Showing papers by "Liqing Zhang published in 2015"

Bayesian CP Factorization of Incomplete Tensors with Automatic Rank Determination

Abstract: CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors. The existing CP algorithms require the tensor rank to be manually specified, however, the determination of tensor rank remains a challenging problem especially for CP rank . In addition, existing approaches do not take into account uncertainty information of latent factors, as well as missing entries. To address these issues, we formulate CP factorization using a hierarchical probabilistic model and employ a fully Bayesian treatment by incorporating a sparsity-inducing prior over multiple latent factors and the appropriate hyperpriors over all hyperparameters, resulting in automatic rank determination. To learn the model, we develop an efficient deterministic Bayesian inference algorithm, which scales linearly with data size. Our method is characterized as a tuning parameter-free approach, which can effectively infer underlying multilinear factors with a low-rank constraint, while also providing predictive distributions over missing entries. Extensive simulations on synthetic data illustrate the intrinsic capability of our method to recover the ground-truth of CP rank and prevent the overfitting problem, even when a large amount of entries are missing. Moreover, the results from real-world applications, including image inpainting and facial image synthesis, demonstrate that our method outperforms state-of-the-art approaches for both tensor factorization and tensor completion in terms of predictive performance.

Bayesian Sparse Tucker Models for Dimension Reduction and Tensor Completion.

Abstract: Tucker decomposition is the cornerstone of modern machine learning on tensorial data analysis, which have attracted considerable attention for multiway feature extraction, compressive sensing, and tensor completion. The most challenging problem is related to determination of model complexity (i.e., multilinear rank), especially when noise and missing data are present. In addition, existing methods cannot take into account uncertainty information of latent factors, resulting in low generalization performance. To address these issues, we present a class of probabilistic generative Tucker models for tensor decomposition and completion with structural sparsity over multilinear latent space. To exploit structural sparse modeling, we introduce two group sparsity inducing priors by hierarchial representation of Laplace and Student-t distributions, which facilitates fully posterior inference. For model learning, we derived variational Bayesian inferences over all model (hyper)parameters, and developed efficient and scalable algorithms based on multilinear operations. Our methods can automatically adapt model complexity and infer an optimal multilinear rank by the principle of maximum lower bound of model evidence. Experimental results and comparisons on synthetic, chemometrics and neuroimaging data demonstrate remarkable performance of our models for recovering ground-truth of multilinear rank and missing entries.

Object proposal by multi-branch hierarchical segmentation

Abstract: Hierarchical segmentation based object proposal methods have become an important step in modern object detection paradigm. However, standard single-way hierarchical methods are fundamentally flawed in that the errors in early steps cannot be corrected and accumulate. In this work, we propose a novel multi-branch hierarchical segmentation approach that alleviates such problems by learning multiple merging strategies in each step in a complementary manner, such that errors in one merging strategy could be corrected by the others. Our approach achieves the state-of-the-art performance for both object proposal and object detection tasks, comparing to previous object proposal methods.

Sketch-based Image Retrieval via Shape Words

Abstract: The explosive growth of touch screens has provided a good platform for sketch-based image retrieval However, most previous works focused on low level descriptors of shapes and sketches In this paper, we try to step forward and propose to leverage shape words descriptor for sketch-based image retrieval First, the shape words are defined and an efficient algorithm is designed for shape words extraction Then we generalize the classic Chamfer Matching algorithm to address the shape words matching problem Finally, a novel inverted index structure is proposed to make shape words representation scalable to large scale image databases Experimental results show that our method achieves competitive accuracy but requires much less memory, eg, less than 3% of memory storage of MindFinder Due to its competitive accuracy and low memory cost, our method can scale up to much larger database

Uncorrelated multiway discriminant analysis for motor imagery EEG classification.

Abstract: Motor imagery-based brain-computer interfaces (BCIs) training has been proved to be an effective communication system between human brain and external devices. A practical problem in BCI-based systems is how to correctly and efficiently identify and extract subject-specific features from the blurred scalp electroencephalography (EEG) and translate those features into device commands in order to control external devices. In real BCI-based applications, we usually define frequency bands and channels configuration that related to brain activities beforehand. However, a steady configuration usually loses effects due to individual variability among different subjects in practical applications. In this study, a robust tensor-based method is proposed for a multiway discriminative subspace extraction from tensor-represented EEG data, which performs well in motor imagery EEG classification without the prior neurophysiologic knowledge like channels configuration and active frequency bands. Motor imagery EEG patterns in spatial-spectral-temporal domain are detected directly from the multidimensional EEG, which may provide insights to the underlying cortical activity patterns. Extensive experiment comparisons have been performed on a benchmark dataset from the famous BCI competition III as well as self-acquired data from healthy subjects and stroke patients. The experimental results demonstrate the superior performance of the proposed method over the contemporary methods.

