Search

Copyright of China Pulp & Paper Industry is the property of China Pulp & Paper Industry Publishing House and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Software enables researchers and editors todetect and resolve image manipulations andduplications before publication, reducing the riskof printing mistakes or costly investigations whilemaintaining their reputation. Global research Academic papers are the most important medium forintroducing results to the scientific community, soresearchers, editors and publishers have an ethicalobligation to ensure all the data shared is valid. Additionally, duringthe review process, grant committees or peerreview teams can use image integrity software tostreamline reviews, enabling reviewers to checkmore papers in shorter time frames withoutcompromising on the impact factor of the journal. [Extracted from the article]

Researchers at the University of Virginia have developed a computer vision software that can digitize handwritten data from paper anesthesia charts in low-middle income countries. The software uses deep neural networks to identify and assign values to handwritten blood pressure symbols and physiological data. The researchers achieved high levels of accuracy, with the software digitizing checkbox data with over 99% accuracy and blood pressure data with a mean average error of 1.0 and 1.36 mmHg for systolic and diastolic blood pressure respectively. This technology provides improved access to digital data for healthcare practitioners in low-middle income countries. [Extracted from the article]

Features The Vatican's archives contain thousands of manuscripts that are encrypted BEATA MEGYESI strode past the Pontifical Swiss Guards, in their Renaissance-era uniforms. Then there are ciphers that involve translations of letters, for example swapping the first and last letters of every word before you can read the plaintext. Lasry showed that Bourbon used a cipher that is neither polyphonic nor homophonic, but polyhomophonic - in other words, some of its individual cipher symbols can represent several plaintext letters, but equally each plaintext letter can be represented by several different cipher symbols. Megyesi had the opportunity to use the Vatican's encrypted papers for a project with an audacious goal: to fully automate the process of decrypting historical ciphers so that many thousands of otherwise inaccessible letters could finally speak to us from down the centuries. [Extracted from the article]

Video processing requires an increasing amount of buffered data. The paper proposes a multi-line buffer circuit that stores compressed data thus saving logic and power. The lossy compression algorithm provides the output stream with a fixed, decided by the user, delay from the input stream. Further, the amount of memory of the compressed buffer can be designed to trade off the correctness of the output with the logic resources footprint. The circuit is tested in a computer vision processing chain as a binary line buffer for the stream of foreground pixels. The paper also proposes a multi-line buffer circuit that integrates a morphological operation. The latter, when compared against the state of the art and against the proposed multi-line lossy buffer, allows larger saving of logic resources (up to 75%) and power (up to 85%), with reduced penalty on video quality. [ABSTRACT FROM AUTHOR]

This paper provides a review of design approaches towards artificial intelligence (AI) System-on-Chip. AI algorithms have progressed over the past decades from perceptron-based neural network (NN) and neuro-fuzzy (NF) system to today’s deep neural network (DNN) and neuromorphic computing. Recent DNN hardware accelerators focus on energy-efficient integration of digital circuits to realize real-time DNN operation while neuromorphic processors deploy new memory technologies with analog computation for low power consumption. However, different design approaches can be applied to such processor implementation with their pros and cons. This paper reviews from the early processor designs for NN and NF in both mixed-mode and digital implementations to the recent DNN SoC designs that we have proposed for a decade. The former content deals with NN and NF processors used as a functional building block of a machine vision SoC, while the latter concentrates on integration of the whole DNN function. We also provide a discussion on the approaches, and provide perspective on future research directions. [ABSTRACT FROM AUTHOR]

This paper addresses a comparison of architectures for the hardware implementation of Gaussian image pyramids. Main differences between architectural choices are in the sensor front-end. One side is for architectures consisting of a conventional sensor that delivers digital images and which is followed by digital processors. The other side is for architectures employing a non-conventional sensor with per-pixel embedded preprocessing structures for Gaussian spatial filtering. This later choice belongs to the general category of “artificial retina” sensors which have been for long claimed as potentially advantageous for enhancing throughput and reducing energy consumption of vision systems. These advantages are very important in the internet of things context, where imaging systems are constantly exchanging information. This paper attempts to quantify these potential advantages within a design space in which the degrees of freedom are the number and type of ADCs, single-slope, SAR, cyclic, $\Sigma \Delta$ , and pipeline, and the number of digital processors. Results show that speed and energy advantages of preprocessing sensors are not granted by default and are only realized through proper architectural design. The methodology presented for the comparison between focal-plane and digital approaches is a useful tool for imager design, allowing for the assessment of focal-plane processing advantages. [ABSTRACT FROM PUBLISHER]

