5,319 Hits in 6.1 sec

Directed Graph Learning via High-Order Co-linkage Analysis [chapter]

Hua Wang, Chris Ding, Heng Huang
2010 Lecture Notes in Computer Science  
On the induced undirected graph, we use a Green's function approach to solve the semi-supervised learning problem. We present a new zero-mode free Laplacian which is invertible.  ...  This leads to an Improved Green's Function (IGF) method to solve the classification problem, which is also extended to deal with multi-label classification problems.  ...  Semi-supervised Learning via Improved Green's Function Method With the symmetric CA similarity induced from a directed graph, we may use any existing graph-based semi-supervised learning algorithm for  ... 
doi:10.1007/978-3-642-15939-8_29 fatcat:dicxad3nkvanvjrwwkj6wfx6re

Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition [article]

Xuesong Niu and Hu Han and Shiguang Shan and Xilin Chen
2020 arXiv   pre-print
Unlike traditional co-training methods that require provided multi-view features and model re-training, we propose a novel co-training method, namely multi-label co-regularization, for semi-supervised  ...  In this work, we propose a semi-supervised approach for AU recognition utilizing a large number of web face images without AU labels and a relatively small face dataset with AU annotations inspired by  ...  generation and AU classification via multi-view loss and multilabel co-regularization loss.  ... 
arXiv:1910.11012v2 fatcat:e3dkdghbhrggpl2s6dc2m7n6ze

Graph based multi-modality learning

Hanghang Tong, Jingrui He, Mingjing Li, Changshui Zhang, Wei-Ying Ma
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
in every graph as well as supervision information (if available).  ...  For semi-supervised learning, two different fusion schemes, namely linear form and sequential form, are proposed.  ...  GRAPH BASED SEMI-SUPERVISED LEARNING IN MULTI-MODALITY First, we address the graph based semi-supervised learning in multi-modality, including classification and retrieval in the scenario of QBK.  ... 
doi:10.1145/1101149.1101337 dblp:conf/mm/TongHLZM05 fatcat:ux2tzibo6nbfrhr3pca2hxme6m

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Learning for Image Classification Improving Web Image Search Results using Query-relative Classifiers Vezhnevets, Alexander Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance  ...  Graph Cuts Li, Hanxi Rapid Face Recognition Using Hashing Li, Hongdong Support Vector Regression for Multi-View Gait Recognition based on Local Motion Feature Selection Multi-View Structure Computation  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Image Categorization Using Directed Graphs [chapter]

Hua Wang, Heng Huang, Chris Ding
2010 Lecture Notes in Computer Science  
Most existing graph-based semi-supervised classification methods use pairwise similarities as edge weights of an undirected graph with images as the nodes of the graph.  ...  We apply this new co-linkage similarity in two important computer vision tasks for image categorization: object recognition and image annotation.  ...  Because image annotation is a multi-label classification task, we use multi-label correlated Green's function (MCGF) method [16] for classification, which is an extension of the Green's function semi-supervised  ... 
doi:10.1007/978-3-642-15558-1_55 fatcat:ns4i7uus7vhnlb72btvzf6kzim

Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning

Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng, Ebroul Izquierdo, Liang Lin
2017 IEEE transactions on circuits and systems for video technology (Print)  
images, which boosts image classification performance and achieves promising results compared to other semi-supervised learning methods.  ...  Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS).  ...  Mult-view Learning (MVL) Multi-view learning is a family of learning algorithms deriving from Co-Training [22] , and focuses on exploiting data with multi-representation.  ... 
doi:10.1109/tcsvt.2017.2710478 fatcat:uor66op47ngyvdam6xfjq4x6ny

Joint consensus and diversity for multi-view semi-supervised classification

Wenzhang Zhuge, Chenping Hou, Shaoliang Peng, Dongyun Yi
2019 Machine Learning  
Considering the high price of labeling data in many machine learning applications, we focus on multi-view semi-supervised classification problem.  ...  To address this problem, in this paper, we propose a method called joint consensus and diversity for multi-view semi-supervised classification, which learns a common label matrix for all training samples  ...  Multi-view semi-supervised classification via adaptive regression The multi-view semi-supervised classification via adaptive regression (MVAR) is a regression-based semi-supervised algorithm .  ... 
doi:10.1007/s10994-019-05844-9 fatcat:ocvcl4cb4bau5hwaaxj4v4knna

