Search

The problem of simultaneously predicting multiple real-valued outputs using a shared set of input variables is known as multi-target regression and has attracted considerable interest in the past couple of years. The dominant approach in the literature for multi-target regression is to capture the dependencies between the outputs through a linear model and express it as an output mixing matrix. This modelling formalism, however, is too simplistic in real-world problems where the output variables are related to one another in a more complex and non-linear fashion. To address this problem, in this study, we propose a structural modelling approach where the correlations between output variables are modelled using a non-linear approach. In particular, we pose the multi-target regression problem as one of vector-valued composition function learning in the reproducing kernel Hilbert space and propose a non-linear structure learning approach to capture the relationship between the outputs via an output kernel. By virtue of using a non-linear output kernel function, the proposed approach can better discover non-linear dependencies among targets for improved prediction performance. An extensive evaluation conducted on different databases reveals the benefits of the proposed multi-target regression technique against the baseline and the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Efficient and robust facial landmark localisation is crucial for the deployment of real-time face analysis systems. This paper presents a new loss function, namely Rectified Wing (RWing) loss, for regression-based facial landmark localisation with Convolutional Neural Networks (CNNs). We first systemically analyse different loss functions, including L2, L1 and smooth L1. The analysis suggests that the training of a network should pay more attention to small-medium errors. Motivated by this finding, we design a piece-wise loss that amplifies the impact of the samples with small-medium errors. Besides, we rectify the loss function for very small errors to mitigate the impact of inaccuracy of manual annotation. The use of our RWing loss boosts the performance significantly for regression-based CNNs in facial landmarking, especially for lightweight network architectures. To address the problem of under-representation of samples with large pose variations, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation strategies. Last, the proposed approach is extended to create a coarse-to-fine framework for robust and efficient landmark localisation. Moreover, the proposed coarse-to-fine framework is able to deal with the small sample size problem effectively. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits of our RWing loss and prove the superiority of the proposed method over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

• We propose supervised spatial attention that employs a heatmap generator for instructive feature learning. • We formulate a rectified Gaussian scoring function to generate informative heatmaps. • We present scale-aware layer attention that eliminates redundant information from pyramid features. • A voting strategy is designed to produce more reliable classification results. • Our face detector achieves encouraging performance in accuracy and speed on several benchmarks. Modern anchor-based face detectors learn discriminative features using large-capacity networks and extensive anchor settings. In spite of their promising results, they are not without problems. First, most anchors extract redundant features from the background. As a consequence, the performance improvements are achieved at the expense of a disproportionate computational complexity. Second, the predicted face boxes are only distinguished by a classifier supervised by pre-defined positive, negative and ignored anchors. This strategy may ignore potential contributions from cohorts of anchors labeled negative/ignored during inference simply because of their inferior initialisation, although they can regress well to a target. In other words, true positives and representative features may get filtered out by unreliable confidence scores. To deal with the first concern and achieve more efficient face detection, we propose a Heatmap-assisted Spatial Attention (HSA) module and a Scale-aware Layer Attention (SLA) module to extract informative features using lower computational costs. To be specific, SLA incorporates the information from all the feature pyramid layers, weighted adaptively to remove redundant layers. HSA predicts a reshaped Gaussian heatmap and employs it to facilitate a spatial feature selection by better highlighting facial areas. For more reliable decision-making, we merge the predicted heatmap scores and classification results by voting. Since our heatmap scores are based on the distance to the face centres, they are able to retain all the well-regressed anchors. The experiments obtained on several well-known benchmarks demonstrate the merits of the proposed method. [ABSTRACT FROM AUTHOR]

Brain computation is metabolically expensive and requires the supply of significant amounts of energy. Mitochondria are highly specialized organelles whose main function is to generate cellular energy. Due to their complex morphologies, neurons are especially dependent on a set of tools necessary to regulate mitochondrial function locally in order to match energy provision with local demands. By regulating mitochondrial transport, neurons control the local availability of mitochondrial mass in response to changes in synaptic activity. Neurons also modulate mitochondrial dynamics locally to adjust metabolic efficiency with energetic demand. Additionally, neurons remove inefficient mitochondria through mitophagy. Neurons coordinate these processes through signalling pathways that couple energetic expenditure with energy availability. When these mechanisms fail, neurons can no longer support brain function giving rise to neuropathological states like metabolic syndromes or neurodegeneration. [ABSTRACT FROM AUTHOR]