Approximating a curve with a B-spline is a well-known problem with many challenges. Computing parametric values and knot vector that leads to the best approximation of a point sequence is an open problem. Existing methods are usually based on heuristics, genetic algorithms, or meta-heuristics. Nowadays, Deep Neural Networks have demonstrated their usefulness as shown in the use of a Multi-Layer Perceptron in the existing literature. Since its inception, the Transformer architecture has achieved state-of-the-art in multiple domains, like Natural Language Processing and Computer Vision. In this paper, we propose a method for knot placement that focuses on using a Transformer neural network architecture for B-spline approximation. We present and compare the results of our ongoing experimentations with Transformers for B-spline curve approximation. We conclude with possible improvements and modifications to our method for future experiments. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based pooling method is proposed in this paper. The proposed method is inspired from the bag-of-features model and can be used for learning more lightweight deep neural networks. Trainable radial basis function neurons are used to quantize the activations of the final convolutional layer, reducing the number of parameters in the network and allowing for natively classifying images of various sizes. The proposed method employs differentiable quantization and aggregation layers leading to an end-to-end trainable CNN architecture. Furthermore, a fast linear variant of the proposed method is introduced and discussed, providing new insight for understanding convolutional neural architectures. The ability of the proposed method to reduce the size of CNNs and increase the performance over other competitive methods is demonstrated using seven data sets and three different learning tasks (classification, regression, and retrieval). [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are widely employed in modern computer vision algorithms, where the input image is convolved iteratively by many filters to extract the knowledge behind it. However, while the depth of convolutional layers gets deeper and deeper in recent years, the enormous computational complexity makes it difficult to be deployed on embedded systems with limited hardware resources. In this paper, inspired by rate-distortion optimization in image and video coding, we propose a computation-performance optimization (CPO) method to remove the redundant convolution filters in a CNN with performance constraints. To prove the effectiveness of the proposed method, CPO is applied to the networks for image super-resolution and image classification. Under almost the same PSNR drop and accuracy drop for performance evaluation in these two tasks, we can achieve the best parameter and computation reduction when compared with previous works. [ABSTRACT FROM AUTHOR]

Visual feature detection has been widely used in many computer vision applications, with increasing concern on feature robustness, processing speed, and power efficiency. In comparison with popular feature detection algorithms, affine-SIFT achieves the strongest robustness on the image illumination, image rotation, and image scale transformation, but exhibits extreme high computation complexity. To improve its computing efficiency, this work first proposes three hardware optimization methods to address three main performance bottlenecks. The first method is the reverse affine-based pipelined computing with optimized memory accessing. The second method is about stream processing with full parallel Gaussian pyramid. The third method is the rotation invariant binary pattern based feature vector generation. Then by incorporating these three optimization methods, this paper designs a high-efficient pipelined and parallel hardware architecture with optimized parallel memory accessing. Postlayout simulations using TSMC 65-nm 1P9M low power process show that this work achieves a processing speed of 97 fps at 1080p (1000 feature points per frame on average) under 200 MHz, with power consumption at 300 mW. In comparison, its computing efficiency (1005.6K pixels/s at 1 MHz) and power efficiency (670.5K pixels/s at 1 mW) are higher than state-of-the-art works and it is more promising for broad vision applications especially the embedded vision and mobile vision applications. [ABSTRACT FROM AUTHOR]

Google has juiced more than 50 of its own apps for the big screen; stalwarts like Gmail and Maps offer desktop-like experiences with multipane views. Gear BenQ Genie e-Reading Desk Lamp The whimsical, swooping grin on the curved head of BenQ's desk lamp doesn't just brighten the mood, it also illuminates more of your desk than a traditional lamp. Google's first bendy phone, the Pixel Fold, has a 5.8-inch display on the outside and a 7.6-inch folding screen on the inside. [Extracted from the article]

Spiking neural networks (SNNs), which are inspired by the human brain, have recently gained popularity due to their relatively simple and low-power hardware for transmitting binary spikes and highly sparse activation maps. However, because SNNs contain extra time dimension information, the SNN accelerator will require more buffers and take longer to infer, especially for the more difficult high-resolution object detection task. As a result, this paper proposes a sparse compressed spiking neural network accelerator that takes advantage of the high sparsity of activation maps and weights by utilizing the proposed gated one-to-all product for low power and highly parallel model execution. The experimental result of the neural network shows 71.5% mAP with mixed (1,3) time steps on the IVS 3cls dataset. The accelerator with the TSMC 28nm CMOS process can achieve $1024\times 576.29$ frames per second processing when running at 500MHz with 35.88TOPS/W energy efficiency and 1.05mJ energy consumption per frame. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have recently shown state-of-the-art results on various applications, such as computer vision and recognition tasks. DNN inference engines can be implemented in hardware with high energy efficiency as the computation can be realized using a low-precision fixed point or even binary precision with sufficient cognition accuracies. On the other hand, training DNNs using the well-known back-propagation algorithm requires high-precision floating-point computations on a CPU and/or GPU causing significant power dissipation (more than hundreds of kW) and long training time (several days or more). In this paper, we demonstrate a training chip fabricated using a commercial 65-nm CMOS technology for machine learning. The chip performs training without back propagation by using invertible logic with stochastic computing that can directly obtain weight values using input/output training data with low precision suitable for inference. When training neurons that compute the weighted sum of all inputs and then apply a non-linear activation function, our chip demonstrates a reduction of power dissipation and latency by 99.98% and 99.95%, respectively, in comparison with a state-of-the-art software implementation. [ABSTRACT FROM AUTHOR]

