Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

State-of-the-art in artificial neural network applications: A survey

Traditional and recent approaches in background modeling for foreground detection: An overview

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also review the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

Recent Advances in Open Set Recognition: A Survey

In this paper, we propose a clustering-based online news topic detection and tracking (TDT) approach based on hierarchical Bayesian nonparametric framework that allows topics to be shared across different news stories in a corpus. Our approach is formulated using the hierarchical Pitman-Yor process mixture model with the inverted Beta-Liouville (IBL) distribution as its component density, which has shown superior performance in modeling text data than the widely used Gaussian distribution. Moreover, we theoretically develop a convergence-guaranteed online learning algorithm that can effectively learn the proposed TDT model from a stream of news stories based on varational Bayes. The merits of our TDT approach are illustrated by comparing it with other well-defined clustering-based TDT approaches on different news data sets.

Clustering-Based Online News Topic Detection and Tracking Through Hierarchical Bayesian Nonparametric Models

In this paper, we propose an unsupervised video object segmentation approach which is mainly based on a saliency detection method and the Gaussian mixture model with Markov random field. In our approach, the saliency detection method is developed as a preprocessing technique to calculate the probability of each pixel as the target object. In contrast to traditional saliency detection methods which are normally difficult to obtain the object’s precise boundary and are therefore hard to segment consistent objects, the developed saliency detection method can calculate the saliency of each frame in the video sequence and extract the position and region of the target object with more accurate object boundary. The refined extracted object region is then taken as the prior information and incorporated into the Gaussian mixture model with Markov random field to obtain the precise pixel-wise segmentation result of each frame. The effectiveness of the proposed unsupervised video object segmentation approach is validated through experimental results using both the SegTrack and the SegTrack v2 data sets.

Unsupervised Video Object Segmentation Based on Mixture Models and Saliency Detection

Online variational learning of finite inverted Beta‐Liouville mixture model for biomedical analysis

Video background subtraction is an essential task in computer vision for detecting moving objects in video sequences. In this paper, we propose a novel Bayesian nonparametric statistical approach to subtract video background. The proposed approach is based on a mixture of Dirichlet processes with Dirichlet distributions, which can be considered as an infinite Dirichlet mixture model. Compared to other background subtraction approaches, the proposed one has the advantages that it is more robust and adaptive to dynamic background, and it has the ability to handel multi-modal background distributions. Moreover, thanks to the nature of nonparametric Bayesian models, the determination of the correct number of components is sidestepped by assuming that there is an infinite number of components. Our results demonstrate the merits of the proposed approach.

Video background subtraction using online infinite dirichlet mixture models

Video texture is a new type of medium which can provide a continuous, infinitely varying stream of video images from a recorded video clip. It can be synthesized by rearranging the order of frames based on the similarities between all pairs of frames. In this paper, we propose a new method for generating video textures by implementing probabilistic principal components analysis (PPCA) and Gaussian Process Dynamical model (GPDM). Compared to the original video texture technique, video texture synthesized by PPCA and GPDM has the following advantages: it might generate new video frames that have never existed in the input video clip before; the problem of "dead-end" is totally avoided; it could also provide video textures that are more robust to noise.

/pdf/generating-video-textures-by-ppca-and-gaussian-process-589tsl8sgq.pdf

Wentao Fan

Papers

Clustering-Based Online News Topic Detection and Tracking Through Hierarchical Bayesian Nonparametric Models

Unsupervised Video Object Segmentation Based on Mixture Models and Saliency Detection

Online variational learning of finite inverted Beta‐Liouville mixture model for biomedical analysis

Video background subtraction using online infinite dirichlet mixture models

Generating Video Textures by PPCA and Gaussian Process Dynamical Model