Benefiting from the excellent global expression ability, transformer-based image super-resolution (SR) has made significant progress. However, the existing transformer-based SR methods still have the problem of high-frequency information reconstruction loss when processing remote sensing images due to their wide imaging range, rich high-frequency information and large differences, which affects the characterization ability of the transformer. In addition, the high computational overhead is unacceptable. To alleviate the above problems, we consider the remote sensing image SR from the perspective of the frequency domain. Specifically, we propose an efficient frequency decoupling-fusion remote sensing image SR framework, which is called FDFNet. In particular, we consider that when a large amount of previous work was carried out to extract features in the spatial domain, it was very easy to lose the high-frequency information in the original image. Therefore, we first introduce a frequency decoupling block (FDB), which decouples the image into low-frequency and high-frequency components, processes high-frequency and low-frequency information respectively in a divide-and-conquer manner, and restores high-frequency details before delving deeper. Furthermore, we notice that spatial self-attention is a low-pass filter that tends to have global perception and to demonstrate limitations in reconstructing high-frequency details. Therefore, we meticulously designed a parallel frequency-aware transformer module (PFTM) to extract spatial frequency attention and channel transposition attention, which enables our model to focus more on local texture details to restore high-frequency details. A large number of experimental results on multiple public datasets show that our FDFNet outperforms the state-of-the-art SR methods in quantitative metrics and visual quality, and achieves a balance between performance and efficiency within a limited computing budget.

The emotion-cause pair extraction (ECPE) task is to simultaneously extract emotions and causes as pairs (EC-pairs) from documents, which is important for natural language processing. Previous research tackled this task via a two-step approach, which first predicts separately the emotion and cause clauses, and then pairs them up by using a binary classifier. However, such a two-step approach may suffer from the possible propagation of errors, and it neglects the interaction between emotions and causes. In this article, an end-to-end double-graph method with relational enhancement (DGRE) is proposed to stimulate two relationship modes among clauses, i.e., semantic dependence and logical dependence. First, two united graph encoders are established to embed the semantic dependence into the representation of clauses and pairs. The first encoder is built on graph attention networks (GATs) for clause-level representation, the result of which is used by a relational graph convolutional network (RGCN) for the refinement of pair-level representation. Aiming to enhance the fitting ability of logical dependence, the emotion-type classification task is introduced into the multitask learning framework of GATs, which can effectively distinguish the logical relations between clauses according to their emotion types. Moreover, seven types of dependence relations have been designed for the node connections in RGCN, which emphasize the contextual interaction and clustering among neighboring nodes. Experiments on a benchmark Chinese corpus demonstrate that the proposed DGRE approach could effectively establish the communication mechanism between clauses and pairs from multiple perspectives, and comparisons with state-of-the-art (SOTA) models well validate its effectiveness.

Image explicit prior has made breakthrough progress in the super-resolution (SR) due to the additional supervisory information provided. However, existing explicit prior-guided SR methods directly use the Gaussian gradient or Laplacian gradient prior, which cannot fit the gradient distribution of remote sensing images. Through the statistics of gradient probability density distribution of the remote sensing image dataset, we found that the hyper-Laplacian prior can fit the heavy-tailed distribution better, which aroused us to use the hyper-Laplacian before facilitating the SR reconstruction. We propose a novel hyper-Laplacian prior SR method for remote sensing images in this manuscript. Specifically, our model consists of three components: rough reconstruction subnetwork (RRS), hyper-Laplacian prior subnetwork (HPS), and image refinement enhancement subnetwork (RES). In the RRS, we reconstruct low-resolution (LR) images into rough SR images by a set of resblocks. In the HPS, we first introduce the hyper-Laplacian prior for LR images to provide an additional texture. Hereafter, we set up a prior loss which imposes a second-order supervision on the SR image. Like the previous image space loss function, it helps the model to gather the geometric structure of the image. Finally, the outputs of the RRS and HPS are fused and then fed to the RES for high-quality image reconstruction. Numerous studies of SR reconstruction and segmentation on UCMerced, PatternNet, and OpenBayes datasets confirm that our method is superior compared to state-of-the-art methods.