This paper proposes a unified approach to learning in environments in which patterns can be represented in variable-dimension domains, which nicely includes the case in which there are missing features. The proposal is based on the representation of the environment by pointwise constraints that are shown to model naturally pattern relationships that come out in problems of information retrieval, computer vision, and related fields. The given interpretation of learning leads to capturing the truly different aspects of similarity coming from the content at different dimensions and the pattern links. It turns out that functions that process real-valued features and functions that operate on symbolic entities are learned within a unified framework of regularization that can also be expressed using the kernel machines mathematical and algorithmic apparatus. Interestingly, in the extreme cases in which only the content or only the links are available, our theory returns classic kernel machines or graph regularization, respectively. We show experimental results that provide clear evidence of the remarkable improvements that are obtained when both types of similarities are exploited on artificial and real-world benchmarks. [ABSTRACT FROM PUBLISHER]

Checking validity of a model is a crucial step in the process of system identification. This is especially true when dealing with switched affine systems since, in this case, the problem of system identification from noisy data is known to be generically NP-Hard and can only be solved in practice by using heuristics and relaxations. Therefore, before the identified models can be used for instance for controller design, they should be systematically validated against additional experimental data. In this paper we address the problem of model (in)validation for multi-input multi-output switched affine systems in output error form with unknown switches. As a first step, we prove that necessary and sufficient invalidation certificates can be obtained by solving a sequence of convex optimization problems. In principle, these problems involve increasingly large matrices. However, as we show in the paper by exploiting recent results from semialgebraic geometry, the proposed algorithm is guaranteed to stop after a finite number of steps that can be be explicitly computed from the a priori information. In addition, this algorithm exploits the sparse structure of the underlying optimization problem to substantially reduce the computational burden. The effectiveness of the proposed method is illustrated using both academic examples and a non-trivial problem arising in computer vision: activity monitoring. [ABSTRACT FROM AUTHOR]

In this paper, we describe a simple and highly efficient module for image classification, which we term the “Attention Inspiring Receptive-fields” (Air) module. We effectively convert the spatial attention mechanism into a plug-in module. In addition, we reveal the relationship between the spatial attention mechanism and the receptive fields, indicating that the proper use of the spatial attention mechanism can effectively increase the receptive fields of the module, which is able to enhance translation invariance and scale invariance of the network. By integrating the Air module into advanced convolutional neural networks (such as ResNet and ResNeXt), we can construct AirNet architectures for learning invariant representations and gain significant improvements on challenging data sets. We present extensive experiments on CIFAR and ImageNet data sets to verify the effectiveness and feature invariance of the Air module and explore more concise and efficient designs of the proposed module. On ImageNet classification, our AirNet-50 and AirNet-101 (ResNet-50/101 with Air module) achieve 1.69% and 1.50% top-1 accuracy improvement with a small amount of extra computation and parameters compared with the original ResNet. We make models and code public available https://github.com/soeaver/AirNet-PyTorch. We further demonstrate that AirNet has a good ability for transfer learning and measure the performance on Microsoft Common Objects in Context object detection, instance segmentation, and pose estimation. [ABSTRACT FROM AUTHOR]

More often than laypeople might expect, step two is followed by unplanned bolt loosening, which necessitates step three, a slick bit of robotic detective work known to insiders as "loosened-bolt detection". Successful detection of a loose bolt leads, of course, to another go at step two, bolt tightening. A classic work about loosened bolt detection is Lovedeep Ramana and colleagues' "Automated vision-based loosened bolt detection using the cascade detector". [Extracted from the article]

Typical dimensionality reduction (DR) methods are data-oriented, focusing on directly reducing the number of random variables (or features) while retaining the maximal variations in the high-dimensional data. Targeting unsupervised situations, this paper aims to address the problem from a novel perspective and considers model-oriented DR in parameter spaces of binary multivariate distributions. Specifically, we propose a general parameter reduction criterion, called confident-information-first (CIF) principle, to maximally preserve confident parameters and rule out less confident ones. Formally, the confidence of each parameter can be assessed by its contribution to the expected Fisher information distance within a geometric manifold over the neighborhood of the underlying real distribution. Then, we demonstrate two implementations of CIF in different scenarios. First, when there are no observed samples, we revisit the Boltzmann machines (BMs) from a model selection perspective and theoretically show that both the fully visible BM and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle. This finding would help us uncover and formalize the essential parts of the target density that BM aims to capture and the nonessential parts that BM should discard. Second, when there exist observed samples, we apply CIF to the model selection for BM, which is in turn made adaptive to the observed samples. The sample-specific CIF is a heuristic method to decide the priority order of parameters, which can improve the search efficiency without degrading the quality of model selection results as shown in a series of density estimation experiments. [ABSTRACT FROM AUTHOR]

