Search

The ability to exert cognitive control is central to human brain function, facilitating goal-directed task performance. However, humans exhibit limitations in the duration over which they can exert cognitive control---a phenomenon referred to as cognitive fatigue. This study explores a computational rationale for cognitive fatigue in continual learning scenarios: cognitive fatigue serves to limit the extended performance of one task to avoid the forgetting of previously learned tasks. Our study employs a meta-learning framework, wherein cognitive control is optimally allocated to balance immediate task performance with forgetting of other tasks. We demonstrate that this model replicates common patterns of cognitive fatigue, such as performance degradation over time and sensitivity to reward. Furthermore, we discuss novel predictions, including variations in cognitive fatigue based on task representation overlap. This approach offers a novel perspective on the computational role of cognitive fatigue in neural systems.

As AIGC has impacted our society profoundly in the past years, ethical issues have received tremendous attention. The most urgent one is the AIGC copyright dilemma, which can immensely stifle the development of AIGC and greatly cost the entire society. Given the complexity of AIGC copyright governance and the fact that no perfect solution currently exists, previous work advocated copyleft on AI governance but without substantive analysis. In this paper, we take a step further to explore the feasibility of copyleft to alleviate the AIGC copyright dilemma. We conduct a mixed-methods study from two aspects: qualitatively, we use a formal what-if analysis to clarify the dilemma and provide case studies to show the feasibility of copyleft; quantitatively, we perform a carefully designed survey to find out how the public feels about copylefting AIGC. The key findings include: a) people generally perceive the dilemma, b) they prefer to use authorized AIGC under loose restriction, and c) they are positive to copyleft in AIGC and willing to use it in the future., Comment: 9 pages, 8 figures

Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated to gathering and transferring users' personal interaction data are often underestimated or ignored. Existing privacy-preserving studies are mainly applied to traditional collaborative filtering or matrix factorization rather than sequential recommendation. Moreover, these studies are mostly based on differential privacy or federated learning, which often leads to significant performance degradation, or has high requirements for communication. In this work, we address privacy-preserving from a different perspective. Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence. Even if the target interaction sequence is obtained by attackers, it is difficult to discern which ones are the actual user interaction records. To achieve this goal, we propose a CoLlaborative-cOnfusion seqUential recommenDer, namely CLOUD, which incorporates a collaborative confusion mechanism to edit the raw interaction sequences before conducting recommendation. Specifically, CLOUD first calculates the similarity between the target interaction sequence and other neighbor sequences to find similar sequences. Then, CLOUD considers the shared representation of the target sequence and similar sequences to determine the operation to be performed: keep, delete, or insert. We design a copy mechanism to make items from similar sequences have a higher probability to be inserted into the target sequence. Finally, the modified sequence is used to train the recommender and predict the next item.

Automatic theorem proving with deep learning methods has attracted attentions recently. In this paper, we construct an automatic proof system for trigonometric identities. We define the normalized form of trigonometric identities, design a set of rules for the proof and put forward a method which can generate theoretically infinite trigonometric identities. Our goal is not only to complete the proof, but to complete the proof in as few steps as possible. For this reason, we design a model to learn proof data generated by random BFS (rBFS), and it is proved theoretically and experimentally that the model can outperform rBFS after a simple imitation learning. After further improvement through reinforcement learning, we get AutoTrig, which can give proof steps for identities in almost as short steps as BFS (theoretically shortest method), with a time cost of only one-thousandth. In addition, AutoTrig also beats Sympy, Matlab and human in the synthetic dataset, and performs well in many generalization tasks.

With the continuous extension of the Industrial Internet, cyber incidents caused by software vulnerabilities have been increasing in recent years. However, software vulnerabilities detection is still heavily relying on code review done by experts, and how to automatedly detect software vulnerabilities is an open problem so far. In this paper, we propose a novel solution named GraphEye to identify whether a function of C/C++ code has vulnerabilities, which can greatly alleviate the burden of code auditors. GraphEye is originated from the observation that the code property graph of a non-vulnerable function naturally differs from the code property graph of a vulnerable function with the same functionality. Hence, detecting vulnerable functions is attributed to the graph classification problem.GraphEye is comprised of VecCPG and GcGAT. VecCPG is a vectorization for the code property graph, which is proposed to characterize the key syntax and semantic features of the corresponding source code. GcGAT is a deep learning model based on the graph attention graph, which is proposed to solve the graph classification problem according to VecCPG. Finally, GraphEye is verified by the SARD Stack-based Buffer Overflow, Divide-Zero, Null Pointer Deference, Buffer Error, and Resource Error datasets, the corresponding F1 scores are 95.6%, 95.6%,96.1%,92.6%, and 96.1% respectively, which validate the effectiveness of the proposed solution.