Offline sketch parsing via shapeness estimation

Abstract: In this work, we target at the problem of offline sketch parsing, in which the temporal orders of strokes are unavailable. It is more challenging than most of existing work, which usually leverages the temporal information to reduce the search space. Different from traditional approaches in which thousands of candidate groups are selected for recognition, we propose the idea of shapeness estimation to greatly reduce this number in a very fast way. Based on the observation that most of hand-drawn shapes with well-defined closed boundaries can be clearly differentiated from nonshapes if normalized into a very small size, we propose an efficient shapeness estimation method. A compact feature representation as well as its efficient extraction method is also proposed to speed up this process. Based on the proposed shapeness estimation, we present a three-stage cascade framework for offline sketch parsing. The shapeness estimation technique in this framework greatly reduces the number of false positives, resulting in a 96.2% detection rate with only 32 candidate group proposals, which is two orders of magnitude less than existing methods. Extensive experiments show the superiority of the proposed framework over stateof-the-art works on sketch parsing in both effectiveness and efficiency, even though they leveraged the temporal information of strok.

Abnormal Event Detection Using Recurrent Neural Network

Abstract: In this paper, we introduce a simple but novel model to detect abnormal event in surveillance video using sparse autoencoder and recurrent neuron network. In this model, we first train a sparse autoencoder to extract features and use a sequence of temporal continuous features to train a recurrent neuron network to predict the subsequent features. We classify the frame as normal and abnormal based on the prediction error of recurrent neuron network. Experimental result on a crowd activity dataset verifies the effectiveness of our model and the implication of recurrent neural networks in abnormal detection is also discussed.

Separation and Recognition of Electroencephalogram Patterns Using Temporal Independent Component Analysis

Abstract: A common problem in Electroencephalogram (EEG) analysis is how to separate EEG patterns from noisy recordings. Independent component analysis (ICA), which is an effective method to recover independent sources from sensor outputs without assuming any a priori knowledge, has been widely used in such biological signals analysis. However, when dealing with EEG signals, the mixing model usually does not satisfy the standard ICA assumptions due to the time-variable structures of source signals. In this case, EEG patterns should be precisely separated and recognized in a short time window. Another issue is that we usually over-separate the signals by ICA due to the over learning problem when the length of data is not sufficient. In order to tackle these problems mentioned above, we try to exploit both high order statistics and temporal structures of source signals under condition of short time windows. We utilize a temporal-independent component analysis (tICA) method to formulate the blind separation problem into a new framework of analyzing the mutual independence of the residual signals. Furthermore, in order to find better features for classification, both temporal and spatial features of EEG recordings are extracted by integrating tICA together with some other algorithm like Common Spatial Pattern (CSP) for feature extraction. Computer simulations are given to evaluate the efficiency and performance of tICA based on EEG data recorded not from the normal people but from some special populations suffering from neurophysiological diseases like stroke. To the best of our knowledge, this is the first time that EEG characteristics of stroke patients are explored and reported using ICA algorithm. Superior separation performance and high classification rate evidence that the tICA method is promising for EEG analysis.

PPTLens: Create Digital Objects with Sketch Images

Abstract: In this work, we introduce the PPTLens system to convert sketch images captured by smart phones to digital flowcharts in PowerPoint. Different from existing sketch recognition system, which is based on hand-drawn strokes, PPTLens enables users to use sketch images as inputs directly. It's more challenging since strokes extracted from sketch images might not only be very messy, but also without temporal information of the drawings. To implement the 'Image to Object' (I2O) scenario, we propose a novel sketch image recognition framework, including an effective stroke extraction strategy and a novel offline sketch parsing algorithm. By enabling sketch images as inputs, our system makes flowchart/diagram production much more convenient and easier.

Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding

Abstract: This paper presents a novel image denoising framework using overcomplete topographic model. To adapt to the statistics of natural images, we impose both spareseness and topograpgic constraints on the denoising model. Based on the overcomplete topographic model, our denoising system improves the previous work on the following aspects: multi-category based sparse coding, adaptive learning, local normalization, lasso shrinkage function, and subset selection. A large number of simulations have been performed to show the performance of the modified model, demonstrating that the proposed model achieves better denoising performance.

Content Based Image Search for Clothing Recommendations in E-Commerce

Abstract: A number of algorithms exist in measuring clothing similarity for clothing recommendations in E-commerce. The clothing similarity mostly depends on its shape, texture and style. In this paper we introduce three models of defining feature space for clothing recommendations. The sketch-based image search mainly focuses on defining similarity of clothing in contour dimension. The spatial bag-of-feature approach is employed to measure the clothing similarity of local image patterns. Finally, we introduce a query adaptive shape model which combines shape characteristics and labels of clothing, in order to take the semantic information of clothing. A large number of simulations are given to show the feasibility and performance of the clothing recommendations by using content-based image search.

IdeaPanel: A Large Scale Interactive Sketch-based Image Search System

Abstract: In this work, we introduce the IdeaPanel system, an interactive sketch-based image search engine with millions of images. IdeaPanel enables users to sketch the target image in their minds and also supports tagging to describe their intentions. After a search is triggered, similar images will be returned in real time, based on which users can interactively refine their query sketches until ideal images are returned. Different from existing work, most of which requires a huge amount of memory for indexing and matching, IdeaPanel can achieve very competitive performance but requires much less memory storage. IdeaPanel needs only about 240MB memory to index 1.3M images (less than 3% of previous MindFinder system). Due to its high accuracy and low memory cost, IdealPanel can scale up to much larger database and thus has larger potential to return the most desired images for users.