Data encoded as symmetric positive definite (SPD) matrices frequently arise in many areas of computer vision and machine learning. While these matrices form an open subset of the Euclidean space of symmetric matrices, viewing them through the lens of non-Euclidean Riemannian (Riem) geometry often turns out to be better suited in capturing several desirable data properties. Inspired by the great success of dictionary learning and sparse coding (DLSC) for vector-valued data, our goal in this paper is to represent data in the form of SPD matrices as sparse conic combinations of SPD atoms from a learned dictionary via a Riem geometric approach. To that end, we formulate a novel Riem optimization objective for DLSC, in which the representation loss is characterized via the affine-invariant Riem metric. We also present a computationally simple algorithm for optimizing our model. Experiments on several computer vision data sets demonstrate superior classification and retrieval performance using our approach when compared with SC via alternative non-Riem formulations. [ABSTRACT FROM PUBLISHER]

Aiming at the problem of low efficiency during manual inspection of the magnetron-sputtered parts, an automatic inspection system based on machine vision technology was designed to achieve the automatic detection of scratches on the surface of magnetron-sputtered part with the needs of a plant. Firstly, the captured images ware corrected, and the region of interest was extracted from the sample image through shape template matching with a template which was created from the standard image. The image was then decomposed into two parts: low-frequency part and high-frequency part. The dilation and erosion were carried out on the low-frequency part, and the median filter denoising operation was performed on the highfrequency part. After the image is synthesized, an enhanced image was generated through inversion and gray scaling. Finally, the image was segmented by two-dimensional Otsu thresholding method, and the scratch defects were extracted and measured by shape feature specifying and skeleton extraction. According to the results of multiple random verifications on 100 samples, the system designed in this paper is able to extract and measure scratch defects quickly, accurately, and efficiently. The average detection time for each sample was 0.25 s, and the positive detection rate was 98.5%. As compared with manual inspection, this solution is faster and more accurate, and meets the needs of industrial applications. [ABSTRACT FROM AUTHOR]

This paper proposes a theory for understanding perceptual learning processes within the general framework of laws of nature. Artificial neural networks are regarded as systems whose connections are Lagrangian variables, namely, functions depending on time. They are used to minimize the cognitive action, an appropriate functional index that measures the agent interactions with the environment. The cognitive action contains a potential and a kinetic term that nicely resemble the classic formulation of regularization in machine learning. A special choice of the functional index, which leads to the fourth-order differential equations—Cognitive Action Laws (CAL)—exhibits a structure that mirrors classic formulation of machine learning. In particular, unlike the action of mechanics, the stationarity condition corresponds with the global minimum. Moreover, it is proven that typical asymptotic learning conditions on the weights can coexist with the initialization provided that the system dynamics is driven under a policy referred to as information overloading control. Finally, the theory is experimented for the problem of feature extraction in computer vision. [ABSTRACT FROM AUTHOR]

Recently, there is a rapidly increasing attraction for the efficient recovery of low-rank matrix in computer vision and machine learning. The popular convex solution of rank minimization is nuclear norm-based minimization (NNM), which usually leads to a biased solution since NNM tends to overshrink the rank components and treats each rank component equally. To address this issue, some nonconvex nonsmooth rank (NNR) relaxations have been exploited widely. Different from these convex and nonconvex rank substitutes, this paper first introduces a general and flexible rank relaxation function named weighted NNR relaxation function, which is actually derived from the initial double NNR (DNNR) relaxations, i.e., DNNR relaxation function acts on the nonconvex singular values function (SVF). An iteratively reweighted SVF optimization algorithm with continuation technology through computing the supergradient values to define the weighting vector is devised to solve the DNNR minimization problem, and the closed-form solution of the subproblem can be efficiently obtained by a general proximal operator, in which each element of the desired weighting vector usually satisfies the nondecreasing order. We next prove that the objective function values decrease monotonically, and any limit point of the generated subsequence is a critical point. Combining the Kurdyka–Łojasiewicz property with some milder assumptions, we further give its global convergence guarantee. As an application in the matrix completion problem, experimental results on both synthetic data and real-world data can show that our methods are competitive with several state-of-the-art convex and nonconvex matrix completion methods. [ABSTRACT FROM AUTHOR]

The article offers brief descriptions of several computer science journals, including "International Journal of Computer Vision," "Machine Learning," and "International Journal of Parallel Programming."

Human preferences are usually measured using ordinal variables. A system whose goal is to estimate the preferences of humans and their underlying decision mechanisms requires to learn the ordering of any given sample set. We consider the solution of this ordinal regression problem using a support vector machine algorithm. Specifically, the goal is to learn a set of classifiers with common direction vectors and different biases correctly separating the ordered classes. Current algorithms are either required to solve a quadratic optimization problem, which is computationally expensive, or based on maximizing the minimum margin (i.e., a fixed-margin strategy) between a set of hyperplanes, which biases the solution to the closest margin. Another drawback of these strategies is that they are limited to order the classes using a single ranking variable (e.g., perceived length). In this paper, we define a multiple ordinal regression algorithm based on maximizing the sum of the margins between every consecutive class with respect to one or more rankings (e.g., perceived length and weight). We provide derivations of an efficient, easy-to-implement iterative solution using a sequential minimal optimization procedure. We demonstrate the accuracy of our solutions in several data sets. In addition, we provide a key application of our algorithms in estimating human subjects’ ordinal classification of attribute associations to object categories. We show that these ordinal associations perform better than the binary one typically employed in the literature. [ABSTRACT FROM AUTHOR]