The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical problem in advanced deep model training with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation and its modified version for high GPU usage. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter optimization algorithm called BOSS. Empirical studies validate our theoretical arguments of SS and demonstrate the superior performance of BOSS on a number of applications, including Neural Architecture Search (NAS), Data Augmentation (DA), Object Detection (OD), and Reinforcement Learning (RL).

We study the smooth minimax optimization problem $\min_{\bf x}\max_{\bf y} f({\bf x},{\bf y})$, where $f$ is $\ell$-smooth, strongly-concave in ${\bf y}$ but possibly nonconvex in ${\bf x}$. Most of existing works focus on finding the first-order stationary points of the function $f({\bf x},{\bf y})$ or its primal function $P({\bf x})\triangleq \max_{\bf y} f({\bf x},{\bf y})$, but few of them focus on achieving second-order stationary points. In this paper, we propose a novel approach for minimax optimization, called Minimax Cubic Newton (MCN), which could find an $\big(\varepsilon,\kappa^{1.5}\sqrt{\rho\varepsilon}\,\big)$-second-order stationary point of $P({\bf x})$ with calling ${\mathcal O}\big(\kappa^{1.5}\sqrt{\rho}\varepsilon^{-1.5}\big)$ times of second-order oracles and $\tilde{\mathcal O}\big(\kappa^{2}\sqrt{\rho}\varepsilon^{-1.5}\big)$ times of first-order oracles, where $\kappa$ is the condition number and $\rho$ is the Lipschitz continuous constant for the Hessian of $f({\bf x},{\bf y})$. In addition, we propose an inexact variant of MCN for high-dimensional problems to avoid calling expensive second-order oracles. Instead, our method solves the cubic sub-problem inexactly via gradient descent and matrix Chebyshev expansion. This strategy still obtains the desired approximate second-order stationary point with high probability but only requires $\tilde{\mathcal O}\big(\kappa^{1.5}\ell\varepsilon^{-2}\big)$ Hessian-vector oracle calls and $\tilde{\mathcal O}\big(\kappa^{2}\sqrt{\rho}\varepsilon^{-1.5}\big)$ first-order oracle calls. To the best of our knowledge, this is the first work that considers the non-asymptotic convergence behavior of finding second-order stationary points for minimax problems without the convex-concave assumptions.

The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter optimization algorithm called BOSS. Empirical studies validate our theoretical arguments of SS and demonstrate the superior performance of BOSS on a number of applications, including Neural Architecture Search (NAS), Data Augmentation (DA), Object Detection (OD), and Reinforcement Learning (RL).

MXenes, a new class of two-dimensional materials with excellent performance, are promising materials for wearable energy storage devices. However, the lack of sufficient interaction between various MXene particles makes it difficult to translate the exceptional performance from the nanoscale to macroscale. Additionally, the intrinsic characteristic of easy oxidation limits their practical applications. Herein, inspired by the structure of wood, a biomimetic core-shell MXene@graphene oxide (MX@GO) fiber was fabricated using GO as a mechanical layer to wrap MXenes. The GO layer could easily assemble MXene particles into macroscale materials and protect them from oxidation. Therefore, the as-fabricated core-shell MX@GO fiber showed a high tensile strength (290 MPa) and excellent electrical conductivity (2400 S m-1). Notably, the conductivity of the biomimetic fiber only decreased to 1800 S m-1 with a reduction of about 30% at 100 °C. This work paves the way to fabricate MXene-based fibers with freely designed functionalities and morphologies, which are suitable for various high-value fabric-based applications.

We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence guarantees. However, these methods have a slow convergence when the condition number of the problem is very large. In this paper, we propose a stochastic proximal point algorithm, which accelerates the variance reduction method SAGA for saddle point problems. Compared with the catalyst framework, our algorithm reduces a logarithmic term of condition number for the iteration complexity. We adopt our algorithm to policy evaluation and the empirical results show that our method is much more efficient than state-of-the-art methods.

