Search

Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused on the search of a latent shared feature space where source and target domain data can be aligned either statistically and/or geometrically. In this paper, we propose a novel unsupervised DA method, namely Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation (DOLL-DA). The proposed DOLL-DA derives from a novel integrated model which searches a shared feature subspace where data labels are orthogonally regressed using a label embedding trick, and source and target domain data are discriminatively aligned statistically through optimization of some repulse force terms. Furthermore, in minimizing a novel Noise Robust Sparse Orthogonal Label Regression(NRS_OLR) term, the proposed model explicitly accounts for data outliers to avoid negative transfer and introduces the property of sparsity when regressing data labels. We carry out comprehensive experiments in comparison with 35 state of the art DA methods using 8 standard DA benchmarks and 49 cross-domain image classification tasks. The proposed DA method demonstrates its effectiveness and consistently outperforms the state-of-the-art DA methods with a margin which reaches 17 points on the CMU PIE dataset. To gain insight into the proposed DOLL-DA, we also derive three additional DA methods based on three partial models from the full model, namely OLR, CDDA+, and JOLR-DA, highlighting the added value of (1) discriminative statistical data alignment; (2) Noise Robust Sparse Orthogonal Label Regression; and (3) their joint optimization through the full DA model. In addition, we also perform time complexity and an in-depth empiric analysis of the proposed DA method in terms of its sensitivity w.r.t. hyper-parameters, convergence speed, impact of the base classifier and random label initialization as well as performance stability w.r.t. target domain data being used in training. [ABSTRACT FROM AUTHOR]

In this paper we present a novel visual tracking algorithm, in which object tracking is achieved by using subspace learning and Huber loss regularization in a particle filter framework. The changing appearance of tracked target is modeled by principle component analysis basis vectors and row group sparsity. This method takes advantage of the strengths of subspace representation and explicitly takes the underlying relationship between particle candidates into consideration in the tracker. The representation of each particle is learned via the multi-task sparse learning method. Huber loss function is employed to model the error between candidates and templates, yielding robust tracking. We utilize the alternating direction method of multipliers to solve the proposed representation model. In experiments we tested sixty representative video sequences that reflect the specific challenges of tracking and used both qualitative and quantitative metrics to evaluate the performance of our tracker. The experiment results demonstrated that the proposed tracking algorithm achieves superior performance compared to nine state-of-the-art tracking methods. [ABSTRACT FROM AUTHOR]

In view of the obvious shortcomings of single factor Lee-Carter model where mortality rate improves at constant rate, this paper, using Bayesian Markov Chain Monte Carlo (MCMC) method, gives a study on the predictive power of two-factor Lee-Carter model with Chinese actual population data. The test results indicate that two-factor model can preferably capture the volatility of mortality improvement and significantly outperform the original model in terms of goodness of fit and deviance information criteria (DIC). Moreover, comparisons of annuity prices, statistic characteristics, risk measurements and capital requirements between the two models show that the two-factor model, characterized by sharp peak and heavy tail feature of annuity price kernel density figure, should work together with the TVaR, instead of the traditional Solvency II and VaR principle, to better respond to the longevity risk of annuities caused by larger-than-expected mortality improvement. [ABSTRACT FROM AUTHOR]

This paper presents a novel framework for dynamic textures (DTs) modeling and recognition, investigating the use of chaotic features. We propose to extract chaotic features from each pixel intensity series in a video. The chaotic features in each pixel intensity series are concatenated to a feature vector, chaotic feature vector. Then, a video is modeled as a feature vector matrix. Next, two approaches of DTs recognition are investigated. A bag of words approach is used to represent each video as a histogram of chaotic feature vector. The recognition is carried out by 1-nearest neighbor classifier. We also investigate the use of earth mover's distance (EMD) method. Mean shift clustering algorithm is employed to cluster each feature vector matrix. EMD method is used to compare the similarity between two videos. The output of EMD matrix whose entry is the matching score can be used to DTs recognition. We have tested our approach on four datasets and obtained encouraging results which demonstrate the feasibility and validity of our proposed methods. [ABSTRACT FROM AUTHOR]