A research paper from the Dr. Sivanthi Aditanar College of Engineering in Tiruchendur, India, explores the analysis of Bipolar Disorder (BD) using structural magnetic resonance imaging (MRI) and a supervised learning framework. The study aims to identify specific abnormalities in brain cells that indicate BD. The researchers employed a 3D texture analysis approach, extracting texture features from the MRI data and using a supervised learning algorithm called Support Vector Machine (SVM) to classify samples as healthy or abnormal. The results showed promising outcomes, with the SVM model achieving an accuracy of 90.42%. This research provides valuable insights into the application of supervised learning and MRI data analysis for understanding BD. [Extracted from the article]

Generative models have emerged as potential tools for creating high-quality images, videos, and text. This paper explores the application of generative models in automating vlog content creation. It addresses both static and dynamic visual elements, eliminating the need for human intervention. Traditional vlogs often require specific environmental conditions and proper lighting for the vlog creation. To streamline this process, an automated system utilizing the generative models is proposed here. Generative models excel at generating realistic content that seamlessly integrates with real-world content. They enhance overall video quality and introduce creative elements by generating new scenes and backgrounds. This paper categorizes various generative modeling techniques based on frame elements and foreground-background conditions. It offers a comparative analysis of different generative model variants tailored for specific objectives. Furthermore, the paper reviews existing research on generative models for video and image content generation, visual quality enhancement, diversity, and coherence outcomes. Additionally, the paper highlights practical uses of the generative model for content creation in various contexts, such as face swapping, scene translation, and virtual content insertion. The paper also examines the public datasets used to train generative models. These datasets contain diverse visual content such as celebrity images, urban landscapes, and everyday scenes. [ABSTRACT FROM AUTHOR]

Purpose – Image edge detection is an essential issue in image processing and computer vision. The purpose of this paper is to provide a novel and effective algorithm for image edge detection. Design/methodology/approach – Because GM (1,1) model is a typical model for tendency analysis, GM (1,1) model can be used for detecting edge. Prediction image data are close to the original image data by reason of the data being smooth in the non-edge zone of image. The principle of edge detection by GM (1,1) model is that the predicted value at an edge point will be an overestimate or underestimate owing to the data changing drastically in the edge zone of the image. First, the edge image information is obtained by a preprocessed image subtracting from prediction image via GM (1,1). Second, median filter is used to eliminate isolated point noise in edge information images, and discrete wavelet transform is used to extract the image edge. Finally, this paper verifies the proposed algorithm by experiment. Findings – Experimental results show that the proposed algorithm has advantages such as precisely locating, abundant weak edge, and better anti-noise performance. Practical implications – The algorithm proposed in the paper can precisely detect the information of edge image, and get a clear image detail. Originality/value – Grey system theory developed vigorously lays the foundation for image processing. Wavelet analysis in image processing has its characteristics. This paper combines grey prediction model with discrete wavelet transform (DWT) successfully and obtains a novel and effective algorithm for image edge detection. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are powerful machine learning models that have become the state of the art in several problems in the areas of computer vision and image processing. Nevertheless, the knowledge of why and how these models present an impressive performance is still limited. There are visualization techniques that can help us to understand the inner working of neural networks. However, they have mostly been applied to classification models. In this paper, we evaluate the application of visualization methods to networks where the input and output are images of proportional dimensions. The results show that visualization brings visual cues associated with how these systems work, helping in their understanding and improvement. We use the knowledge obtained from the visualization of an image restoration CNN to improve the architecture’s efficiency with no significant degradation of its performance. [ABSTRACT FROM AUTHOR]

Subspace clustering is a problem of exploring the low-dimensional subspaces of high-dimensional data. State-of-the-art approaches are designed by following the model of spectral clustering-based method. These methods pay much attention to learn the representation matrix to construct a suitable similarity matrix and overlook the influence of the noise term on subspace clustering. However, the real data are always contaminated by the noise and the noise usually has a complicated statistical distribution. To alleviate this problem, in this paper, we propose a subspace clustering method based on Cauchy loss function (CLF). Particularly, it uses CLF to penalize the noise term for suppressing the large noise mixed in the real data. This is due to that the CLF’s influence function has an upper bound that can alleviate the influence of a single sample, especially the sample with a large noise, on estimating the residuals. Furthermore, we theoretically prove the grouping effect of our proposed method, which means that highly correlated data can be grouped together. Finally, experimental results on five real data sets reveal that our proposed method outperforms several representative clustering methods. [ABSTRACT FROM AUTHOR]

