Book section · January 1, 2026
While multimodal medical image segmentation improves accuracy via complementary information, real-world constraints often result in incomplete modality inputs, posing a major challenge to robust segmentation. This work addresses the most constrained single ...
Full textCite
Book section · January 1, 2026
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled substances and t ...
Full textCite
Book section · January 1, 2024
In the era of the Internet of Things (IoT), the retrieval of relevant medical information has become essential for efficient clinical decision-making. This paper introduces MedFusionRank, a novel approach to zero-shot medical information retrieval (MIR) th ...
Full textCite
Book section · January 1, 2024
Character string recognition (CSR) has drawn much attention for document intelligence, but its performance is limited by the pre-defined character set without the ability to recognize new characters. To overcome this issue, class incremental learning (CIL) ...
Full textCite
Book section · January 1, 2024
Document dewarping has made great progress in recent years, however it usually requires huge document pairs with pixel-level annotation to learn a mapping function. Although photographed document images are easy to obtain, the pixel-level annotation betwee ...
Full textCite
Book section · January 1, 2020
CDMC-International Cybersecurity Data Mining Competition (http://www.csmining.org) is a world unique data-analytic competition sitting in the trans-disciplinary area of artificial intelligence and cybersecurity. In this paper, we summarize CDMC’19—the 10th ...
Full textCite
Book section · January 1, 2020
In this paper, we are aiming for a general reference-based super-resolution setting: it does not require the low-resolution image and the high-resolution reference image to be well aligned or with a similar texture. Instead, we only intend to transfer the ...
Full textCite
Book section · January 1, 2020
Image caption aims to generate a description of an image by using techniques of computer vision and natural language processing, where the framework of Convolutional Neural Networks (CNN) followed by Recurrent Neural Networks (RNN) or particularly LSTM, is ...
Full textCite
Book section · January 1, 2020
Scene text recognition with irregular layouts is a challenging yet important problem in computer vision. One widely used method is to employ a rectification network before the recognition stage. However, most previous rectification methods either did not c ...
Full textCite
Book section · January 1, 2020
Few-shot classification aims to learn novel categories by giving few labeled samples. How to make best use of the limited data to obtain a learner with fast learning ability has become a challenging problem. In this paper, we propose a feature redirection ...
Full textCite
Book section · January 1, 2020
Fine-grained image classification is used to identify dozens or hundreds of subcategory images which are classified in a same large category. This task is challenging due to the subtle inter-class visual differences. Most existing methods try to locate dis ...
Full textCite
Book section · January 1, 2020
Image-to-image translation aims to change attributes or domains of images, where the feature disentanglement based method is widely used recently due to its feasibility and effectiveness. In this method, a feature extractor is usually integrated in the enc ...
Full textCite
Book section · January 1, 2020
Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have no the attention ...
Full textCite
Book section · January 1, 2020
In pattern recognition, automatic handwriting recognition (AHWR) is an area of research that has developed rapidly in the last few years. It can play a significant role in broad-spectrum of applications rending from, bank cheque processing, application for ...
Full textCite
Book section · January 1, 2020
Zero-shot learning (ZSL), i.e. classifying patterns where there is a lack of labeled training data, is a challenging yet important research topic. One of the most common ideas for ZSL is to map the data (e.g., images) and semantic attributes to the same em ...
Full textCite
Book section · January 1, 2020
Human has well demonstrated its cognitive consistency over image transformations such as flipping and scaling. In order to learn from human’s visual perception consistency, researchers find out that convolutional neural network’s capacity of discernment ca ...
Full textCite
Book section · January 1, 2019
Recurrent neural networks (RNNs) are powerful models for sequence learning. However, the training of RNNs is complicated because the internal covariate shift problem, where the input distribution at each iteration changes during the training as the paramet ...
Full textCite
Book section · January 1, 2018
Due to the huge category number, the sophisticated combinations of various strokes and radicals, and the free writing or printing styles, generating Chinese characters with diverse styles is always considered as a difficult task. In this paper, an efficien ...
Full textCite
Book section · January 1, 2018
In this paper, we present a novel training strategy using kernelized Min-Max objective to enable improved object recognition performance on deep neural networks (DNN), e.g., convolutional neural networks (CNN). Without changing the other part of the origin ...
