Spectral dimensionality reduction methods have recently emerged as powerful tools for various applications in pattern recognition, data mining and computer vision. These methods use information contained in the eigenvectors of a data affinity (i.e, item-item similarity) matrix to reveal the low dimensional structure of the high dimensional data. One of the limitations of various spectral dimensionality reduction methods is their high computational complexity. They all need to construct a data affinity matrix and compute the top eigenvectors. This leads to O(n2) computational complexity, where n is the number of samples. Moreover, when the data are highly non-linear distributed, some linear methods have to be performed in a reproducing kernel Hilbert space (leads to the corresponding kernel methods) to learn an effective non-linear mapping. The computational complexity of these kernel methods is O(n3). In this paper, we propose a novel nonlinear dimensionality reduction algorithm, called Compressed Spectral Regression, with O(n) computational complexity. Extensive experiments on data clustering demonstrate the effectiveness and efficiency of the proposed approach.

A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maximum entropy principle into IRL and unlike its predecessors, it resolves the ambiguity arising from the fact that a possibly large number of policies could match the expert's behavior. In this paper, we study an AL setting in which in addition to the expert's trajectories,a number of unsupervised trajectories is available. We introduce MESSI,a novel algorithm that combines MaxEnt-IRL with principles coming from semisupervised learning. In particular, MESSI integrates the unsupervised data into the MaxEnt-IRL framework using a pairwise penalty on trajectories. Empirical results in a highway driving and grid-world problems indicate that MESSI is able to take advantage of the unsupervised trajectories and improve the performance of MaxEnt-IRL.

Traditional techniques for monitoring wildlife populations are temporally and spatially limited. Alternatively, in order to quickly and accurately extract information about the current state of the environment, tools for processing and recognition of acoustic signals can be used. In the past, a number of research studies on automatic classification of species through their vocalizations have been undertaken. In many of them, however, the segmentation applied in the preprocessing stage either implies human effort or is insufficiently described to be reproduced. Therefore, it might be unfeasible in real conditions. Particularly, this paper is focused on the extraction of local information as units --called instances-- from audio recordings. The methodology for instance extraction consists in the segmentation carried out using image processing techniques on spectrograms and the estimation of a needed threshold by the Otsu's method. The multiple instance classification (MIC) approach is used for the recognition of the sound units. A public data set was used for the experiments. The proposed unsupervised segmentation method has a practical advantage over the compared supervised method, which requires the training from manually segmented spectrograms. Results show that there is no significant difference between the proposed method and its baseline. Therefore, it is shown that the proposed approach is feasible to design an automatic recognition system of recordings which only requires, as training information, labeled examples of audio recordings.

Clustering has gained widespread use, especially for static data. However, the rapid growth of spatio-temporal data from numerous instruments, such as earth-orbiting satellites, has created a need for spatio-temporal clustering methods to extract and monitor dynamic clusters. Dynamic spatio-temporal clustering faces two major challenges: First, the clusters are dynamic and may change in size, shape, and statistical properties over time. Second, numerous spatio-temporal data are incomplete, noisy, heterogeneous, and highly variable (over space and time). We propose a new spatio-temporal data mining paradigm, to autonomously identify dynamic spatio-temporal clusters in the presence of noise and missing data. Our proposed approach is more robust than traditional clustering and image segmentation techniques in the case of dynamic patterns, non-stationary, heterogeneity, and missing data. We demonstrate our method's performance on a real-world application of monitoring in-land water bodies on a global scale.

Aesthetic evaluation of Chinese calligraphy is one of the most challenging tasks in Artificial Intelligence. This paper attempts to solve this problem by proposing a number of aesthetic feature representations and feeding them into Artificial Neural Networks. Specifically, 22 global shape features are presented to describe a given handwritten Chinese character from different aspects according to classical calligraphic rules, and a new 10-dimensional feature vector is introduced to represent the component layout information using sparse coding. Moreover, a Chinese Handwriting Aesthetic Evaluation Database (CHAED) is also built by collecting 1000 Chinese handwriting images with diverse aesthetic qualities and inviting 33 subjects to evaluate the aesthetic quality for each calligraphic image. Finally, back propagation neural networks are constructed with the concatenation of the proposed features as input and then trained on our CHAED database for the aesthetic evaluation of Chinese calligraphy. Experimental results demonstrate that the proposed AI system provides a comparable performance with human evaluation. Through our experiments, we also compare the importance of each individual feature and reveal the relationship between our aesthetic features and the aesthetic perceptions of human beings.