Yujun Li,1–4,* Jie Liu,5,* Wanglai Hu,6,* Yuliang Zhang,1–4,* Jiangwei Sang,1–4 Huizheng Li,7 Teng Ma,8 Yunfeng Bo,9 Tao Bai,10 Huina Guo,1–4 Yan Lu,11 Xuting Xue,1–4 Min Niu,1–4 Shanshan Ge,12 Shuxin Wen,1–4 Binquan Wang,1–4 Wei Gao,1–4 Yongyan Wu1–4 1Shanxi Key Laboratory of Otorhinolaryngology Head and Neck Cancer, Shanxi Medical University, Taiyuan, Shanxi 030001, People’s Republic of China; 2Department of Otolaryngology Head & Neck Surgery, The First Hospital of Shanxi Medical University, Taiyuan, Shanxi 030001, People’s Republic of China; 3Otolaryngology Head & Neck Surgery Research Institute, Shanxi Medical University, Taiyuan, Shanxi 030001, People’s Republic of China; 4The Key Scientific and Technological Innovation Platform for Precision Diagnosis and Treatment of Head and Neck Cancer, Shanxi Province, Taiyuan 030001, Shanxi, People’s Republic of China; 5Department of Head and Neck Surgical Oncology, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, People’s Republic of China; 6School of Basic Medical Science, Anhui Medical University, Hefei, Anhui 230027, People’s Republic of China; 7Department of Otolaryngology Head & Neck Surgery, Dalian Municipal Friendship Hospital, Dalian, Liaoning 116001, People’s Republic of China; 8Department of Cellular and Molecular Biology, Beijing Chest Hospital, Beijing Tuberculosis and Thoracic Tumor Research Institute, Capital Medical University, Beijing 101149, People’s Republic of China; 9Department of Pathology, Shanxi Cancer Hospital, Shanxi Medical University, Taiyuan, Shanxi 030000, People’s Republic of China; 10Department of Pathology, The First Hospital of Shanxi Medical University, Ta

Coordinated control strategies to provide system inertia support for main grid from offshore wind farm that is integrated through HVdc transmission is the subject matter of this paper. The strategy that seeks to provide inertia support to the main grid through simultaneous utilization of HVdc capacitors energy, and wind turbines (WTs) inertia without installing the remote communication of two HVdc terminals is introduced in details. Consequently, a novel strategy is proposed to improve system inertia through sequentially exerting dc capacitors energy and then WTs inertia via a cascading control scheme. Both strategies can effectively provide inertia support while the second one minimizes the control impacts on harvesting wind energy with the aid of communication between onshore and offshore ac grids. Case studies of a wind farm connecting with a HVdc system considering sudden load variations have been successfully conducted to compare and demonstrate the effectiveness of the control strategies in DIgSILENT/PowerFactory.

Zhuxiang Zhao,1,2 Changbin Jiang,1 Dongxing Zhao,1 Yujun Li,2 Chunxiao Liang,1 Weifeng Liu,2 Shuquan Wei,2 Yumin Zhou,1 Ziwen Zhao,2 Pixin Ran1 1The State Key Laboratory of Respiratory Diseases, The First Affliated Hospital, Guangzhou Medical University, Guangzhou, 2The Pulmonary Medicine,Guangzhou First People’s Hospital, Guangzhou Medical University, Guangzhou, Guangdong, People’s Republic of China Abstract: Quantitative computed tomography (CT) measures of emphysema have been shown to be associated with increased mortality in humans, but genetic variants affecting the quantitative parameters of chest CT that measure degree of emphysema have not yet been examined. In this study, using available chest CT data from a total of 344 emphysema patients, we assessed the correlations between five chronic obstructive pulmonary disease (COPD) susceptibility variants in the cholinergic receptor nicotinic (CHRN) genes and the degree of emphysema and chest CT manifestations. We verified that most of the parameters were significantly correlated with the degree of emphysema. Compared to rs76071148AA and TT genotype carriers, the rs76071148AT genotype carriers exhibited a decreased probability of having severe emphysema (odds ratio [OR] =0.63, 95% confidence interval [CI] =0.40–0.99), whereas the variant rs8040868C allele was negatively correlated with the emphysema index (P=0.002). Interestingly, further stratification analysis grouped by spirometry-diagnosed COPD status revealed that the variant rs8040868C (CT + CC) genotypes exerted a protective effect against severe emphysema with borderline significance (OR =0.41, 95% CI =0.16–1.05) and affected the mean lung density, emphysema index, ratio of airway wall thickness to airway dimensions (AWT/AD), and AWT grade in spirometry-diagnosed non-COPD subjects. The rs76071148 variant was also significantly associated with AWT/AD and AWT grade in those individuals. In summary, we determined that