Multidimensional data (i.e., tensors) with missing entries are common in practice. Extracting features from incomplete tensors is an important yet challenging problem in many fields such as machine learning, pattern recognition, and computer vision. Although the missing entries can be recovered by tensor completion techniques, these completion methods focus only on missing data estimation instead of effective feature extraction. To the best of our knowledge, the problem of feature extraction from incomplete tensors has yet to be well explored in the literature. In this paper, we therefore tackle this problem within the unsupervised learning environment. Specifically, we incorporate low-rank tensor decomposition with feature variance maximization (TDVM) in a unified framework. Based on orthogonal Tucker and CP decompositions, we design two TDVM methods, TDVM-Tucker and TDVM-CP, to learn low-dimensional features viewing the core tensors of the Tucker model as features and viewing the weight vectors of the CP model as features. TDVM explores the relationship among data samples via maximizing feature variance and simultaneously estimates the missing entries via low-rank Tucker/CP approximation, leading to informative features extracted directly from observed entries. Furthermore, we generalize the proposed methods by formulating a general model that incorporates feature regularization into low-rank tensor approximation. In addition, we develop a joint optimization scheme to solve the proposed methods by integrating the alternating direction method of multipliers with the block coordinate descent method. Finally, we evaluate our methods on six real-world image and video data sets under a newly designed multiblock missing setting. The extracted features are evaluated in face recognition, object/action classification, and face/gait clustering. Experimental results demonstrate the superior performance of the proposed methods compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Low-rank tensor completion plays an important role in many applications such as image processing, computer vision, and machine learning. A widely used convex relaxation of this problem is to minimize the nuclear norm of the square deal matrix generated by reshaping a tensor. However, this approach can be substantially suboptimal. In order to seek a highly accurate solution, in this paper, we propose to use a family of nonconvex functions onto the singular values of the square deal matrix of the tensor to approximate the rank of the tensor. A proximal linearized minimization (PLM) algorithm is proposed to solve the resulting model. Furthermore, based on the Kurdyka–Łojasiewicz property, we show that the sequence generated by the PLM algorithm globally converges to a critical point of the objective function. Extensive numerical experiments including synthetic data, video data, and the extended Yale Face Database B show the effectiveness of the proposed model compared with several existing state-of-the-art models. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel variational Bayesian learning method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements. The recently proposed extended variational inference (EVI) framework is adopted to derive an analytically tractable solution. The convergency of the proposed algorithm is theoretically guaranteed by introducing single lower bound approximation to the original objective function in the EVI framework. In principle, the proposed model can be viewed as an infinite inverted Dirichlet mixture model that allows the automatic determination of the number of mixture components from data. Therefore, the problem of predetermining the optimal number of mixing components has been overcome. Moreover, the problems of overfitting and underfitting are avoided by the Bayesian estimation approach. Compared with several recently proposed DP-related methods and conventional applied methods, the good performance and effectiveness of the proposed method have been demonstrated with both synthesized data and real data evaluations. [ABSTRACT FROM AUTHOR]

Video classification has been extensively researched in computer vision due to its wide spread applications. However, it remains an outstanding task because of the great challenges in effective spatial-temporal feature extraction and efficient classification with high-dimensional video representations. To address these challenges, in this paper, we propose an end-to-end learning framework called deep ensemble machine (DEM) for video classification. Specifically, to establish effective spatio-temporal features, we propose using two deep convolutional neural networks (CNNs), i.e., vision and graphics group and C3-D to extract heterogeneous spatial and temporal features for complementary representations. To achieve efficient classification, we propose ensemble learning based on random projections aiming to transform high-dimensional features into a set of lower dimensional compact features in subspaces; an ensemble of classifiers is trained on the subspaces and combined with a weighting layer during the backpropagation. To further enhance the performance, we introduce rectified linear encoding (RLE) inspired from error-correcting output coding to encode the initial outputs of classifiers, followed by a softmax layer to produce the final classification results. DEM combines the strengths of deep CNNs and ensemble learning, which establishes a new end-to-end learning architecture for more accurate and efficient video classification. We show the great effectiveness of DEM by extensive experiments on four data sets for diverse video classification tasks including action recognition and dynamic scene classification. Results have shown that DEM achieves high performance on all tasks with an improvement of up to 13% on CIFAR10 data set over the baseline model. [ABSTRACT FROM AUTHOR]

The low-rank tensor factorization (LRTF) technique has received increasing attention in many computer vision applications. Compared with the traditional matrix factorization technique, it can better preserve the intrinsic structure information and thus has a better low-dimensional subspace recovery performance. Basically, the desired low-rank tensor is recovered by minimizing the least square loss between the input data and its factorized representation. Since the least square loss is most optimal when the noise follows a Gaussian distribution, $L_{1}$ -norm-based methods are designed to deal with outliers. Unfortunately, they may lose their effectiveness when dealing with real data, which are often contaminated by complex noise. In this paper, we consider integrating the noise modeling technique into a generalized weighted LRTF (GWLRTF) procedure. This procedure treats the original issue as an LRTF problem and models the noise using a mixture of Gaussians (MoG), a procedure called MoG GWLRTF. To extend the applicability of the model, two typical tensor factorization operations, i.e., CANDECOMP/PARAFAC factorization and Tucker factorization, are incorporated into the LRTF procedure. Its parameters are updated under the expectation–maximization framework. Extensive experiments indicate the respective advantages of these two versions of MoG GWLRTF in various applications and also demonstrate their effectiveness compared with other competing methods. [ABSTRACT FROM AUTHOR]