Face hallucination in low-light environments is an extremely challenging task due to the significant loss of facial structure and facial texture information. Although cascading image relighting and face hallucination tasks is a feasible strategy, simply cascading these two tasks does not achieve satisfactory results because they do not fit into each other naturally. In this article, we propose a novel duplex fusing-embedding learning approach to tackle this challenge in low-light environments. The core of the proposed approach is the duplexity of feature fusion and embedding between relighting and hallucination tasks. In the feature fusion phase, the shallow features from two tasks are bidirectionally fused and activated into a consistent feature space. In the feature embedding phase, the fused features from the previous iteration are fed back and bidirectionally embedded into the deep features of two tasks in the current iteration so that they can learn feature representations that consistently represent both tasks, thereby boosting the performance of relighting and hallucination to generate photorealistic HR face images. Experimental results show that the proposed approach allows current face hallucination methods to learn to hallucinate face in the dark.

Recently, facial priors (e.g., facial parsing maps and facial landmarks) have been widely employed in prior-guided face super-resolution (FSR) because it provides the location of facial components and facial structure information, and helps predict the missing high-frequency (HF) information. However, most existing approaches suffer from two shortcomings: 1) the extracted facial priors are inaccurate since they are extracted from low-resolution (LR) or low-quality super-resolved (SR) face images and 2) they only consider embedding facial priors into the reconstruction process from LR to SR face images, thus failing to explore facial priors to generate LR face image. In this article, we propose a novel pre-prior guided approach that extracts facial prior information from original high-resolution (HR) face images and embeds them into LR ones to obtain HF information-rich LR face images, thereby improving the performance of face reconstruction. Specifically, a novel component hybrid method is proposed, which fuses HR facial components and LR facial background to generate new LR face images (namely, LRmix) via facial parsing maps extracted from HR face images. Furthermore, we design a component hybrid network (CHNet) that learns the LR to LRmix mapping function to ensure that the LRmix can be obtained from LR face images in testing and real-world datasets. Experimental results show that our proposed scheme significantly improves the reconstruction performance for FSR.

Recently, face hallucination methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e.g., facial parsing maps and landmarks) to focus on global facial structure and constrain facial texture generation. However, the limited receptive fields of CNNs and inaccurate facial priors will reduce the naturalness and fidelity of restored face. In this paper, we propose a FaceFormer that aggregates global representation of Transformers and local representation of CNNs to maintain the consistency of facial structure while restoring local facial details. The reason for this design is that the Transformer can capture global facial information by exploiting the long-distance visual relation modeling, while the local modeling capability of CNNs can recover fine-grained facial details. Therefore, aggregating these two independent representations can help to maximize their merits and reconstruct high-quality and high-fidelity face images. Experimental results of face reconstruction and recognition verify that the proposed FaceFormer significantly outperforms current state-of-the-arts.

Image fusion synthesizes a new image from multiple images of the same scene. The synthesized image should be suitable for human visual perception and follow-up high-level image-processing tasks. However, existing methods focus on fusing low-level features, ignoring high-level semantic perception information. We propose a new end-to-end model to obtain a more semantically consistent image in infrared and visible image fusion, termedsemantic-supervised dual-discriminator generative adversarial network(SDDGAN). In particular, we design an information quantity discrimination (IQD) block to guide fusion progress. For each source image, the block determines the weight for preserving each semantic object’s feature. By this way, the generator learns to fuse various semantic objects via different weights to preserve their characteristics. Moreover, the dual discriminator is employed to identify the distribution of infrared and visible information in the fused image. Each discriminator acts on a certain modality (infrared/visible) of different semantic objects in the fused image to preserve and enhance their modality features. Thus, our fused image is more informative. Both the thermal radiation in the infrared image and the visible image texture details can be well preserved. Qualitative and quantitative experiments demonstrate the superiority of our SDDGAN over state-of-the-art methods in terms of visual effects, efficiency, and quantitative metrics.