Abstract artists use non-figurative elements (i.e. colours, lines, shapes, and textures) to convey emotions and often rely on the titles of their various compositions to generate (or enhance) an emotional reaction in the audience. Several psychological works observed that the metadata (i.e., titles, description and/or artist statements) associated with paintings increase the understanding and the aesthetic appreciation of artworks. In this paper we explore if the same metadata could facilitate the computational analysis of artworks, and reveal what kind of emotional responses they awake. To this end, we employ computer vision and sentiment analysis to learn statistical patterns associated with positive and negative emotions on abstract paintings. We propose a multimodal approach which combines both visual and metadata features in order to improve the machine performance. In particular, we propose a novel joint flexible Schatten p-norm model which can exploit the sharing patterns between visual and textual information for abstract painting emotion analysis. Moreover, we conduct a qualitative analysis on the cases in which metadata help improving the machine performance.

Many e-commerce systems allow users to express their opinions towards products through user reviews systems. The user generated reviews not only help other users to gain a more insightful view of the products, but also help online businesses to make targeted improvements on the products or services. Besides, they compose the key component of various personalized recommender systems. However, the existence of spam user accounts in the review systems introduce unfavourable disturbances into personalized recommendation by promoting or degrading targeted items intentionally through fraudulent reviews. Previous shilling attack detection algorithms usually deal with a specific kind of attacking strategy, and are exhausted to handle with the continuously emerging new cheating methods. In this work, we propose to conduct shilling attack detection for more informed recommendation by fraudulent action propagation on the reviews themselves, without caring about the specific underlying cheating strategy, which allows us a unified and flexible framework to detect the spam users.

Community detection is of crucial importance in understanding structures of complex networks. In many real-world networks, communities naturally overlap since a node usually has multiple community memberships. One popular technique to cope with overlapping community detection is Matrix Factorization (MF). However, existing MF-based models have ignored the fact that besides neighbors, "local non-neighbors" (e.g., my friend's friend but not my direct friend) are helpful when discovering communities. In this paper, we propose a Locality-based Non-negative Matrix Factorization (LNMF) model to refine a preference-based model by incorporating locality into learning objective. We define a subgraph called "k-degree local network" to set a boundary between local non-neighbors and other non-neighbors. By discriminately treating these two class of non-neighbors, our model is able to capture the process of community formation. We propose a fast sampling strategy within the stochastic gradient descent based learning algorithm. We compare our LNMF model with several baseline methods on various real-world networks, including large ones with ground-truth communities. Results show that our model outperforms state-of-the-art approaches.

User interest inference from social networks is a fundamental problem to many applications. It usually exhibits dual-heterogeneities: a user's interests are complementarily and comprehensively reflected by multiple social networks; interests are inter-correlated in a nonuniform way rather than independent to each other. Although great success has been achieved by previous approaches, few of them consider these dual-heterogeneities simultaneously. In this work, we propose a structure-constrained multi-source multi-task learning scheme to co-regularize the source consistency and the tree-guided task relatedness. Meanwhile, it is able to jointly learn the task-sharing and task-specific features. Comprehensive experiments on a real-world dataset validated our scheme. In addition, we have released our dataset to facilitate the research communities.

There are lots of texts appearing in the web every day. This fact enables the amount of texts in the web to explode. Therefore, how to deal with large-scale text collection becomes more and more important. Clustering is a generally acceptable solution for text organization. Via its unsupervised characteristic, users can easily dig the useful information that they desired. However, traditional clustering algorithms can only deal with small-scale text collection. When it enlarges, they lose their performances. The main reason attributes to the high-dimensional vectors generated from texts. Therefore, to cluster texts in large amount, this paper proposes a novel clustering algorithm, where only the features that can represent cluster are preserved in cluster’s vector. In this algorithm, clustering process is separated into two parts. In one part, feature’s weight is fine-tuned to make cluster partition meet an optimization function. In the other part, features are reordered and only the useful features that can represent cluster are kept in cluster’s vector. Experimental results demonstrate that our algorithm obtains high performance on both small-scale and large-scale text collections.