Full textCite
Book section · January 1, 2018
Breathtaking improvement has been seen with the recently proposed deep Generative Adversarial Network (GAN). Purposes of most existing GAN-based models majorly concentrate on generating realistic and vivid patterns by a pattern generator with the aid of th ...
Full textCite
Book section · January 1, 2018
Despite the great success of graph-based transductive learning methods, most of them have serious problems in scalability and robustness. In this chapter, we propose an efficient and robust graph-based transductive classification method, called minimum tre ...
Cite
Book section · January 1, 2018
Conventional predictors often regard input samples as identically and independently distributed (i.i.d.). Such an assumption does not always hold in many real scenarios, especially when patterns occur as groups, where each group shares a homogeneous style. ...
Cite
Book section · January 1, 2017
We propose a novel approach capable of embedding the unsupervised objective into hidden layers of the deep neural network (DNN) for preserving important unsupervised information. To this end, we exploit a very simple yet effective unsupervised method, i.e. ...
Full textCite
Book section · January 1, 2017
In regression tasks for static data, existing methods often assume that they were generated from an identical and independent distribution (i.i.d.). However, violation can be found when input samples may form groups, each affected by a certain different do ...
Full textCite
Book section · January 1, 2017
In this paper, we propose a novel deep density model, called Deep Mixtures of Factor Analyzers with Common Loadings (DMCFA). Employing a mixture of factor analyzers sharing common component loadings, this novel model is more physically meaningful, since th ...
Full textCite
Book section · December 1, 2016
Entity search is a new application meeting either precise or vague requirements from the search engines users. Baidu Cup 2016 Challenge just provided such a chance to tackle the problem of the entity search. We achieved the first place with the average MAP ...
Full textCite
Book section · January 1, 2016
Neural Networks (NN) have achieved great success in pattern recognition and machine learning. However, the success of NNs usually relies on a sufficiently large number of samples. When fed with limited data, NN’s performance may be degraded significantly. ...
Full textCite
Book section · January 1, 2016
This paper reviews the state of the art techniques for designing next generation CDSSs. CDSS can aid physicians and radiologists to better analyse and treat patients by combining their respective clinical expertise with complementary capabilities of the co ...
Full textCite
Book section · January 1, 2016
Non-negative Matrix Factorization (NMF) has been widely exploited to learn latent features from data. However, previous NMF models often assume a fixed number of features, say p features, where p is simply searched by experiments. Moreover, it is even diff ...
Full textCite
Book section · January 1, 2015
Hybrid algorithms play a prominent role in improving the search capability of algorithms. Hybridization aims to combine the advantages of each algorithm to form a hybrid algorithm, while simultaneously trying to minimize any substantial disadvantage. In ge ...
Full textCite
Book section · January 1, 2015
In recent years, deep learning has attracted much interest for addressing complex AI tasks. However, most of the deep learning models need to be trained for a long time in order to obtain good results. To overcome this problem, the deep convolutional activ ...
Full textCite
Book section · January 1, 2014
Over last fifty years, Neural Networks (NN) have been important and active models in machine learning and pattern recognition. Among different types of NNs, Back Propagation (BP) NN is one popular model, widely exploited in various applications. Recently, ...
Full textCite
Book section · January 1, 2014
Text categorization (TC), has many typical traits, such as large and difficult category taxonomies, noise and incremental data, etc. Random Forests, one of the most important but simple state-of-the-art ensemble methods, has been used to solve such type of ...
Full textCite
Book section · January 1, 2014
Dimensionality reduction is a fundamental yet active research topic in pattern recognition and machine learning. On the other hand, Gaussian Mixture Model (GMM), a famous model, has been widely used in various applications, e.g., clustering and classificat ...
Full textCite
Book section · December 1, 2013
Imbalanced learning is a challenged task in machine learning, where the data associated with one class are far fewer than those associated with the other class. In this paper, we propose a novel model called One-Side Probability Machine (OSPM) able to lear ...