The structure and texture of images are crucial for remote sensing image super-resolution. Generative adversarial networks (GANs) recover image details through adversarial training. However, the recovered images always have structural distortions on the one hand, and GANs are difficult to train on the other hand. In addition, some methods assist reconstruction by introducing prior information of the image, but this brings additional computational cost. To address this issue, we propose a novel structure-texture parallel embedding (SPE) method for super-resolution (SR) of remote sensing images. Our method does not require additional image priors to reconstruct high-quality images. Specifically, we use the global structure information and local texture information of the image in the ascending space to guide the reconstruction result of the image. Firstly, we design a structure preserving block (SPB) to extract global structural features in the ascending space of the image, so as to obtain global structure information for a priori representation. Then, we design a local texture attention module (LTAM) to restore richer texture details. We have conducted lots of experiments on Draper public dataset. Experimental results show that our proposed method not only achieves a better trade-off between computational cost and performance, but also outperforms the existing several SR methods in terms of objective index evaluation and subjective visual effects.

Prototype learning is extensively used in few-shot semantic segmentation due to its excellent capability of semantic information extraction and effective prevention of overfitting. The previous prototype based methods ignore the frequency discrepancy inside the object, thereby leading to semantic confusion of the object. In this paper, we propose a frequency guided network (FGNet) which explicitly models the semantic information of different frequencies and precisely guides the semantic alignment of the object. Specifically, the proposed FGNet consists of two modules: a frequency separation module (FSM) and a multi-guided feature enrichment module (MG-FEM) to complete the multi-frequency semantic information extraction and alignment, respectively. Experiments on PASCAL-$5^{i}$dataset show that our FGNet achieves mIoU score of 61.2% in 1-shot which surpasses the state-of-the-art methods.

Recently, most existing face SR methods only focus on generating pleasant texture details, even artifacts. Identity information is an important high-level face attribute, which is often ignored in the low-level super-resolution (SR) task. In view of this, we propose a dual-identity constraint dual-loop network (DIDnet), which employs identity information to constrain the SR model. First, the proposed framework consists of two closed-loop networks: one of the networks is used for generating high resolution (HR) images for exploring identity-preserving in HR feature space and the other one can learn degradation process for utilizing low resolution (LR) identity information. Furthermore, we integrate dual-identity constraints together for rendering characteristic facial images. Extensive experimental results are conducted on face databases and real-world data, which confirmed that the proposed DIDnet consistently and significantly improves both objective and subjective facial image reconstruction performances.

Recently, convolutional neural networks (CNNs) have been widely employed to promote the face hallucination due to the ability to predict high-frequency details from a large number of samples. However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e.g., face detection, facial recognition). To tackle this issue, we propose a novel external-internal split attention group (ESAG), which encompasses two paths responsible for facial structure information and facial texture details, respectively. By fusing the features from these two paths, the consistency of facial structure and the fidelity of facial details are strengthened at the same time. Then, we propose a split-attention in split-attention network (SISN) to reconstruct photorealistic high-resolution facial images by cascading several ESAGs. Experimental results on face hallucination and face recognition unveil that the proposed method not only significantly improves the clarity of hallucinated faces, but also encourages the subsequent face recognition performance substantially. Codes have been released at https://github.com/mdswyz/SISN-Face-Hallucination.

Recently, the performances of deep convolution neural networks (CNNs)-based single-image super-resolution (SISR) have been significantly improved. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper networks and ignore the potential relationship between multi-scale features, leading to the limited representation ability of the reconstructed network. To address this problem, we propose a new multi-scale information polymerization network (MIPN). Specifically, we propose a multi-scale information polymerization block (MIPB), which uses convolution layers of different convolution kernel sizes to extract multi-scale image features, and effectively polymerizate the extracted features together to obtain fine image features. Moreover, we also propose a shallow residual block in MIPB. Compared with the traditional convolution layer, this proposed block can effectively extract image features without increasing the number of parameters. Extensive experiments show that the proposed method performs better than several state-of-the-art methods in quantitative and visual quality indicators.