In this paper, a novel framework is proposed for dynamic textures (DTs) recognition by learning a high level feature using deep neural network (DNN). The insight behind the method is that a DT appearing in different videos should share similar features, which can be learned for better recognition performance. Unlike many prior works only focus on low level or middle level features, we propose a novel high level feature learning method using DNN. Our goal is to construct a compact and discriminative semantic feature. The conventional bag of features approach using k-means is not semantically meaningful since the clustering criterion is based on appearance similarity. The proposed framework can effectively overcome the problem by capturing the semantic relations of the middle level by DNN. Extensive experiments with qualitative and quantitative results demonstrate the efficacy of our approach. [ABSTRACT FROM AUTHOR]

We propose a new tracking method based on a group sparsity learning model. Previous work on sparsity tracking rely on a single sparse model to characterize the templates of tracking targets, which is hard to express complex tracking scenes. In this work, we utilize a superposition of multiple simpler sparse models to capture the structural information across templates. More specifically, our tracking method is formulated within particle filter framework and the particle representations are decomposed into two sparsity norms: a $$l_{1,\infty }$$ norm and a $$l_{1,2}$$ norm, capturing the common and different information across the templates, respectively. To efficiently implement the proposed tracker, we adapt the alternating direction method of multipliers to solve the formulated two-norm optimization problem. The proposed tracking method is compared with seven state-of-the-art trackers using 16 publicly available and challenging video sequences due to appearance changes, heavy occlusions, and pose variations. Experiment results show that our tracker outperforms the five other tracking methods. [ABSTRACT FROM AUTHOR]

Abstract: Probability hypothesis density (PHD) based trackers have enjoyed growing popularity in recent years, particularly in the field of nonlinear non-Gaussian visual tracking scenarios. These visual trackers can be degraded by a variety of factors, including changes of illumination, occlusion, poor image contrast, shape and appearance variation, clutter and other unmodeled changes of tracked objects. In this paper, for enhancing the performance of PHD based trackers, both scale invariant feature and color distribution feature are used as descriptors of targets of interest. To adaptively adjust the weights of each feature in the tracking process, a confidence measure, i.e., a quantitative measure for the spatial uncertainty of each feature is incorporated into the multifeature tracking algorithm. Experimental results show that the proposed multifeature tracker can improve the reliability and robustness of state estimation and the number estimation in tracking a variable number of objects of varying scales even when background region was similar to the object's appearance. [Copyright &y& Elsevier]

In leveraging manifold learning in domain adaptation (DA), graph embedding-based DA methods have shown their effectiveness in preserving data manifold through the Laplace graph. However, current graph embedding DA methods suffer from two issues: 1). they are only concerned with preservation of the underlying data structures in the embedding and ignore sub-domain adaptation, which requires taking into account intra-class similarity and inter-class dissimilarity, thereby leading to negative transfer; 2). manifold learning is proposed across different feature/label spaces separately, thereby hindering unified comprehensive manifold learning. In this paper, starting from our previous DGA-DA, we propose a novel DA method, namely ${A}$ ttention ${R}$ egularized Laplace ${G}$ raph-based ${D}$ omain ${A}$ daptation (ARG-DA), to remedy the aforementioned issues. Specifically, by weighting the importance across different sub-domain adaptation tasks, we propose the ${A}$ ttention ${R}$ egularized Laplace Graph for class aware DA, thereby generating the attention regularized DA. Furthermore, using a specifically designed FEEL strategy, our approach dynamically unifies alignment of the manifold structures across different feature/label spaces, thus leading to comprehensive manifold learning. Comprehensive experiments are carried out to verify the effectiveness of the proposed DA method, which consistently outperforms the state of the art DA methods on 7 standard DA benchmarks, i.e., 37 cross-domain image classification tasks including object, face, and digit images. An in-depth analysis of the proposed DA method is also discussed, including sensitivity, convergence, and robustness. [ABSTRACT FROM AUTHOR]