The state of classifier incongruence in decision making systems incorporating multiple classifiers is often an indicator of anomaly caused by an unexpected observation or an unusual situation. Its assessment is important as one of the key mechanisms for domain anomaly detection. In this paper, we investigate the sensitivity of Delta divergence, a novel measure of classifier incongruence, to estimation errors. Statistical properties of Delta divergence are analysed both theoretically and experimentally. The results of the analysis provide guidelines on the selection of threshold for classifier incongruence detection based on this measure. [ABSTRACT FROM AUTHOR]

In recent years, facial landmark detection – also known as face alignment or facial landmark localisation – has become a very active area, due to its importance to a variety of image and video-based face analysis systems, such as face recognition, emotion analysis, human-computer interaction and 3D face reconstruction. This article looks at the challenges and latest technology advances in facial landmarks. [ABSTRACT FROM AUTHOR]

In decision making systems involving multiple classifiers there is the need to assess classifier (in)congruence, that is to gauge the degree of agreement between their outputs. A commonly used measure for this purpose is the Kullback–Leibler (KL) divergence. We propose a variant of the KL divergence, named decision cognizant Kullback–Leibler divergence (DC-KL), to reduce the contribution of the minority classes, which obscure the true degree of classifier incongruence. We investigate the properties of the novel divergence measure analytically and by simulation studies. The proposed measure is demonstrated to be more robust to minority class clutter. Its sensitivity to estimation noise is also shown to be considerably lower than that of the classical KL divergence. These properties render the DC-KL divergence a much better statistic for discriminating between classifier congruence and incongruence in pattern recognition systems. [ABSTRACT FROM AUTHOR]

Multi-label classification is a challenging research problem due to the fact that each example may belong to a varying number of classes. This problem can be further aggravated by high dimensionality and complex correlation among labels. In this paper, a discriminant approach to multi-label classification is proposed using the concept of stacking and spectral regression based kernel discriminant analysis (SSRKDA). For effective stacked generalisation, a novel fast implementation of the leave-one-out cross-validation for SSRKDA is also presented in this paper. The proposed system is validated on several multi-label databases. The results indicate a significant boost in performance when SSRKDA is compared to other multi-label classification techniques. [ABSTRACT FROM AUTHOR]

The authors present an algorithm that models the rate of change of biometric performance over time on a subject‐dependent basis. It is called 'homomorphic users grouping algorithm'. Although the model is based on very simplistic assumptions that are inherent in linear regression, it has been applied successfully to estimate the performance of talking face and speech identity verification modalities, as well as their fusion, over a period of more than 600 days. Their experiments carried out on the MOBIO database show that subjects exhibit very different performance trends. Although the performance of some users degrades over time, which is consistent with the literature, they also found that for a similar proportion of users, their performance actually improves with use. The latter finding has never been reported in the literature. Hence, their findings suggest that the problem of biometric performance degradation may be not as serious as previously thought, and so far, the community has ignored the possibility of improved biometric performance over time. The findings also suggest that adaptive biometric systems, that is, systems that attempt to update biometric templates, should be subject‐dependent. [ABSTRACT FROM AUTHOR]

Fully automatic annotation of tennis game using broadcast video is a task with a great potential but with enormous challenges. In this paper we describe our approach to this task, which integrates computer vision, machine listening, and machine learning. At the low level processing, we improve upon our previously proposed state-of-the-art tennis ball tracking algorithm and employ audio signal processing techniques to detect key events and construct features for classifying the events. At high level analysis, we model event classification as a sequence labelling problem, and investigate four machine learning techniques using simulated event sequences. Finally, we evaluate our proposed approach on three real world tennis games, and discuss the interplay between audio, vision and learning. To the best of our knowledge, our system is the only one that can annotate tennis game at such a detailed level. [ABSTRACT FROM AUTHOR]