Recently, Retinex theory based low-light image enhancement (LLIE) algorithms have achieved impressive results in controlled environment. However, the majority of deep learning based LLIE algorithms leverage relighting by enhancing the illumination components that directly determines the image brightness, regretfully, they ignore the information of reflectance components, which may cause problems such as image noise and color distortion in reconstructed images. To tackle this problem, in this letter, we propose a component enhancement network based on Generative Adversarial Network (Component-GAN) for recovering clear images from low-light ones. Specifically, the network is composed of the decomposition part for dividing the paired low/normal-light images into illumination components and reflectance components, and the enhancement part for generating high-quality images. It is worth to note that we provide two branches of component enhancement network, which are parallel to improve the two components simultaneously. Hereby, we treat the reconstruction part as the generative network and adopt discriminative network to boost image reconstruction performance. Through extensive experiments, the proposed approach outperforms some state-of-the-art LLIE methods in terms of visual and subjective qualities.

Image alignment/registration/correspondence is a critical prerequisite for many vision-based tasks, and it has been widely studied in computer vision. However, aligning images from different domains, such as cross-weather/season road scenes, remains a challenging problem. Inspired by the success of classic intensity-constancy-based image alignment methods and the modern generative adversarial network (GAN) technology, we propose a cross-weather road scene alignment method called latent generative model with intensity constancy. From a novel perspective, the alignment problem is formulated as a constrained 2D flow optimization problem with latent encoding, which can be decoded into an intensity-constancy image on the latent image manifold. The manifold is parameterized by a pre-trained GAN, which is able to capture statistic characteristics from large datasets. Moreover, we employ the learned manifold to constrain the warped latent image identical to the target image, thereby producing a realistic warping effect. Experimental results on several cross-weather/season road scene datasets demonstrate that our approach can significantly outperform the state-of-the-art methods.

Sparsity and locality regularizations are successfully applied to face hallucination algorithms to ameliorate their ill-posed nature. However, most of patch-based face hallucination approaches only consider the manifold structure of single patch, thus resulting in unstable solution for image reconstruction. In this paper, we propose a novel face hallucination, termed manifold-regularized group locality-constrained representation (MGLR), in order to exploit the multiple manifold structures rooted in grouped self-similarly patches. Specifically, we first group similar patches to form a matrix which contains the recurrent non-local patches. Then graph regularization term is formulated to represent the group manifolds for better reconstruction quality. Taking advantages of grouped self-similar patches, MGLR can offer stable sparse solution to take advantage of the the accurate prior for super-resolution reconstruction. Experimental results on LFW database and CMU real-world images demonstrate the superiority of the proposed method over some state-of-the-art face methods both in terms of subjective and objective qualities.

Automatic protocol mining is a promising approach for inferring accurate and complete API protocols. However, just as with any data-mining technique, this approach requires sufficient training data (object usage scenarios). Existing approaches resolve the problem by analyzing more programs, which may cause significant runtime overhead. In this paper, we propose an inheritance-based oversampling approach for object usage scenarios (OUSs). Our technique is based on the inheritance relationship in object-oriented programs. Given an object-oriented program p , generally, the OUSs that can be collected from a run of p are not more than the objects used during the run. With our technique, a maximum of n times more OUSs can be achieved, where n is the average number of super-classes of all general OUSs. To investigate the effect of our technique, we implement it in our previous prototype tool, ISpecMiner, and use the tool to mine protocols from several real-world programs. Experimental results show that our technique can collect 1.95 times more OUSs than general approaches. Additionally, accurate and complete API protocols are more likely to be achieved. Furthermore, our technique can mine API protocols for classes never even used in programs, which are valuable for validating software architectures, program documentation, and understanding. Although our technique will introduce some runtime overhead, it is trivial and acceptable.

Most deep learning based face hallucinations exploit random patch prior from training samples, then to learn the mapping functions between low-resolution (LR) and high-resolution (HR) images, and achieve satisfactory reconstruction performance. However, most of them do not take into account the prior information on facial structure, which is pivotal for face hallucination. Different from random patch prior based deep learning approaches, in this paper, we utilize facial structural prior and develop a simple yet powerful face hallucination, named region-based deep convolutional networks (RDCN). Firstly, we divide facial image into several regions of interest, then to train multiple parallel subnetworks of these regions for exacting better structure priors, finally HR output is reconstructed by stitching facial parts. Experiments on the FEI database demonstrate that the proposed region-based convolution networks outperform other state-of-the-art, including recently proposed deep learning based approaches, both in subjective and objective reconstruction qualities.