In marrying with Unmanned Aerial Vehicles (UAVs), the person re-identification (re-ID) techniques are further strengthened in terms of mobility. However, the simple hybridization brings unavoidable scale diversity and occlusions caused by the altitude and attitude variations during the flight of UAVs. To harmoniously blend the two techniques, in this research, we argue that the pedestrian should be globally perceived regardless of the scale variation, and the internal occlusions should also be well suppressed. For this purpose, we propose a novel Multi-granularity Attention in Attention (MGAiA) network to satisfy the raised demands for the aerial-based re-ID. Specifically, a novel multi-granularity attention (MGA) module is designed to supply the feature extraction model with a global awareness to explore the discriminative knowledge within scale variations. Subsequently, an Attention in Attention (AiA) mechanism is proposed to generate attention scores for measuring the importance of the different granularity, thereby proactively reducing the negative efforts caused by occlusions. We carry out comprehensive experiments on two large-scale UAV-based datasets including PRAI-1581 and P-DESTRE, as well as the transfer learning from three popular ground-based re-ID datasets CUHK03, Market-1501, and CUHK-SYSU to quantify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, an iterative algorithm is proposed to determine the pose of a planar target. The algorithm relies on the planar target whose size is known, and the pose of the target can be recovered by using coplanar points from only a single image. The iterative optimization algorithm includes two steps: first, the rough pose parameters are calculated by using the least square method based on the 2D-to-3D point correspondences, then, the rough pose is used as the initial guess for the optimal iterative algorithm which minimizes the reprojection errors for coplanar image points to determine the exact pose solution. Moreover, the corresponding image processing algorithm is addressed. The pose determination algorithm includes edge detection, line extraction, pose computing, etc. Simulation results concerning the effectiveness and accuracy of the method are presented; furthermore, experiments carried out on a variable geometry truss robot manipulator with eye-in-hand camera configuration for the autonomous capturing task demonstrate the robustness of the proposed method in the real environments. [ABSTRACT FROM AUTHOR]

Patients with extensive burns are critically ill and have long treatment periods. Length of stay (LOS) is a good measure for assessing treatment. This study sought to identify predictors of prolonged LOS in patients with extensive burns (≥50% TBSA). This retrospective multicenter cohort study included adults aged ≥ 18 years who survived extensive burns in three burn centers in Eastern China between January 2016 and June 2022. Epidemiological, demographic and clinical outcomes data were extracted from electronic medical records and compared between patients with/without prolonged LOS, which was defined as LOS greater than the median. Logistic regression analysis was used to identify predictors of prolonged LOS. The study sample included 321 patients, of whom 156 (48.6%) had an LOS of 58 days (IQR 41.0–77.0). Univariate regression analysis showed that increased total burn area and increased full-thickness burn area; electrical, chemical and other burns; increased erythrocytes, leukocytes, platelets or serum creatinine within 24 h of admission; concomitant inhalation injury, pulmonary edema, sepsis, bloodstream infection, wound infection, pulmonary infection, urinary tract infection, or HB < 70 g/L during hospitalization were associated with prolonged LOS in patients with extensive burns. Increased number of surgical operations, mechanical ventilation and renal replacement therapy were also associated with prolonged LOS (P < 0.05 or P < 0.001). Multivariate regression analysis revealed that increased total burn area (ratio 1.032, 95%CI 1.01–1.055; P = 0.004), electrical and chemical or other burns (3.282, 1.335–8.073; P = 0.01), development of wound infection (2.653 1.285–5.481; P = 0.008) and increased number of operative procedures (1.714, 1.388–2.116, P < 0.001) were significant predictors. Increased area of full-thickness burn,occurrence of electrical and chemical or other burns,occurrence of wound infection and increased number of surgeries are the best predictors of prolonged LOS in patients with extensive burns. Clarifying relevant predictors of burn patients' LOS provides a reliable reference for clinical treatment. • This study has examined the risk factors that contribute to prolonged hospital stays in patients with extensive burns. • The full-thickness burn area, causes of burns, wound infection and number of surgeries were the important factor. [ABSTRACT FROM AUTHOR]

Assistive aerial teleoperation in unknown environments can be challenging due to the limited sensing range of cameras and the insufficient human–computer interaction. Obstacles occluding the field of view (FOV) of camera reduce the visibility of unknown environments, and it coupled with insufficient pilot instructions directly affect human intention recognition. To address this issue, the planned trajectory generated by assistive teleoperation should align with human intention while considering perception awareness (PA) of the FOV. However, most of the existing works considering PA solely increase the FOV visibility while neglect the human intention constraints. As a result, the PA constraints can cause the heading of the quadrotor to deviate from human expectation, requiring more human–computer interactions to correct it. In this paper, we propose a human-guided motion planner with perception awareness to solve these issues. Specifically, in the path-finding stage, we introduce a spatio-temporal path similarity metric method. This method, combined with motion primitive propagation, finds an initial path that is collision-free and roughly aligned with human intention. In the subsequent trajectory optimization stage, we jointly consider PA with respect to occlusion and human intention constraints, effectively optimizing FOV visibility without deviating the heading of quadrotor from human intention. Extensive experiments and benchmark comparisons demonstrate the effectiveness of our proposed method in solving assistive aerial teleoperation for even novice operators. [ABSTRACT FROM AUTHOR]