Full textCite
Book section · December 1, 2013
Classifier ensemble is an active topic for learning from non-stationary data. In particular, batch growing ensemble methods present one important direction for dealing with concept drift involved in non-stationary data. However, current batch growing ensem ...
Full textCite
Book section · January 1, 2013
The k nearest neighbors (kNN) graph, perhaps the most popular graph in machine learning, plays an essential role for graph-based learning methods. Despite its many elegant properties, the brute force kNN graph construction method has computational complexi ...
Full textCite
Book section · December 1, 2012
This chapter presents a novel manifold learning algorithm, named Local Tangent Space Laplacian Eigenmaps (LTSLE). The theoretical framework of LTSLE is based on a local tangent space theorem, which is also delivered in this chapter. LTSLE ismotivated by th ...
Cite
Book section · November 19, 2012
Multi-task learning (MTL) has drawn a lot of attentions in machine learning. By training multiple tasks simultaneously, information can be better shared across tasks. This leads to significant performance improvement in many problems. However, most existin ...
Full textCite
Book section · November 19, 2012
Classifier ensemble has been intensively studied with the aim of overcoming the limitations of individual classifier components in two prevalent directions, i.e., to diversely generate classifier components, and to sparsely combine multiple classifiers. Cu ...
Full textCite
Book section · November 19, 2012
Multiple Outlooks Learning (MOL) has recently received considerable attentions in machine learning. While traditional classification models often assume patterns are living in a fixed-dimensional vector space, MOL focuses on the tasks involving multiple re ...
Full textCite
Book section · January 1, 2012
Multi-task learning has been widely studied in machine learning due to its capability to improve the performance of multiple related learning problems. However, few researchers have applied it on the important metric learning problem. In this paper, we pro ...
Full textCite
Book section · November 28, 2011
The quadratic discriminant function (QDF) derived from the multivariate Gaussian distribution is effective for classification in many pattern recognition tasks. In particular, a variant of QDF, called MQDF, has achieved great success and is widely recogniz ...
Full textCite
Book section · November 28, 2011
Multi-task learning, referring to the joint training of multiple problems, can usually lead to better performance by exploiting the shared information across all the problems. On the other hand, metric learning, an important research topic, is however ofte ...
Full textCite
Book section · December 21, 2010
In this paper, we present a first study which learns the ECOC matrix as well as dichotomizers simultaneously from data; these two steps are usually conducted independently in previous methods. We formulate our learning model as a sequence of concave-convex ...
Full textCite
Book section · December 1, 2009
In this paper, we investigate the impact of the non-numerical information on exchange rate changes and that of ensemble multiple classifiers on forecasting exchange rate between U.S. dollar and Japanese yen. We first engage the fuzzy comprehensive evaluati ...
Full textCite
Book section · December 1, 2009
Formation Micro Imager (FMI) can directly reflect changes of wall stratum and rock structures. It is also an important method to divide stratum and identify lithology. However, people usually deal with FMI images manually, which is extremely inefficient an ...
Full textCite
Book section · October 27, 2008
Kernel methods have been widely used in data classification. Many kernel-based classifiers like Kernel Support Vector Machines (KSVM) assume that data can be separated by a hyperplane in the feature space. These methods do not consider the data distributio ...
Full textCite
Book section · December 1, 2007
Naive Bayesian network (NB) is a simple yet powerful Bayesian network. Even with a strong independency assumption among the features, it demonstrates competitive performance against other state-of-the-art classifiers, such as support vector machines (SVM). ...
Full textCite
Book section · January 1, 2006
Handwritten Chinese Address Recognition describes a difficult yet important pattern recognition tusk. There are three difficulties in this problem: (1) Handwritten address is often of free styles and of high variations, resulting in inevitable segmentation ...
Full textCite
Book section · January 1, 2004
Recently, the Support Vector Regression (SVR) has been applied in the financial time series prediction. The financial data are usually highly noisy and contain outliers. Detecting outliers and deflating their influence are important but hard problems. In t ...
Full textCite
Book section · January 1, 2003
The Semi-Naive Bayesian network (SNB) classifier, a probabilistic model with an assumption of conditional independence among the combined attributes, shows a good performance in classification tasks. However, the traditional SNBs can only combine two attri ...
Full textCite