In this paper, we propose a novel closed-form transformation estimation method based on moving regularized least squares optimization with thin-plate spline (MRLS-TPS) for non-rigid image deformation. The method takes the user-controlled point-offset-vectors as the input data, and estimates the spatial transformation about the two control point sets for each pixel. To achieve a realistic deformation, we formulates the transformation estimation as a vector-field interpolation problem by a moving regularized least squares method. Unlike MLS, the mapping function is modeled by a non-rigid function thin-plate spline with regularization technique, such that the deformation can satisfy both global linear affine motion and local non-rigid warping. We derive a closed-form solution of the transformation and achieve a fast implementation. In addition, the proposed method can give a wonderful user experience, fast and convenient manipulating. Extensive experiments on real images demonstrated the proposed method outperforms other state-of-the-art methods and the commercial software Adobe PhotoShop CS 6, especially in case of flexible object motion.

Learning-based face super-resolution approaches rely on representative dictionary as self-similarity prior from training samples to estimate the relationship between the low-resolution (LR) and high-resolution (HR) image patches. The most popular approaches, learn mapping function directly from LR patches to HR ones but neglects the multi-layered nature of image degradation process (resolution down-sampling) which means observed LR images are gradually formed from HR version to lower resolution ones. In this paper, we present a novel deep linear mappings learning framework for face super-resolution to learn the complex relationship between LR features and HR ones by alternately updating multi-layered embedding dictionaries and linear mapping matrices instead of directly mapping. Furthermore, in contrast to existing position based studies that only use local patch for self-similarity prior, we develop a feature-induced nonlocal dictionary pair embedding method to support hierarchical multiple linear mappings learning. With coarse-to-fine nature of deep learning architecture, cascaded incremental linear mappings matrices can be used to exploit the complex relationship between LR and HR images. Experimental results demonstrate that such framework outperforms state-of-the-art (including both general super-resolution approaches and face super-resolution approaches) on FEI face database.

The Microsoft Kinect sensor has been widely used in many applications, but it suffers from the drawback of low depth accuracy. In this paper, we present a unified depth modification model to improve the Kinect depth accuracy by registering depth and color images in an iterative manner. Specifically, in each iteration, we first establish a coarse correspondence based on the feature descriptor of the canny edge. Then, we estimate the fine correspondence using a robust estimator called the L2E with the nonparametric model. Finally, we correct the depth data according to the correspondence results. In order to evaluate the effectiveness of our approach, we have performed extensive experiments and then analyzed the experimental results from the following respects: the accuracy of depth data, the accuracy of correspondence between color and depth images as well as the measurement error in the 3D reconstruction by our method. The experimental results show that our approach greatly improves the depth accuracy.

In this paper, a novel closed-form transformation estimation method based on feature guided moving least squares together with manifold regularization is proposed for nonrigid image/surface deformation. The method takes the user-controlled point-offset-vectors and the feature points of the image/surface as input, and estimates the spatial transformation between the two control point sets for each pixel/voxel. To achieve a detail-preserving and realistic deformation, the transformation estimation is formulated as a vector-field interpolation problem using a feature guided moving least squares method, where a manifold regularization is imposed as a prior on the transformation to capture the underlying intrinsic geometry of the input image/surface. The non-rigid transformation is specified in a reproducing kernel Hilbert space. We derive a closed-form solution of the transformation and adopt a sparse approximation to achieve a fast implementation, which largely reduces the computation complexity without performance sacrifice. In addition, the proposed method can give a wonderful user experience, fast and convenient manipulating. Extensive experiments on both 2D and 3D data demonstrate that the proposed method can produce more natural deformations compared with other state-of-the-art methods.

Patch-based face hallucination algorithms utilize either local patches (e.g., position-patch approaches) or nonlocal patches (e.g., dictionary-learning approaches) to exploit self-similarity prior from training samples. Although they yield decent results, solo source patches limit their performance due to not fully taking self-similarity prior from both local and nonlocal ones. In order to overcome this shortcoming, we propose a novel and efficient deep collaborative representation (DCR) based approach, to exploit both local and nonlocal self-similarity patches, for boosting face hallucination performance. First we learn a feature-inducing dictionary pair to represent local and nonlocal self-similarity prior, then deep (multiple-layer) representation weights and corresponding support dictionaries are iteratively updated to exploit accurate prior from coarse to fine. Finally, the high resolution (HR) output are optimized layer by layer. Experimental results outperform some state-of-the-art (e.g. Convolutional Neural Network based deep learning approach) which verify the validity of the proposed approach.

