of Vogel & Schiele [19] and Oliva & Torralba [11] , and the semi-supervised approach of Fei Fei & Perona [3] using their own datasets  ...  In all cases the combination of (unsupervised) pLSA followed by (supervised) nearest neighbour classification achieves superior results.  ...  [15] ; (ii) the dense SIFT [9] features developed in Dalal and Triggs [2] for pedestrian detection; and (iii) the semi-supervised application of Latent Dirichlet Analysis (LDA) for scene classification  ... 
doi:10.1007/11744085_40 fatcat:iyk2uone3netfdq3h3eyatgtny

Image categorization by learning with context and consistency

Zhiwu Lu, H.H.S. Ip
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
This paper presents a novel semi-supervised learning method which can make use of intra-image semantic context and inter-image cluster consistency for image categorization with less labeled data.  ...  To develop a graph-based semi-supervised learning approach to image categorization, we incorporate the intra-image semantic context into a kind of spatial Markov kernel which can be used as the affinity  ...  Semi-Supervised Categorization Spatial Markov Kernel To develop a graph-based semi-supervised learning approach to image categorization with less labeled data, we then incorporate the above intra-image  ... 
doi:10.1109/cvprw.2009.5206851 fatcat:vc75h3mph5dzrkeezjekmubexm

Image categorization by learning with context and consistency

Zhiwu Lu, Horace H.S. Ip
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
This paper presents a novel semi-supervised learning method which can make use of intra-image semantic context and inter-image cluster consistency for image categorization with less labeled data.  ...  To develop a graph-based semi-supervised learning approach to image categorization, we incorporate the intra-image semantic context into a kind of spatial Markov kernel which can be used as the affinity  ...  Semi-Supervised Categorization Spatial Markov Kernel To develop a graph-based semi-supervised learning approach to image categorization with less labeled data, we then incorporate the above intra-image  ... 
doi:10.1109/cvpr.2009.5206851 dblp:conf/cvpr/LuI09a fatcat:f223rgnavnerportvhrd6qaxqu

TV ad video categorization with probabilistic latent concept learning

Jinqiao Wang, Lingyu Duan, Lei Xu, Hanqing Lu, Jesse S. Jin
2007 Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07  
A semi-supervised co-training is finally employed to fuse visual and textual features for ad classification.  ...  A bag-of-words representation is proposed to discover ad categories-related latent visual and textual concepts by probabilistic latent semantics analysis (PLSA).  ...  For example, [3] and [4] proposed to learn object categories, and natural scene classification over unlabelled training images using the PLSA model with bag of words.  ... 
doi:10.1145/1290082.1290113 dblp:conf/mir/WangDXLJ07 fatcat:zls6oxtxybczxcehr5paz6yvmi

Action categorization by structural probabilistic latent semantic analysis

Jianguo Zhang, Shaogang Gong
2010 Computer Vision and Image Understanding  
Results show that the proposed approach outperforms the standard pLSA.  ...  In this work, we propose a new approach structural pLSA (SpLSA) to model explicitly word orders by introducing latent variables.  ...  Some degree of manual correction/semi-supervised labeling is needed.  ... 
doi:10.1016/j.cviu.2010.04.006 fatcat:swrrkvuz4za6hh2bbnklb2msmq

Multi-view learning via probabilistic latent semantic analysis

Fuzhen Zhuang, George Karypis, Xia Ning, Qing He, Zhongzhi Shi
2012 Information Sciences  
Blum and Mitchell [3] initiated the idea of co-training for semi-supervised classification.  ...  classification In this subsection, we show how to adapt our model to multi-view semi-supervised classification, i.e., how to incorporate some labeled information to supervise the EM algorithm.  ... 
doi:10.1016/j.ins.2012.02.058 fatcat:yanwaz25y5hh3jrga7vvxwdifi

Automatic audio tag classification via semi-supervised canonical density estimation

Jun Takagi, Yasunori Ohishi, Akisato Kimura, Masashi Sugiyama, Makoto Yamada, Hirokazu Kameoka
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
semi-supervised variant of canonical correlation analysis, and 2) topic models are learned by multi-class extension of semi-supervised kernel density estimation in the topic space.  ...  We propose a novel semi-supervised method for building a statistical model that represents the relationship between sounds and text labels ("tags").  ...  Thus, we introduce an idea of semi-supervised KDE [16] used for discrimination tasks, and extend it to multi-label classification.  ... 
doi:10.1109/icassp.2011.5946925 dblp:conf/icassp/TakagiOKSYK11 fatcat:5xol6vom35hwtmsel6zir442li

A Thousand Words in a Scene

Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Daniel Gatica-Perez, Tinne Tuytelaars
2007 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Finally, through aspect-based image ranking experiments, we show the ability of PLSA to automatically extract visually meaningful scene patterns, making such representation useful for browsing image collections  ...  We also show that Probabilistic Latent Semantic Analysis (PLSA) generates a compact scene representation, discriminative for accurate classification, and more robust than the bag-of-visterms representation  ...  Alternatively, Lim and Jin [18] successfully used the soft output of semi-supervised regional concept detectors in an image indexing and retrieval application.  ... 
doi:10.1109/tpami.2007.1155 pmid:17627045 fatcat:cydaugboi5gpbmod7zza7qw3gi

Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

Obed Tettey Nartey, Guowu Yang, Sarpong Kwadwo Asare, Jinzhao Wu, Lady Nadia Frempong
2020 Sensors  
In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data.  ...  Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms.  ...  Comparison of the classification accuracy of our approach and some semi-supervised methods on the GTSRB.  ... 
doi:10.3390/s20092684 pmid:32397197 pmcid:PMC7248915 fatcat:mnrq4g25ungxhjwju7dztagkx4

Automatic Image Annotation with Relevance Feedback and Latent Semantic Analysis [chapter]

Donn Morrison, Stéphane Marchand-Maillet, Eric Bruno
2008 Lecture Notes in Computer Science  
We demonstrate how automatic annotation of images can be implemented on partially annotated databases by learning imageconcept relationships from positive examples via inter-query learning.  ...  The goal of this paper is to study the image-concept relationship as it pertains to image annotation.  ...  User intervention is relied upon in a clustering approach in [2] where the authors employ similarity methods with semi-supervised fuzzy clustering for semi-automatic image annotation.  ... 
doi:10.1007/978-3-540-79860-6_6 fatcat:l5y7ly5jhrdxflr4r6v4dwhkqm

Which is the best way to organize/classify images by content?

Anna Bosch, Xavier Muñoz, Robert Martí
2007 Image and Vision Computing  
Scene classification, the classification of images into semantic categories (e.g. coast, mountains and streets), is a challenging and important problem nowadays.  ...  Thousands of images are generated every day, which implies the necessity to classify, organise and access them using an easy, faster and efficient way.  ...  Acknowledgements We thank Julia Vogel, for providing their image data and corresponding ground-truth. This work was partially funded by research grant BR03/01 from the University of Girona.  ... 
doi:10.1016/j.imavis.2006.07.015 fatcat:jicc44pv5ffa7csqzkkqhmoo4m
« Previous Showing results 1 — 15 out of 246 results