Kaczmarz algorithm is an efficient iterative algorithm to solve overdetermined consistent system of linear equations. During each updating step, Kaczmarz chooses a hyperplane based on an individual equation and projects the current estimate for the exact solution onto that space to get a new estimate. Many vairants of Kaczmarz algorithms are proposed on how to choose better hyperplanes. Using the property of randomly sampled data in high-dimensional space, we propose an accelerated algorithm based on clustering information to improve block Kaczmarz and Kaczmarz via Johnson-Lindenstrauss lemma. Additionally, we theoretically demonstrate convergence improvement on block Kaczmarz algorithm.

Prior optimal CUR decomposition and near optimal column reconstruction methods have been established by combining BSS sampling and adaptive sampling. In this paper, we propose a new approach to the optimal CUR decomposition and near optimal column reconstruction by just using leverage score sampling. In our approach, both the BSS sampling and adaptive sampling are not needed. Moreover, our approach is the first $O(\mathrm{nnz}(\A))$ optimal CUR algorithm where $\A$ is a data matrix in question. We also extend our approach to the Nystr{\"o}m method, obtaining a fast algorithm which runs $\tilde{O}(n^{2})$ or $O(\mathrm{\nnz}(\A))$, Comment: this work can be derived from other work easily

In this paper, we present a novel view synthesis method named Visto, which uses a reference input view to generate synthesized views in nearby viewpoints. We formulate the problem as a joint optimization of inter-view texture and depth map similarity, a framework that is significantly different from other traditional approaches. As such, Visto tends to implicitly inherit the image characteristics from the reference view without the explicit use of image priors or texture modeling. Visto assumes that each patch is available in both the synthesized and reference views and thus can be applied to the common area between the two views but not the out-of-region area at the border of the synthesized view. Visto uses a Gauss-Seidel-like iterative approach to minimize the energy function. Simulation results suggest that Visto can generate seamless virtual views and outperform other state-of-the-art methods.

In this paper, we present a novel view synthesis method named Visto, which uses a reference input view to generate synthesized views in nearby viewpoints. We formulate the problem as a joint optimization of inter-view texture and depth map similarity, a framework that is significantly different from other traditional approaches. As such, Visto tends to implicitly inherit the image characteristics from the reference view without the explicit use of image priors or texture modeling. Visto assumes that each patch is available in both the synthesized and reference views and thus can be applied to the common area between the two views but not the out-of-region area at the border of the synthesized view. Visto uses a Gauss-Seidel-like iterative approach to minimize the energy function. Simulation results suggest that Visto can generate seamless virtual views and outperform other state-of-the-art methods.

In this paper, we present a novel view synthesis method named Visto, which uses a reference input view to generate synthesized views in nearby viewpoints. We formulate the problem as a joint optimization of inter-view texture and depth map similarity, a framework that is significantly different from other traditional approaches. As such, Visto tends to implicitly inherit the image characteristics from the reference view without the explicit use of image priors or texture modeling. Visto assumes that each patch is available in both the synthesized and reference views and thus can be applied to the common area between the two views but not the out-of-region area at the border of the synthesized view. Visto uses a Gauss-Seidel-like iterative approach to minimize the energy function. Simulation results suggest that Visto can generate seamless virtual views and outperform other state-of-the-art methods.

Given two pictures of the same scene captured using the same camera and the same lens, the one captured with a large aperture will appear partially blurred while the other captured with a small aperture will appear totally sharp. This paper investigates two possible ways of inferring depth of the scene from such an image pair with the constraint that both pictures are focused on the closest point of the scene. Our first method uses a series of Gaussian kernels to blur the image pair, and in the second method, the image pair will be shrunk to a series of smaller dimensions. In both methods, sharp areas in both images will always stay similar to each other, whereas the areas that appear sharp in one image but blurred in the other will not be similar until they are blurred using a large Gaussian kernel or shrunk to small dimensions. This observation enables us to roughly tell which objects in the scene are closer to us and which ones are farther away. At the end of this paper, we will discuss the limitations of our proposed approaches and some of the directions for future work. © Springer-Verlag 2013.