Special issue on contextual vision computing

Richang Hong, Qi Tian, Nicu Sebe
2014 Machine Vision and Applications  
By virtue of that, web images and videos are generally accompanied by user-contributed contextual information such as tags, comments, etc.  ...  These papers focus on the image representation, classification and local semantic analysis by directly leveraging user-generated context information. In the first paper,  ...  They claim that the web multimedia resources can be considered as multi-view data among which the complementary information and the supervision from the partially label information are used to learn the  ... 
doi:10.1007/s00138-014-0618-1 fatcat:qt7qfz5tk5c3lctgqbnpywr6iy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 265-276 Multi-View Image Classification With Visual, Semantic and View Consistency.  ...  Huang, Z., +, TIP 2020 2066-2077 Semi-Supervised Deep Coupled Ensemble Learning With Classification Landmark Exploration.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Cross-Modal Learning via Pairwise Constraints [article]

Ran He and Man Zhang and Liang Wang and Ye Ji and Qiyue Yin
2014 arXiv   pre-print
In multimedia applications, the text and image components in a web document form a pairwise constraint that potentially indicates the same semantic concept.  ...  This paper studies cross-modal learning via the pairwise constraint, and aims to find the common structure hidden in different modalities.  ...  [20] [21] presented co-training and co-regularized approaches for multi-view spectral clustering respectively.  ... 
arXiv:1411.7798v1 fatcat:pp77pnvwmvftnkrwql5gu4my34

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Zou, W., +, TIP 2021 4084-4098 Dexterous manipulators Embedding Regularizer Learning for Multi-View Semi-Supervised Classification. Huang, A., +, TIP 2021 6997-7011 -degree Images.  ...  Li, Y., +, TIP 2021 1354-1368 Multi-View Feature Selection for PolSAR Image Classification via l 2 , 1 Spar-sity Regularization and Manifold Regularization.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Action and Event Recognition in Videos by Learning From Heterogeneous Web Sources

Li Niu, Xinxing Xu, Lin Chen, Lixin Duan, Dong Xu
2017 IEEE Transactions on Neural Networks and Learning Systems  
Objectbased Multiple Foreground Video Co-segmentation via Multistate Selection Graph. IEEE Transactions on Image Processing, 24(11), 3415-3424.  ...  Semi-Supervised Heterogeneous Fusion for Multimedia Data Co-clustering. IEEE Transactions On Knowledge And Data Engineering, 26(9), 2293-2306.  ... 
doi:10.1109/tnnls.2016.2518700 pmid:26978834 fatcat:ez6dptqrmbcjfjiqpmp56qetdu

Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes [chapter]

Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta
2012 Lecture Notes in Computer Science  
We consider the problem of semi-supervised bootstrap learning for scene categorization.  ...  The goal of this paper is to exploit these relationships and constrain the semi-supervised learning problem.  ...  The key contributions of our paper are: (a) a semi-supervised image classification framework which jointly learns multiple classifiers, (b) demonstrating that sharing information across categories via  ... 
doi:10.1007/978-3-642-33712-3_27 fatcat:sba532lngzff5opk33zugijy4i

Multi-view learning overview: Recent progress and new challenges

Jing Zhao, Xijiong Xie, Xin Xu, Shiliang Sun
2017 Information Fusion  
Since the last survey of multi-view machine learning in early 2013, multi-view learning has made great progress and developments in recent years, and is facing new challenges.  ...  Multi-view learning is an emerging direction in machine learning which considers learning with multiple views to improve the generalization performance.  ...  clustering multi-view supervised learning multi-view semi-supervised learning margin consistency MVMED [10] SMVMED [12] MED-2C [13] multi-view classification categories and applications under different  ... 
doi:10.1016/j.inffus.2017.02.007 fatcat:6we7lm2buncftg7xzym63ncxmy

A Reconstruction Error Formulation for Semi-Supervised Multi-task and Multi-view Learning [article]

Buyue Qian, Xiang Wang, Ian Davidson
2012 arXiv   pre-print
While other work has addressed each of these problems separately, in this paper we show how to address them together, namely semi-supervised dimension reduction for multi-task and multi-view learning (  ...  SSDR-MML), which performs optimization for dimension reduction and label inference in semi-supervised setting.  ...  We propose such a framework which we refer to as semi-supervised dimension reduction for multi-task and multi-view learning (SSDR-MML).  ... 
arXiv:1202.0855v1 fatcat:kagfqlq7dbgahhvmwsfp4difue
« Previous Showing results 1 — 15 out of 5,319 results