Direct visual odometry (DVO) is an important vision task which aims to obtain the camera motion via minimizing the photometric error across the different correlated images. However, the previous research on DVO rarely considered the motion bias and only calculated using single direction, therefore potentially ignoring useful information compared with leveraging diverse directions. We assume that jointly considering forward and backward calculation can improve the accuracy of pose estimation. To verify our assumption and solid this contribution, in this paper, we test various combination of direct dense methods, including different error metrics, e.g., (intensity, gradient magnitude), alignment strategies (Forward-Compositional, Inverse-Compositional), and calculation directions (forward, backward, and bi-direction). We further study the issue of motion bias in RGB-D visual odometry and propose four strategy options to improve pose estimation accuracy, e.g., joint bi-direction estimation; two stage bi-direction estimation; transform average with weights; and transform fusion with covariance. We demonstrate the effectiveness and efficiency of our proposed algorithms across a range of popular datasets, e.g., TUM RGB-D and ICL-NUIM, in which we achieve an impressive performance through comparing with state of the art methods and provide benefits for existing RGB-D visual odometry and visual SLAM systems. [ABSTRACT FROM AUTHOR]

Interactive image segmentation has been an active research topic in image processing and computer graphics. One of its appealing advantage is the optimization of human feedback and interactions to generate user-desired results. Segmentation results of most previous methods usually depend on the quality and quantity of the user input. In this paper, we propose an algorithm to solve one important challenge arising from inputs with bad or limited quality. Our work is notably different from previous methods. First, the weakly interactive image segmentation is formulated and deduced in theory, then we propose to reconstruct enough samples via sparse reconstruction to enhance the robustness to weakly interactive labels. More importantly, we leverage interactive labels to extract a latent subspace which jointly optimizes multiclass classification and binary classification based on fisher rules. Numerous experiments are conducted on MSRC (Ning et al. in Interact Imaging Vis Pattern Recognit 43(2):445–456, 2010) and KIM (Kim et al. in: 2010 IEEE computer society conference on computer vision and pattern recognition, 2010) database. The results demonstrate effectiveness and efficiency of our method. [ABSTRACT FROM AUTHOR]

Numerous feature descriptors have been proposed for holistic facial analysis with satisfactory performances. However, few studies have been conducted on how to model the concept of facial beauty for face-related tasks. In addition, existing learning-based face recognition methods suffer from efficiency problems and rely heavily on a sufficient database. In this paper, we develop an efficient method which leverages the perception of human facial beauty for face recognition. Our work is notably different from previous face recognition works in several aspects: (1) we derive a set of facial features based on the fruits of facial attractiveness and beauty analysis research; (2) compared with traditional optimization-based learning methods, we propose simple yet effective C4.5 decision tree as classification model; (3) proposed method is invariant to both gesture variations and facial occlusions, which achieves good performance compared with a series of state-of-the-art methods. More importantly, we propose visualization experiments to verify the discriminative attributes of extracted features. In this paper, we start by preprocessing images in order to enhance image quality. Then, inspired by the facial beauty research, we design a set of new feature descriptors defined as natural feature. The extracted natural feature is embedded into C4.5 decision tree for supervised learning and classification. Extensive experiments are conducted on the AR database, FRGC database and Extended Yale B database. Comprehensive experiments and in-depth analysis verify the effectiveness and competitiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, the stability of nonlinear dynamic system for a multilink flexible manipulator (MLFM) is investigated by designing of linear observer to construct a closed-loop system such that for all admissible parameter uncertainties, unknown nonlinearities, and exogenous disturbances input. In a Lagrangian approach, one closed-loop augmented system is unfolded and proven to be asymptotically stable in the mean square (ASMS) by utilizing a Lyapunov theory. Further, if the stability of dynamic closed-loop system of the manipulator is maintained, a desired linear observer will be obtained by solving several algebraic Riccati inequalities. Simulation studies are used to verify the effectiveness of the proposed approach. One of the main contributions of this work is in the derivation of dynamic system stability with a suitable linear observer for the MLFM, based on Lyapunov theory, which: (1) explains physical mechanism for flexible-link movements and dynamics in a Lagrangian approach and (2) sufficient and necessary conditions of the dynamic system stability are derived through seeking the optimal feasible solutions of several algebraic Riccati matrix inequalities. [ABSTRACT FROM AUTHOR]