This paper introduces sparse coding and dictionary learning for symmetric positive definite (SPD) matrices, which are often used in machine learning, computer vision, and related areas. Unlike traditional sparse coding schemes that work in vector spaces, in this paper, we discuss how SPD matrices can be described by sparse combination of dictionary atoms, where the atoms are also SPD matrices. We propose to seek sparse coding by embedding the space of SPD matrices into the Hilbert spaces through two types of the Bregman matrix divergences. This not only leads to an efficient way of performing sparse coding but also an online and iterative scheme for dictionary learning. We apply the proposed methods to several computer vision tasks where images are represented by region covariance matrices. Our proposed algorithms outperform state-of-the-art methods on a wide range of classification tasks, including face recognition, action recognition, material classification, and texture categorization. [ABSTRACT FROM PUBLISHER]

Time series forecasting has wide applications in our daily lives, such as meteorological warnings and decision-making. However, traditional supervised models do not perform well on forecasting tasks due to the lack of annotated training data available in real time series. Recently, researchers have proposed self-supervised methods, especially the contrastive learning approach, which can build a universal representation framework for downstream tasks through data augmentation and contrastive loss. Although it alleviates the shortage of labeled data, the data augmentation approach directly transferred from computer vision is not appropriate for the time domain due to noise vectors and unrelated variables that may interfere with the accuracy of representation. In this paper, we propose a novel time series forecasting model based on disentangled seasonal-trend representation named ACST. It employs an improved cycle generative adversarial data augmentation method to generate samples close to real data for contrastive loss. Moreover, we apply gated residual networks and a noise decomposition module to reduce the impact of different noise vectors and feature variable weights on the results. Extensive experiments show that ACST achieves an average improvement of 26.8% on six benchmarks. [ABSTRACT FROM AUTHOR]

Currently, the majority of solutions for human interactive action recognition typically rely on machine vision methods, thus leading to limited application scenarios for accurate recognition. In this paper, we proposed a novel two-level multi-head attentional human interaction action recognition model based on inertial measurement units. Considering that individual actions may contribute differently to interaction actions, the overall model of weighting individual actions to identify interaction actions is divided into individual scenes and interaction scenes. A multi-head attention mechanism is added to the model to obtain action weighting information in both scenes. We combine a bi-directional gated recurrent unit (BiGRU) and an improved convolutional neural network constructs to fully capture spatiotemporal features. The experimental results show that the established model can accurately recognize seven interactive actions with an average recognition accuracy of 98.73%, which verifies the excellent performance of the proposed method. • A new inertial sensor-based action recognition model for human interaction. • A dataset of inertial sensor-based human interaction movements was collected. • Human interaction scenes are divided into individual scenes and interaction scenes. • Multi-head attention mechanism captures local and global information. [ABSTRACT FROM AUTHOR]

We have seen remarkable recent progress in computational visual recognition, producing systems that can classify objects into thousands of different categories with increasing accuracy. However, one question that has received relatively less attention is “what labels should recognition systems output?” This paper looks at the problem of predicting category labels that mimic how human observers would name objects. This goal is related to the concept of entry-level categories first introduced by psychologists in the 1970s and 1980s. We extend these seminal ideas to study human naming at large scale and to learn computational models for predicting entry-level categories. Practical applications of this work include improving human-focused computer vision applications such as automatically generating a natural language description for an image or text-based image search. [ABSTRACT FROM AUTHOR]

Monocular multiple-object tracking is a fundamental yet under-addressed computer vision problem. In this paper, we propose a novel learning framework for tracking multiple objects by detection. First, instead of heuristically defining a tracking algorithm, we learn that a discriminative structure prediction model from labeled video data captures the interdependence of multiple influence factors. Given the joint targets state from the last time step and the observation at the current frame, the joint targets state at the current time step can then be inferred by maximizing the joint probability score. Second, our detection results benefit from tracking cues. The traditional detection algorithms need a nonmaximal suppression postprocessing to select a subset from the total detection responses as the final output and a large number of selection mistakes are induced, especially under a congested circumstance. Our method integrates both detection and tracking cues. This integration helps to decrease the postprocessing mistake risk and to improve performance in tracking. Finally, we formulate the entire model training into a convex optimization problem and estimate its parameters using the cutting plane optimization. Experiments show that our method performs effectively in a large variety of scenarios, including pedestrian tracking in crowd scenes and vehicle tracking in congested traffic. [ABSTRACT FROM PUBLISHER]