Given two pictures of the same scene captured using the same camera and the same lens, the one captured with a large aperture will appear partially blurred while the other captured with a small aperture will appear totally sharp. This paper investigates two possible ways of inferring depth of the scene from such an image pair with the constraint that both pictures are focused on the closest point of the scene. Our first method uses a series of Gaussian kernels to blur the image pair, and in the second method, the image pair will be shrunk to a series of smaller dimensions. In both methods, sharp areas in both images will always stay similar to each other, whereas the areas that appear sharp in one image but blurred in the other will not be similar until they are blurred using a large Gaussian kernel or shrunk to small dimensions. This observation enables us to roughly tell which objects in the scene are closer to us and which ones are farther away. At the end of this paper, we will discuss the limitations of our proposed approaches and some of the directions for future work. © Springer-Verlag 2013.

Given two pictures of the same scene captured using the same camera and the same lens, the one captured with a large aperture will appear partially blurred while the other captured with a small aperture will appear totally sharp. This paper investigates two possible ways of inferring depth of the scene from such an image pair with the constraint that both pictures are focused on the closest point of the scene. Our first method uses a series of Gaussian kernels to blur the image pair, and in the second method, the image pair will be shrunk to a series of smaller dimensions. In both methods, sharp areas in both images will always stay similar to each other, whereas the areas that appear sharp in one image but blurred in the other will not be similar until they are blurred using a large Gaussian kernel or shrunk to small dimensions. This observation enables us to roughly tell which objects in the scene are closer to us and which ones are farther away. At the end of this paper, we will discuss the limitations of our proposed approaches and some of the directions for future work. © Springer-Verlag 2013.

We present a convex optimization approach to dense stereo matching in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we are able to formulate stereo matching as a continuous convex quadratic program without performing complicated relaxations or approximations on the objective function. When disparity is modeled as a discrete random variable, the theoretical foundation of our approach can be analyzed from the perspective of probability theory. Our convex optimization framework supports adaptive correlation windows and can be implemented using CVX, the Matlab software for disciplined convex programming, in a straightforward manner. Furthermore, effective techniques for disparity refinement, which include an occlusion detection algorithm performed on a single disparity map that takes advantage of the valuable information provided by the permutation matrix, and a plane fitting method mainly based on minimizing the l1 norm of the disparity errors caused by a disparity plane, are also proposed. Experimental results show that by minimizing our convex objective function and applying the proposed disparity refinement techniques, we are able to generate good quality disparity maps.

In this paper, we present a view synthesis method named Visto which aims to generate seamless novel views from a monocular view input. We formulate the problem as joint optimization of inter-view texture similarity and geometry preservation, which significantly differs from traditional view synthesis framework. In this way, the image characteristics of virtual view are inherently inherited from the reference view without introducing any image prior or texture modeling technique. The energy function is minimized using Gauss-Seidel-like approach, and the quality of the virtual view is refined iteratively. The proposed approach also tolerates small depth map errors. Further more, the algorithm is parallel friendly. The simulation results outperform several existing state-of-the-art monocular view synthesis systems. © 2012 ACM.

in this paper, a novel plane fitting algorithm with low complexity and high accuracy is proposed to refine the depth maps generated by stereo matching. We first compute the confidence coefficient for each pixel in the depth map by cross checking and stable pixel calculation. According to the outlier pixel percentage for each segment, we choose one method, either proposed weighted least square error based or RANSAC based plane fitting algorithm, to estimate the plane parameters. Experimental results show that our method outperforms other existing plane fitting algorithms.

In depth map coding for 3D video coding systems, coding errors in edges can severely affect the synthesis quality. Edge errors mainly compose of two parts: one is blurring and ringing artifact around sharp edge and the other is fake edge caused by blocking artifact. In this paper, we propose an adaptive depth map filter to remove blocking artifacts while preserving depth edges. The proposed filter is designed based on bilateral filter, in which the range kernel parameter is changed adaptively considering the strength of edges and blocking artifacts. Experimental results demonstrate that the proposed depth map filter can achieve up to 0.41 dB gain on the synthesis quality compared to the deblocking filter in MVC at low bit rate.

View synthesis is a technique to generate images/videos in a virtual viewpoint. In this paper, the dis-occlusion/hole problem in view synthesis is resolved from the temporal domain. By the fact that dis-occlusions belong to the background, firstly we build an online background under a newly designed Switchable Gaussian Model (SGM), owning to its computationally simplicity and scene adaptivity. Then, real textures in the dis-occlusions are able to be recovered with the built background. Experimental results have verified the improvements in rendering quality and computation complexity by comparing to the conventional spatial filling methods and other temporal filling methods. © 2012 IEEE.