Visual tracking is a challenging computer vision problem with numerous practical applications. We propose a convolutional features selection-based tracking framework to improve accuracy and robustness. First, we investigate the impact of features extracted from different convolutional neural network layers for the visual tracking problem. Second, we learn correlation filters on each layer outputs to encode the target appearance and design a fluctuation detection technique to select the appropriate convolutional layers, which can improve the target localization precision and avoid drifting caused by the challenging factors, such as occlusions and appearance variations. Third, we present an improved model update strategy to keep positive samples while removing corrupted ones. Extensive experimental results on the OTB-2013 and OTB-2015 benchmarks demonstrate that the proposed algorithm performs favorably against several state-of-the-art trackers. ©2018 SPIEand IS&T [DOI: 10.1117/1 .JEI.27.3.033031] [ABSTRACT FROM AUTHOR]

Existing interactive image segmentation methods heavily rely on manual input, i.e. a sufficient quantity and correct locations of labels. In this paper, we propose a new interactive segmentation algorithm which aims to reduce human intervention and to generate high-quality segmentation results. In contrast to most energy minimizing based segmentation methods, the segmentation is cast as multi-classification in our proposed method. First, the input image is segmented into superpixels by using different methods. Then we build a dictionary consisting of all obtained superpixels and reconstruct samples represented by certain labeled superpixels. Finally, we learn a discriminative projection matrix through Fishers linear discriminant analysis (FLDA) algorithm, which learns a discriminative subspace for classification. The unlabeled superpixels are grouped into foreground or background, via calculating their minimal norm. Our method can capture long range grouping cues and reduce the sensitivity with respect to input label quantity and location of labels, by the combination of superpixels and discriminative dictionary. Extensive experiments are conducted both on MSRC and another challenging database in order to demonstrate the effectiveness of the proposed method. Quantitative and qualitative results show that our method is competitive to the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Particle probability hypothesis density (PHD) filter-based visual trackers have achieved considerable success in the visual tracking field. But position measurements based on detection may not have enough ability to discriminate an object from clutter, and accurate state extraction cannot be obtained in the original PHD filtering framework, especially when targets can appear, disappear, merge, or split at any time. To meet the limitations, the proposed algorithm combines a color histogram of a target and the temporal dynamics in a unifying framework and a Gaussian mixture model clustering method for efficient state extraction is designed. The proposed tracker can improve the accuracy of state estimation in tracking a variable number of objects. [ABSTRACT FROM AUTHOR]

• We confirmed the anti-inflammatory effects of metformin in LPS-stimulated RAW264.7 macrophages. • We unveiled the tsRNA transcriptional profile in inflammatory RAW264.7 macrophages following metformin treatment. • We employed bioinformatics methods to predict the target genes of differentially abumdant tsRNAs (DA-tsRNAs), shedding light on various potential biological functions and signaling pathways associated with inflammation and immunity, indicating that tsRNAs may as potential biomarkers for metformin in the treatment of inflammatory conditions. Metformin, a widely used anti-diabetic drug, has demonstrated its efficacy in addressing various inflammatory conditions. tRNA-derived small RNA (tsRNA), a novel type of small non-coding RNA, exhibits diverse regulatory functions and holds promise as both a diagnostic biomarker and a therapeutic target for various diseases. The purpose of this study is to investigate whether the abundance of tsRNAs changed in LPS versus LPS + metformin-treated cells, utilizing microarray technology. Firstly, we established an in vitro lipopolysaccharide (LPS)-induced inflammation model using RAW264.7 macrophages and assessed the protective effects of metformin against inflammatory damage. Subsequently, we extracted total RNA from both LPS-treated and metformin + LPS-treated cell samples for microarray analysis to identify differentially abundant tsRNAs (DA-tsRNAs). Furthermore, we conducted bioinformatics analysis to predict target genes for validated DA-tsRNAs and explore the biological functions and signaling pathways associated with DA-tsRNAs. Notably, metformin was found to inhibit the inflammatory response in RAW264.7 macrophages. The microarray results revealed a total of 247 DA-tsRNAs, with 58 upregulated and 189 downregulated tsRNAs in the Met + LPS group compared to the LPS group. The tsRNA-mRNA network was visualized, shedding light on potential interactions. The results of bioinformatics analysis suggested that these potential targets of specific tsRNAs were mainly related to inflammation and immunity. Our study provides compelling evidence that metformin exerts anti-inflammatory effects and modulates the abundance of tsRNAs in LPS-treated RAW264.7 macrophages. These findings establish a valuable foundation for using tsRNAs as potential biomarkers for metformin in the treatment of inflammatory conditions. [ABSTRACT FROM AUTHOR]