We discuss the problem of pose invariant face recognition using a Markov Random Field (MRF) model. MRF image to image matching has been shown to be very promising in earlier studies (Arashloo and Kittler, 2011) [4]. Its demanding computational complexity has been addressed in Arashloo et al. (2011) [6] by means of multiresolution MRFs linked by the super coupling transform advocated by Petrou et al. (1998) [37, 11]. In this paper, we benefit from the daisy descriptor for face image representation in image matching. Most importantly, we design an innovative GPU implementation of the proposed multiresolution MRF matching process. The significant speed up achieved (factor of 25) has multiple benefits: It makes the MRF approach a practical proposition. It facilitates extensive empirical optimisation and evaluation studies. The latter conducted on benchmarking databases, including the challenging labelled faces in the wild (LFW) database show the outstanding potential of the proposed method, which consistently achieves state-of-the-art performance in standard benchmarking tests. The experimental studies also show that the super coupled multiresolution MRFs deliver a computational speed up by a factor of 5 over and above the speed up achieved using the GPU implementation. [ABSTRACT FROM AUTHOR]

We address the problem of anomaly detection in machine perception. The concept of domain anomaly is introduced as distinct from the conventional notion of anomaly used in the literature. We propose a unified framework for anomaly detection which exposes the multifaceted nature of anomalies and suggest effective mechanisms for identifying and distinguishing each facet as instruments for domain anomaly detection. The framework draws on the Bayesian probabilistic reasoning apparatus which clearly defines concepts such as outlier, noise, distribution drift, novelty detection (object, object primitive), rare events, and unexpected events. Based on these concepts we provide a taxonomy of domain anomaly events. One of the mechanisms helping to pinpoint the nature of anomaly is based on detecting incongruence between contextual and noncontextual sensor(y) data interpretation. The proposed methodology has wide applicability. It underpins in a unified way the anomaly detection applications found in the literature. To illustrate some of its distinguishing features, in here the domain anomaly detection methodology is applied to the problem of anomaly detection for a video annotation system. [ABSTRACT FROM AUTHOR]

Variations in illumination is one of major limiting factors of face recognition system perfor-mance. The effect of changes in the incident light on face images is analyzed, as well as its influence on the low frequency components of the image. Starting from this analysis, a new photometric normalization method for illumination invariant face recognition is presented. Low-frequency Discrete Cosine Transform coefficients in the logarithmic domain are used in a local way to reconstruct a slowly varying component of the face image which is caused by illumination. After smoothing, this component is subtracted from the original logarithmic image to compensate for illumination variations. Compared to other preprocessing algorithms, our method achieved a very good performance with a total error rate very similar to that produced by the best performing state-of-the-art algorithm. An in-depth analysis of the two preprocessing methods revealed notable differences in their behavior, which is exploited in a multiple classifier fusion framework to achieve further performance improvement. The superiority of the proposal is demonstrated in both face verification and identification experiments. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a novel inverse random under sampling (IRUS) method is proposed for the class imbalance problem. The main idea is to severely under sample the majority class thus creating a large number of distinct training sets. For each training set we then find a decision boundary which separates the minority class from the majority class. By combining the multiple designs through fusion, we construct a composite boundary between the majority class and the minority class. The proposed methodology is applied on 22 UCI data sets and experimental results indicate a significant increase in performance when compared with many existing class-imbalance learning methods. We also present promising results for multi-label classification, a challenging research problem in many modern applications such as music, text and image categorization. [Copyright &y& Elsevier]

Abstract: Multilabel classification is a challenging research problem in which each instance may belong to more than one class. Recently, a considerable amount of research has been concerned with the development of “good” multi-label learning methods. Despite the extensive research effort, many scientific challenges posed by e.g. highly imbalanced training sets and correlation among labels remain to be addressed. The aim of this paper is to use a heterogeneous ensemble of multi-label learners to simultaneously tackle both the sample imbalance and label correlation problems. This is different from the existing work in the sense that we are proposing to combine state-of-the-art multi-label methods by ensemble techniques instead of focusing on ensemble techniques within a multi-label learner. The proposed ensemble approach (EML) is applied to six publicly available multi-label data sets from various domains including computer vision, biology and text using several evaluation criteria. We validate the advocated approach experimentally and demonstrate that it yields significant performance gains when compared with state-of-the art multi-label methods. [Copyright &y& Elsevier]