Dynamic Protocol Mining (DPM) techniques are a promising approach to infer useful API protocols automatically.However, their results are biased to input test cases and the instrumentation overhead discounts their usability in industrial practice.In this paper, we propose a distributed dynamic protocol mining framework NSpecMiner.Our framework is based on a client-server architecture, where the client tracer gathers Program Execution Traces (PETs) and sends them to the server for mining.Mined protocols are saved on the server to provide various kinds of remote services, such as API protocol retrieval and program verification, etc.Compared with local miners, NSpecMiner has many advantages: 1) A large number of diverse PETs are likely to be collected from multiple clients, which is essential for mining accurate and complete API protocols.2) Instrumentation overhead can be balanced among multiple clients.3) Via integrating the client tracer into widely used software, we can mine API protocols transparently and automatically without any human effort.To evaluate our technique, we performed a comparison test with a local miner ISpecMiner and NSpecMiner.Preliminary results show that our approach is effective to mine useful API protocols as local miners.While our method is able to gather PETs concurrently from multiple clients and other merits of the distributed technology will further benefit DPM significantly.

Static analysis is an efficient approach for software assurance. It is indicated that its most effective usage is to perform analysis in an interactive way through the software development process, which has a high performance requirement. This paper concentrates on rule-based static analysis tools and proposes an optimized rule-checking algorithm. Our technique improves the performance of static analysis tools by filtering vulnerability rules in terms of characteristic objects before checking source files. Since a source file always contains vulnerabilities of a small part of rules rather than all, our approach may achieve better performance. To investigate our technique’s feasibility and effectiveness, we implemented it in an open source static analysis tool called PMD and used it to conduct experiments. Experimental results show that our approach can obtain an average performance promotion of 28.7% compared with the original PMD. While our approach is effective and precise in detecting vulnerabilities, there is no side effect.

Recognition tasks in very low-resolution (VLR) images are more challenging than those in high-resolution (HR) due to lack of adequate discriminative information. Previous VLR and HR coupled learning scheme limits both the representation and discriminative ability of features. In this work, we propose a semi-coupled locality-constrained representation (SLR) approach to learn the discriminative representations and the mapping relationship between VLR and HR features simultaneously. Both VLR and HR local manifold geometries are coded during representation, while the learned mapping function improves the manifold consistency by transforming VLR features to HR ones. Finally, the resolutionrobust features are fed into a sparse representation based classifier (SRC) to predict the face labels. The proposed algorithm gives better performance than many state-of-the-art VLR recognition algorithms.

In this paper, we proposed an improved Iterative Closest Point (ICP) algorithm which based on features with the discrete selection mechanism for motion estimation to reconstruct 3D map in indoor environment. We started with detecting, descripting and matching SURF features in consecutive RGB images. Moreover, due to the registration accuracy would be influenced by the initial pose of features in original ICP algorithm based on features, we did initial registration using RANdom Sample Consensus (RANSAC) algorithm to optimize the initial pose of features and remove the outliers. Furthermore, we presented a secondary registration method to calculate the refined transformation between point-clouds in the different coordinate systems with features selected by discrete selection mechanism. Finally, we optimized the global map using General Gragh Optimization (G2O) framework combining with key frames, and reconstructed the 3D map. We tested the performance of our proposed algorithm in six public datasets. The results demonstrate that the algorithm is feasible and effectively.

On the fundamental theory of Structure from Motion, we present an algorithm based on 3D-2D motion estimation monocular visual odometry. In order to resolve the problem of 3D-2D motion estimation, which need to maintain a consistent and accurate set of triangulated 3D feature points and to create precisely 3D-to-2D correspondences, and considering the complexity and variability of the outdoor scene and uncertainty of inter frame motion, a method of combining optical flow with feature matching is proposed. Experimental results show that the proposed algorithm can improve the accuracy effectively.