Abstract: Multi-target Bayesian filter in the framework of finite set statistics (FISST) and its approximations, including probability hypothesis density (PHD) filter and cardinalized probability hypothesis density (CPHD) filter, are elegant methods for multi-target tracking by jointly estimating the number of targets and their states from a sequence of noisy and cluttered observation sets. PHD filter and CPHD filter can deal with the tracking scenario involving the surviving targets, the spawned targets, and the spontaneous births. One of the limitations of PHD and CPHD filter is that it is assumed that intensities of spontaneous birth targets are known at the initialization stage. To address the problem, a track initiation technique is proposed to detect the position unknown birth targets and is hybridized with PHD and CPHD filter. Once new targets are detected, the position estimates are employed to form intensities of spontaneous births for starting PHD and CPHD filter. Simulation results demonstrate that the proposed tracker can adaptively and efficiently track multiple targets especially in scenarios with birth targets of unknown position, which the PHD and CPHD filter are unable to do on their own. [Copyright &y& Elsevier]

Abstract: The localization of multiple emitters from passive angle measurements is a widely investigated problem. Traditionally, the central problem of state estimation for multiple targets by multiple passive sensors is data association. Mathematically, the formulation of the data association problem leads to a generalization of an S-dimensional (S-D) assignment problem. Unfortunately, the complexity of solving an S-D assignment problem for S≥3 is NP hard. A practical solution is to solve the multidimensional assignment problem using multistage Lagrangian relaxation. However, the computational requirements of it explode with the number of sensors. Additionally, it cannot give satisfactory results in dense clutter environment. In this paper, the sequential probability hypothesis density (PHD) filter using passive sensors in two different manners for localization of multiple emitters is introduced. Simulation results show that the sequential PHD filter can achieve better performance with smaller computational complexity than the method based on S-D assignment programming in dense clutter environment. [Copyright &y& Elsevier]

Abstract: Cardinalized probability hypothesis density (CPHD) filter provides more accurate estimates of target number than the probability hypothesis density (PHD) filter, and hence, also of the states of targets. This additional capability comes at the price of greater computational complexity: , where N is the number of targets and M is the cardinality of measurement set at each time index. It is shown that the computational cost of CPHD filter can be reduced by means of reducing the cardinality of measurement set. In practice, the cardinality of measurement set can be reduced by gating techniques as done in traditional tracking algorithms. In this paper, we develop a method of reducing the computational cost of Gaussian mixture CPHD filter by incorporating the elliptical gating technique. Computer simulation results show that the computational cost is reduced and that the tracking performance loss incurred is not significant. [Copyright &y& Elsevier]

Abstract: A robust observation model for visual tracking is proposed in this paper. The model consists of three appearance models: fixed appearance model, adaptive appearance model, and two-frame appearance model. The three appearance models are used, respectively, for catching unchanged components, slow changes, and rapid changes in object appearance. During tracking, the robust observation model is incorporated in a particle filter, and the particle filter can automatically select proper appearance models to track object according to the current tracking situation. Occlusion analysis is implemented using the M-estimation technique. Experimental results demonstrate that the proposed algorithm can track objects well under many challenging tracking situations. [Copyright &y& Elsevier]