Subspace clustering is the task of identifying clusters in subspaces of the input dimensions of a given dataset. Noisy data in certain attributes cause difficulties for traditional clustering algorithms, because the high discrepancies within them can make objects appear too different to be grouped in the same cluster. This requires methods specially designed for subspace clustering. This paper presents our second approach to subspace and projected clustering based on self-organizing maps (SOMs), which is a local adaptive receptive field dimension selective SOM. By introducing a time-variant topology, our method is an improvement in terms of clustering quality, computational cost, and parameterization. This enables the method to identify the correct number of clusters and their respective relevant dimensions, and thus it presents nearly perfect results in synthetic datasets and surpasses our previous method in most of the real-world datasets considered. [ABSTRACT FROM AUTHOR]

This paper considers the problem of estimating the position of a scene point from its image projections onto generalized cameras, i.e., cameras that can be modeled by a spherical projection followed by a perspective one. The sought estimate is defined through a geometric criterion, specifically the minimization of the angles between the projections on the sphere of the available image points and the corresponding projections of the estimate. A solution based on convex optimization with linear matrix inequalities (LMIs) is proposed for addressing this problem, which provides a candidate of the sought estimate. Moreover, a condition is provided for establishing exactness of the found candidate, i.e., establishing whether the found candidate is a minimizer of the considered geometric criterion. [ABSTRACT FROM AUTHOR]

In this paper, we propose an analysis mechanism-based structured analysis discriminative dictionary learning analysis discriminative dictionary learning, framework. The ADDL seamlessly integrates ADDL, analysis representation, and analysis classifier training into a unified model. The applied analysis mechanism can make sure that the learned dictionaries, representations, and linear classifiers over different classes are independent and discriminating as much as possible. The dictionary is obtained by minimizing a reconstruction error and an analytical incoherence promoting term that encourages the subdictionaries associated with different classes to be independent. To obtain the representation coefficients, ADDL imposes a sparse $l_{2,1}$ -norm constraint on the coding coefficients instead of using $l_{0}$ or $l_{1}$ norm, since the $l_{0}$ - or $l_{1}$ -norm constraint applied in most existing DL criteria makes the training phase time consuming. The code-extraction projection that bridges data with the sparse codes by extracting special features from the given samples is calculated via minimizing a sparse code approximation term. Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers. Thus, the classification approach of our model is very efficient, because it can avoid the extra time-consuming sparse reconstruction process with trained dictionary for each new test data as most existing DL algorithms. Simulations on real image databases demonstrate that our ADDL model can obtain superior performance over other state of the arts. [ABSTRACT FROM AUTHOR]

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes are abundant, making them an overrepresented majority, and data of other classes are scarce, making them an underrepresented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this paper, we propose a cost-sensitive (CoSen) deep neural network, which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class-dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multiclass problems without any modification. Moreover, as opposed to data-level approaches, we do not alter the original data distribution, which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification data sets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and CoSen classifiers demonstrate the superior performance of our proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method, called robust latent subspace learning (RLSL), for image classification. We formulate an RLSL problem as a joint optimization problem over both the latent SL and classification model parameter predication, which simultaneously minimizes: 1) the regression loss between the learned data representation and objective outputs and 2) the reconstruction error between the learned data representation and original inputs. The latent subspace can be used as a bridge that is expected to seamlessly connect the origin visual features and their class labels and hence improve the overall prediction performance. RLSL combines feature learning with classification so that the learned data representation in the latent subspace is more discriminative for classification. To learn a robust latent subspace, we use a sparse item to compensate error, which helps suppress the interference of noise via weakening its response during regression. An efficient optimization algorithm is designed to solve the proposed optimization problem. To validate the effectiveness of the proposed RLSL method, we conduct experiments on diverse databases and encouraging recognition results are achieved compared with many state-of-the-arts methods. [ABSTRACT FROM AUTHOR]

The lack of labeled data presents a common challenge in many computer vision and machine learning tasks. Semisupervised learning and transfer learning methods have been developed to tackle this challenge by utilizing auxiliary samples from the same domain or from a different domain, respectively. Self-taught learning, which is a special type of transfer learning, has fewer restrictions on the choice of auxiliary data. It has shown promising performance in visual learning. However, existing self-taught learning methods usually ignore the structure information in data. In this paper, we focus on building a self-taught coding framework, which can effectively utilize the rich low-level pattern information abstracted from the auxiliary domain, in order to characterize the high-level structural information in the target domain. By leveraging a high quality dictionary learned across auxiliary and target domains, the proposed approach learns expressive codings for the samples in the target domain. Since many types of visual data have been proven to contain subspace structures, a low-rank constraint is introduced into the coding objective to better characterize the structure of the given target set. The proposed representation learning framework is called self-taught low-rank (S-Low) coding, which can be formulated as a nonconvex rank-minimization and dictionary learning problem. We devise an efficient majorization–minimization augmented Lagrange multiplier algorithm to solve it. Based on the proposed S-Low coding mechanism, both unsupervised and supervised visual learning algorithms are derived. Extensive experiments on five benchmark data sets demonstrate the effectiveness of our approach. [ABSTRACT FROM PUBLISHER]