We present a convex optimization approach to dense stereo matching in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we are able to formulate stereo matching as a continuous convex quadratic program without performing complicated relaxations or approximations on the objective function. When disparity is modeled as a discrete random variable, the theoretical foundation of our approach can be analyzed from the perspective of probability theory. Our convex optimization framework supports adaptive correlation windows and can be implemented using CVX, the Matlab software for disciplined convex programming, in a straightforward manner. Furthermore, effective techniques for disparity refinement, which include an occlusion detection algorithm performed on a single disparity map that takes advantage of the valuable information provided by the permutation matrix, and a plane fitting method mainly based on minimizing the l1 norm of the disparity errors caused by a disparity plane, are also proposed. Experimental results show that by minimizing our convex objective function and applying the proposed disparity refinement techniques, we are able to generate good quality disparity maps.

View synthesis is a technique to generate images/videos in a virtual viewpoint. In this paper, the dis-occlusion/hole problem in view synthesis is resolved from the temporal domain. By the fact that dis-occlusions belong to the background, firstly we build an online background under a newly designed Switchable Gaussian Model (SGM), owning to its computationally simplicity and scene adaptivity. Then, real textures in the dis-occlusions are able to be recovered with the built background. Experimental results have verified the improvements in rendering quality and computation complexity by comparing to the conventional spatial filling methods and other temporal filling methods. © 2012 IEEE.

in this paper, a novel plane fitting algorithm with low complexity and high accuracy is proposed to refine the depth maps generated by stereo matching. We first compute the confidence coefficient for each pixel in the depth map by cross checking and stable pixel calculation. According to the outlier pixel percentage for each segment, we choose one method, either proposed weighted least square error based or RANSAC based plane fitting algorithm, to estimate the plane parameters. Experimental results show that our method outperforms other existing plane fitting algorithms.

In this paper, we present a view synthesis method named Visto which aims to generate seamless novel views from a monocular view input. We formulate the problem as joint optimization of inter-view texture similarity and geometry preservation, which significantly differs from traditional view synthesis framework. In this way, the image characteristics of virtual view are inherently inherited from the reference view without introducing any image prior or texture modeling technique. The energy function is minimized using Gauss-Seidel-like approach, and the quality of the virtual view is refined iteratively. The proposed approach also tolerates small depth map errors. Further more, the algorithm is parallel friendly. The simulation results outperform several existing state-of-the-art monocular view synthesis systems. © 2012 ACM.

We present a convex optimization approach to dense stereo matching in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we are able to formulate stereo matching as a continuous convex quadratic program without performing complicated relaxations or approximations on the objective function. When disparity is modeled as a discrete random variable, the theoretical foundation of our approach can be analyzed from the perspective of probability theory. Our convex optimization framework supports adaptive correlation windows and can be implemented using CVX, the Matlab software for disciplined convex programming, in a straightforward manner. Furthermore, effective techniques for disparity refinement, which include an occlusion detection algorithm performed on a single disparity map that takes advantage of the valuable information provided by the permutation matrix, and a plane fitting method mainly based on minimizing the l1 norm of the disparity errors caused by a disparity plane, are also proposed. Experimental results show that by minimizing our convex objective function and applying the proposed disparity refinement techniques, we are able to generate good quality disparity maps.

View synthesis is a technique to generate images/videos in a virtual viewpoint. In this paper, the dis-occlusion/hole problem in view synthesis is resolved from the temporal domain. By the fact that dis-occlusions belong to the background, firstly we build an online background under a newly designed Switchable Gaussian Model (SGM), owning to its computationally simplicity and scene adaptivity. Then, real textures in the dis-occlusions are able to be recovered with the built background. Experimental results have verified the improvements in rendering quality and computation complexity by comparing to the conventional spatial filling methods and other temporal filling methods. © 2012 IEEE.

in this paper, a novel plane fitting algorithm with low complexity and high accuracy is proposed to refine the depth maps generated by stereo matching. We first compute the confidence coefficient for each pixel in the depth map by cross checking and stable pixel calculation. According to the outlier pixel percentage for each segment, we choose one method, either proposed weighted least square error based or RANSAC based plane fitting algorithm, to estimate the plane parameters. Experimental results show that our method outperforms other existing plane fitting algorithms.