Chronic ankle instability predominantly occurs due to multiple exercise-related diseases. Conservative treatment methods regarding this condition have not effectively improved in recent years, which is why more focus has been put on exploring different novel reconstruction procedures of the lateral ankle ligament for the treatment of chronic ankle instability.Objectives: This study aims to obtain the overall effectiveness of various lateral ankle ligament reconstruction methods for chronic ankle ligament instability.Methods: We gathered data from PubMed and EMBASE databases using the keywords: ankle, malleolar, and reconstruction. Newcastle - Ottawa quality assessment was carried out for the obtained studies; effect volume combination and image drawing were performed by Stata14, and Excel was used for data statistics.Results: A total of 12 articles were included in the quantitative analysis by performing full-text reading and data inclusion. Among them, 476 patients (485 ankle joints) were treated. The results showed that the overall valid efficiency of "excellent" was 59% and "good" lateral ligament reconstruction was 26%, I2=87.3%, P = 0.000; the subgroup analysis anatomic reconstruction group I2=0.0%, P = 0.993; the autograft group I2=0.0%, P = 1.000; allograft group I2=0.0%, P = 0.993.Conclusion: Reconstruction of the lateral ankle ligament is a relatively stable treatment for chronic ankle instability. [ABSTRACT FROM AUTHOR]

Background: Surgical hand rubbing (SHR) and surgical hand scrubbing (SHS) are two common methods used by surgeons to reduce surgical site infections. To date, the optimal method that can effectively reduce these infections remains unknown. In this study, we performed a comprehensive statistical analysis to compare the efficacy of these two methods in effectively controlling surgical site infections.Methods: A systemic review and meta-analysis was performed by mining literature from major databases, including Pubmed, Embase, Cochrane library, Ovid and Google Scholar, and recruiting studies published between 1980 and 1st April 2019. Analysis was performed using Revman, version 5.3, software, and focused on primary outcomes that included colony-forming unit (CFU) counts and logarithmic reduction of CFU after hand antisepsis and after surgery.Results: Seven clinical trials met our inclusion criteria, with a total of 764 healthcare workers analyzed. We found no statistically significant differences between the two methods with regards to CFU counts and logarithmic reduction of CFU after hand antisepsis and surgery, as well as antisepsis and surgery times.Conclusion: From the literature, it was evident that SHR had similar efficacy to SHS, without necessarily increasing costs. Owing to advantages such as ease of application, exposure to less dermal irritation, and less time consumption, SHR is recommended as a cost-effective alternative for management of surgical site infections. [ABSTRACT FROM AUTHOR]

This paper proposes an online object tracking algorithm in which the object tracking is achieved by using multi-task sparse learning and non-negative matrix factorization under the particle filtering framework. The object appearance is first modeled by subspace learning to reflect the target variations across frames. Combination of non-negative components is learned from examples observed in previous frames. In order to robust tracking an object, group sparsity constraints are included to the non-negativity one. Furthermore, the alternating direction method of multipliers algorithm is employed to compute the model efficiently. Qualitative and quantitative experiments on a variety of challenging sequences show favorable performance of the proposed algorithm against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based target tracking is a long-standing problem in UAV applications. In this paper, we develop a local kernel feature to encode properties of UAV tracking object. Meanwhile, object proposals can provide a reliable prior knowledge to identify tracking target being an object or not. Therefore, we propose to integrate detection proposal method into a tracking by detection framework. More specifically, we adopt edge box proposals and random samplings as training examples and then train these examples for tracking task. The structured support vector machine is employed to implement training and detecting procedure. To reveal the effectiveness of our method, experiment is performed on the UAV123 benchmark dataset. Among state-of-the-art methods, our method achieves comparable results. [ABSTRACT FROM AUTHOR]

Abstract Existing convolutional neural network (CNN) based trackers have limited tracking performance in some challenging scenarios such as deformation, background clutter and illumination variation, because the features extracted from a single layer or from a linear combination of multiple layers are insufficient to describe the target appearance. To overcome this problem, we propose a novel tracking algorithm based on interactive multiple model (IMM) framework for better exploring deep features from different layers (IMM_DFT). In this method, we first build measurement models from convolutional layers by applying correlation filters on hierarchical features. Then, to effectively estimate the target state for each layer, we design a hybrid system which consists of the foregoing measurement model and an online learning motion model. Finally, in order to achieve the optimal fusion of the systems for adapting diverse appearance variation of the target and background, an IMM estimator is developed to dynamically adjust the weight of each system using likelihood function and transition probabilities. Extensive experiments on OTB-2013, OTB-2015 and VOT-2016 benchmark databases demonstrate that the proposed algorithm achieves more favorable performance than several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Highlights • A method for visual object tracking is proposed. • We propose a decomposition model in visual tracking. • The decomposition model is utilized in an integrated generative model and discriminative model tracking framework. • Alternating direction method of multipliers algorithm guarantees the convergence of the decomposition model. This paper presents a multi-task based object tracking algorithm via a collaborative model. Under the framework of particle filtering, we develop a multi-task sparse learning based generative and discriminative classifier model. In the generative model, we propose a histogram based subspace learning method which takes advantage of adaptive templates update. In the discriminative model, we introduce an effective method to compute the confidence value which assigns more weights to the foreground than the background. A decomposition model is employed to take the common features and outliers of each particle into consideration. The alternating direction method of multipliers (ADMM) algorithm guarantees the optimization problem can be solved robustly and accurately. Qualitative and quantitative comparisons with nine state-of-the-art methods demonstrate the effectiveness and efficiency of our method in handling various challenges during tracking. [ABSTRACT FROM AUTHOR]