Recently, deep learning based face recognition algorithms have achieved great success in recognition performance. However, designing and training complex learning models suffer from time and labor efficiency. In this paper, we propose a novel three-layer low-rank supported extreme learning machine (LSELM) algorithm to take advantage of both robust feature representation and fast classification for efficient recognition. Every given probe sample is first clustered into a sub-class spanned by linear representation. With this sub-class, low-rank and robust features that are insensitive to disguise, noise, variant expression or illumination are recovered. These discriminative features are then coded to support a forward neural network for efficient prediction. Experimental results show that LSELM is on par with other deep learning based face recognition algorithms in recognition performance but has less time complexity on both AR and extend Yale-B datasets.

Class temporal specification is a kind of important program specifications, which specifies that methods of a class should be called in a particular sequence.Dynamic specification mining is a promising approach to achieve this kind of specifications automatically.However, they always infer partial specifications, that is, the mined specifications are biased to input programs or program execution traces.In this paper, we propose to mine class temporal specifications based on a probabilistic model in an online mode.Since our method can evolve mined specifications persistently, universal specifications can be achieved.To investigate our technique's feasibility and effectiveness, we implemented it in a prototype tool ISpecMiner and used the tool to perform experiments.Experimental results show that our method is promising to infer universal specifications if sufficient traces are provided for mining.

Automatic protocol mining is a promising approach to infer precise and complete API protocols.However, the effect of the approach largely depends upon the quality of input object usage scenarios, in terms of noise and diversity.This paper aims to extract as many object usage scenarios as possible from object-oriented programs for automatic protocol mining.A large corpus of object usage scenarios can help with eliminating noise accurately and is likely to be diverse.Therefore, precise and complete protocols may be achieved.Given an object-oriented program p, generally, object usage scenarios that can be collected from a run of p is not more than the number of instances used in p. Relying on the inheritance relationship among classes, our technique can extract a maximum of n times more object usage scenarios from p, where n is the average inheritance depth of all object usage scenarios in p.In order to investigate the effect of our technique on mining protocols, we implement it in our previous prototype tool ISpecMiner and use the tool to mine protocols from several real-world applications.The experimental results show that our technique is promising to achieve complete and precise API protocols.In addition, protocols of classes that have not been used in programs can be also achieved, which is helpful for program documentation and understanding.

In this paper, we present an efficient multiscale low-rank representation for image segmentation. Our method begins with partitioning the input images into a set of superpixels, followed by seeking the optimal superpixel-pair affinity matrix, both of which are performed at multiple scales of the input images. Since low-level superpixel features are usually corrupted by image noise, we propose to infer the low-rank refined affinity matrix. The inference is guided by two observations on natural images. First, looking into a single image, local small-size image patterns tend to recur frequently within the same semantic region, but may not appear in semantically different regions. The internal image statistics are referred to as replication prior, and we quantitatively justified it on real image databases. Second, the affinity matrices at different scales should be consistently solved, which leads to the cross-scale consistency constraint. We formulate these two purposes with one unified formulation and develop an efficient optimization procedure. The proposed representation can be used for both unsupervised or supervised image segmentation tasks. Our experiments on public data sets demonstrate the presented method can substantially improve segmentation accuracy.

Most of global face hallucination methods treat the face as a whole, ignoring the fact that the face is composed by part-based organs. Therefore, the results obtained by these methods always lack of detailed information. Nonnegative matrix factorization (NMF) based face hallucination method is properly used to enhance the detailed information. Usually, NMF basis is only learnt from high-resolution (HR) samples, leading to over-smooth output and lack of high frequency details. In order to solve this problem, we propose a simple but novel face hallucination method using nonnegative feature transformation by two-step framework. In particular, we learn the NMF basis from low-resolution (LR) and HR samples separately, and then transform the local representation feature of input into the global representation subspaces, keeping the weights into the HR samples space for output. Furthermore, the maximum a posteriori (MAP) method is used to estimate a better output. Experiments show that the hallucinated face of the proposed method is not only more high-frequency details, but also has better performance than many state-of-art algorithms.