In this paper, we present a view synthesis method named Visto which aims to generate seamless novel views from a monocular view input. We formulate the problem as joint optimization of inter-view texture similarity and geometry preservation, which significantly differs from traditional view synthesis framework. In this way, the image characteristics of virtual view are inherently inherited from the reference view without introducing any image prior or texture modeling technique. The energy function is minimized using Gauss-Seidel-like approach, and the quality of the virtual view is refined iteratively. The proposed approach also tolerates small depth map errors. Further more, the algorithm is parallel friendly. The simulation results outperform several existing state-of-the-art monocular view synthesis systems. © 2012 ACM.

In depth map coding for 3D video coding systems, coding errors in edges can severely affect the synthesis quality. Edge errors mainly compose of two parts: one is blurring and ringing artifact around sharp edge and the other is fake edge caused by blocking artifact. In this paper, we propose an adaptive depth map filter to remove blocking artifacts while preserving depth edges. The proposed filter is designed based on bilateral filter, in which the range kernel parameter is changed adaptively considering the strength of edges and blocking artifacts. Experimental results demonstrate that the proposed depth map filter can achieve up to 0.41 dB gain on the synthesis quality compared to the deblocking filter in MVC at low bit rate.

We present a novel convex-optimization approach to solving the dense stereo matching problem in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we directly formulate the stereo matching problem as a continuous convex quadratic program in a simple, elegant and straightforward manner without performing any complicated relaxation or approximation. By using CVX, the Matlab software for disciplined convex programming, our method is extremely simple to implement. © 2011 IEEE.

Single camera stereo system utilizes mirrors and a single camera for computational stereo, where the mirrors provide extra views needed for stereo and 3D reconstruction. In this paper, we investigate the basic epiploar geometric properties of the single camera stereo image and propose a novel image rectification technique to map the epipolar lines in the original image into the horizontally aligned lines in the rectified image. Besides, the rotation angles of the single camera corresponding to the planar mirror are derived during rectification. Experimental results show the robustness and accuracy of our method. © 2011 IEEE.

View synthesis offers a great flexibility in generating free viewpoint television (FTV) and 3D video (3DV). However, the depth-image-based view synthesis approach is very sensitive to errors in the camera parameters or poorly estimated depth maps (also called depth images). Because of these errors, three kinds of artifacts (blurring, contour, hole) are possibly introduced during the general synthesis process. Comparing to conventional methods which implement the view synthesis only in ideal case, in this paper, we propose to design an error compensation and reliability based view synthesis system where the potential errors are considered. The main contributions are highlighted as follows: Firstly, the camera parameter errors are compensated by a global homography transformation matrix. Secondly, the depth maps are classified into both reliable and unreliable regions and the reliability based weighting masks are built to blend synthesized images from two different views together. Finally, a reliability depth map based hole-filling technique is used to fill the existing holes. The experimental results demonstrate that these artifacts are efficiently reduced in the synthesized images. © 2011 IEEE.

When encrypted data need to be sent to an untrusted computer for processing, it is highly desirable to have a homomorphic cryptosystem that allows the untrusted computer to process the encrypted signals totally without decryption such that, when the encrypted domain result is decrypted, the decrypted value is the same as the equivalent plaintext domain operation. These operations range from basic arithmetic operations to complicated transformations. In this paper, we analyze the existence of equivalent operations in the encrypted domain for four of the common bitwise operations: OR, AND, NOR and NAND in plaintext domain. We will show that such equivalent operations should not exist. For otherwise, if such operations exist, the RSA cryptosystems can be broken by a low-complexity attack. © 2011 IEEE.

When encrypted data need to be sent to an untrusted computer for processing, it is highly desirable to have a homomorphic cryptosystem that allows the untrusted computer to process the encrypted signals totally without decryption such that, when the encrypted domain result is decrypted, the decrypted value is the same as the equivalent plaintext domain operation. These operations range from basic arithmetic operations to complicated transformations. In this paper, we analyze the existence of equivalent operations in the encrypted domain for four of the common bitwise operations: OR, AND, NOR and NAND in plaintext domain. We will show that such equivalent operations should not exist. For otherwise, if such operations exist, the RSA cryptosystems can be broken by a low-complexity attack. © 2011 IEEE.

We present a novel convex-optimization approach to solving the dense stereo matching problem in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we directly formulate the stereo matching problem as a continuous convex quadratic program in a simple, elegant and straightforward manner without performing any complicated relaxation or approximation. By using CVX, the Matlab software for disciplined convex programming, our method is extremely simple to implement. © 2011 IEEE.