In this paper, we formulate particle filter based tracking as a multi-task sparse learning problem that exploits context information. The target and context information which modeled as linear combinations of principal component analysis (PCA) basis is formed as dictionary templates. The target is treated as the guidance and the sampling examples are filtered depending on the similarity between the target and each input. The edge preserving smoothing property of the guided filter is a key factor for object tracking. First, valuable candidates can be selected and the inaccurate candidates become blurry. Therefore, the guided filter can help to distinguish the target from numerous candidates easily. Second, partial occluded target can be recovered by the filtering process via the guidance image. Thus, the drifting problem can be alleviated. Then multi-task sparse learning is employed to learn the target and context information. The proposed learning problem is efficiently solved using an alternating direction method of multipliers (ADMM) method that yields a sequence of closed form updates. We test our tracker on challenging video sequences that involve drastic illumination changes, large pose variations, and heavy occlusions. Experimental results show that our tracker consistently outperforms state-of-the-art trackers. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) person re-identification (re-ID) aims to transfer knowledge from a labeled source domain to guide the task proposed on the unlabeled target domain, in which people share different identifications and cross multiple camera views within two different domains. Consequently, traditional UDA re-ID techniques generally suffer due to the negative transfer caused by the inevitable noise generated by variant backgrounds , while the foregrounds also lack sufficient reliable identification knowledge to guarantee the qualified cross-domain re-ID. To remedy the raised negative transfer caused by variant backgrounds, we propose a novel body structure estimation (BSE) mechanism enforced semantic driven attention network (SDA), which enables the designed model with semantic effectiveness to distinguish the foreground and background. In searching for the reliable feature representations as in the foreground areas, we propose a novel label refinery mechanism to dynamically optimize the traditional attribute learning techniques for the strengthened personal attribute features and thus resulting the qualified UDA - re-ID. Extensive experiments demonstrate the effectiveness of our method in solving unsupervised domain adaptation person re-ID task on three large-scale datasets including Market-1501, DukeMTMC-reID and MSMT17. • Research aims to address the noisy pseudo labels caused by the negative transfer. • We design a semantic driven attention block to distinguish the background and foreground. • A novel label refinery mechanism is proposed to strengthen the attribute learning. • We achieve comparable performance via comparing with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• A novel uncertain motion tracking framework with semantics estimation and region proposals is proposed. • A semantics object proposals generation strategy is proposed. • The proposed hybrid semantics tracking algorithm combines the full advantages of globally sparse semantics region proposals prediction and correlation filter prediction. • The proposed semantics-contextual estimation method can generate more credible candidates. • Experimental results show the state-of-the-art performance of our method. In real world, most of the tracking methods suffer from uncertain motion, which may make the tracker failure because of a local search window with the motion smooth assumption. To address this problem, a novel tracking framework based on convolutional net with semantics estimation and region proposals is proposed. Firstly, we present a semantics object proposals generation strategy, including category-level semantics proposals, one-object-level semantics estimation and semantics-contextual proposals generation, to obtain a few of high-quality object-oriented proposals covering uncertain motion. Secondly, combining the globally sparse semantics region proposals prediction and correlation filter prediction, a hybrid semantics tracking algorithm is proposed, which obtains a coarse object location by the decision of multiple response maps. Finally, we learn and train independent correlation filter to estimate the scale of target for a higher tracking accuracy. Extensive experiments on two visual tracking benchmarks and results demonstrate our method achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]