Single camera stereo system utilizes mirrors and a single camera for computational stereo, where the mirrors provide extra views needed for stereo and 3D reconstruction. In this paper, we investigate the basic epiploar geometric properties of the single camera stereo image and propose a novel image rectification technique to map the epipolar lines in the original image into the horizontally aligned lines in the rectified image. Besides, the rotation angles of the single camera corresponding to the planar mirror are derived during rectification. Experimental results show the robustness and accuracy of our method. © 2011 IEEE.

View synthesis offers a great flexibility in generating free viewpoint television (FTV) and 3D video (3DV). However, the depth-image-based view synthesis approach is very sensitive to errors in the camera parameters or poorly estimated depth maps (also called depth images). Because of these errors, three kinds of artifacts (blurring, contour, hole) are possibly introduced during the general synthesis process. Comparing to conventional methods which implement the view synthesis only in ideal case, in this paper, we propose to design an error compensation and reliability based view synthesis system where the potential errors are considered. The main contributions are highlighted as follows: Firstly, the camera parameter errors are compensated by a global homography transformation matrix. Secondly, the depth maps are classified into both reliable and unreliable regions and the reliability based weighting masks are built to blend synthesized images from two different views together. Finally, a reliability depth map based hole-filling technique is used to fill the existing holes. The experimental results demonstrate that these artifacts are efficiently reduced in the synthesized images. © 2011 IEEE.

We present a novel convex-optimization approach to solving the dense stereo matching problem in computer vision. Instead of directly solving for disparities of pixels, by establishing the connection between a permutation matrix and a disparity vector, we directly formulate the stereo matching problem as a continuous convex quadratic program in a simple, elegant and straightforward manner without performing any complicated relaxation or approximation. By using CVX, the Matlab software for disciplined convex programming, our method is extremely simple to implement. © 2011 IEEE.

When encrypted data need to be sent to an untrusted computer for processing, it is highly desirable to have a homomorphic cryptosystem that allows the untrusted computer to process the encrypted signals totally without decryption such that, when the encrypted domain result is decrypted, the decrypted value is the same as the equivalent plaintext domain operation. These operations range from basic arithmetic operations to complicated transformations. In this paper, we analyze the existence of equivalent operations in the encrypted domain for four of the common bitwise operations: OR, AND, NOR and NAND in plaintext domain. We will show that such equivalent operations should not exist. For otherwise, if such operations exist, the RSA cryptosystems can be broken by a low-complexity attack. © 2011 IEEE.

View synthesis offers a great flexibility in generating free viewpoint television (FTV) and 3D video (3DV). However, the depth-image-based view synthesis approach is very sensitive to errors in the camera parameters or poorly estimated depth maps (also called depth images). Because of these errors, three kinds of artifacts (blurring, contour, hole) are possibly introduced during the general synthesis process. Comparing to conventional methods which implement the view synthesis only in ideal case, in this paper, we propose to design an error compensation and reliability based view synthesis system where the potential errors are considered. The main contributions are highlighted as follows: Firstly, the camera parameter errors are compensated by a global homography transformation matrix. Secondly, the depth maps are classified into both reliable and unreliable regions and the reliability based weighting masks are built to blend synthesized images from two different views together. Finally, a reliability depth map based hole-filling technique is used to fill the existing holes. The experimental results demonstrate that these artifacts are efficiently reduced in the synthesized images. © 2011 IEEE.

Single camera stereo system utilizes mirrors and a single camera for computational stereo, where the mirrors provide extra views needed for stereo and 3D reconstruction. In this paper, we investigate the basic epiploar geometric properties of the single camera stereo image and propose a novel image rectification technique to map the epipolar lines in the original image into the horizontally aligned lines in the rectified image. Besides, the rotation angles of the single camera corresponding to the planar mirror are derived during rectification. Experimental results show the robustness and accuracy of our method. © 2011 IEEE.

This paper presents a super-resolution method based on gradient-based adaptive interpolation. In this method, in addition to considering the distance between the interpolated pixel and the neighboring valid pixel, the interpolation coefficients take the local gradient of the original image into account. The smaller the local gradient of a pixel is, the more influence it should have on the interpolated pixel. And the interpolated high resolution image is finally deblurred by the application of wiener filter. Experimental results show that our proposed method not only substantially improves the subjective and objective quality of restored images, especially enhances edges, but also is robust to the registration error and has low computational complexity., Comment: 4pages, 7figures, This paper presents a super-resolution method based on gradient-based adaptive interpolation