Sparsity-inducing multiple kernel Fisher discriminant analysis (MK-FDA) has been studied in the literature. Building on recent advances in non-sparse multiple kernel learning (MKL), we propose a non-sparse version of MK-FDA, which imposes a general 'p norm regularisation on the kernel weights. We formulate the associated optimisation problem as a semi-infinite program (SIP), and adapt an iterative wrapper algorithm to solve it. We then discuss, in light of latest advances inMKL optimisation techniques, several reformulations and optimisation strategies that can potentially lead to significant improvements in the efficiency and scalability of MK-FDA. We carry out extensive experiments on six datasets from various application areas, and compare closely the performance of 'p MK-FDA, fixed norm MK-FDA, and several variants of SVM-based MKL (MK-SVM). Our results demonstrate that 'p MK-FDA improves upon sparse MK-FDA in many practical situations. The results also show that on image categorisation problems, 'p MK-FDA tends to outperform its SVM counterpart. Finally, we also discuss the connection between (MK-)FDA and (MK-)SVM, under the unified framework of regularised kernel machines. [ABSTRACT FROM AUTHOR]

The optimization of a smart card face verification system is a very complex process with many key factors to consider. It involves the investigation of the effect the system parameters have on the system performance measured in terms of accuracy and speed. As the parameters involved are not independent, the search space is of exponential complexity. In practice only partial optimization is feasible with many parameters forced to take default values. We argue that the key options to optimize are image resolution or/and image pre-processing. In addition the main design issue is the degree of compression that can be applied to the probe image before it is transmitted to the smart card. In this work we investigate different optimization strategies by considering both image compression and image resolution, and demonstrate that both the system performance and speed of access can be improved by the jointly optimized parameter setting and the level of probe compression. The experimental results obtained on the XM2VTS database suggest that the choice of one strategy over another is a matter of the time available for the system design, system performance, and response time. [ABSTRACT FROM AUTHOR]

Fast synaptic inhibition is largely mediated by GABAA receptors (GABAARs), ligand-gated chloride channels that play an essential role in the control of cell and network activity in the brain. Recent work has demonstrated that the delivery, number and stability of GABAARs at inhibitory synapses play a key role in the dynamic regulation of inhibitory synaptic efficacy and plasticity. The regulatory pathways essential for the fine-tuning of synaptic inhibition have also emerged as key sites of vulnerability during pathological changes in cell excitability in disease states. [ABSTRACT FROM AUTHOR]

As biometric technology is rolled out on a larger scale, it will be a common scenario (known as cross-device matching) to have a template acquired by one biometric device used by another during testing. This requires a biometric system to work with different acquisition devices, an issue known as device interoperability. We further distinguish two subproblems, depending on whether the device identity is known or unknown. In the latter case, we show that the device information can be probabilistically inferred given quality measures (e.g., image resolution) derived from the raw biometric data. By keeping the template unchanged, cross-device matching can result in significant degradation in performance. We propose to minimize this degradation by using device-specific quality-dependent score normalization. In the context of fusion, after having normalized each device output independently, these outputs can be combined using the naive Bayes principal. We have compared and categorized several state-of-the-art quality-based score normalization procedures, depending on how the relationship between quality measures and score is modeled, as follows: 1) direct modeling; 2) modeling via the cluster index of quality measures; and 3) extending 2) to further include the device information (device-specific cluster index). Experimental results carried out on the Biosecure DS2 data set show that the last approach can reduce both false acceptance and false rejection rates simultaneously. Furthermore, the compounded effect of normalizing each system individually in multimodal fusion is a significant improvement in performance over the baseline fusion (without using any quality information) when the device information is given. [ABSTRACT FROM AUTHOR]

Mitochondria play an essential role in ATP generation, calcium buffering and apoptotic signalling. In neurons, the transport of mitochondria to specific locations where they are needed has emerged as an important process for correct nerve cell function. Recent studies have shed light on the mechanisms that control mitochondrial transport and localization in neurons. We describe the machinery that is important for constitutive transport of mitochondria throughout the cell, and highlight recent advances in our understanding of how signalling pathways can converge on this machinery and allow for rapid activity-dependent control of mitochondrial trafficking and localization. Regulation of mitochondrial trafficking might work in concert with mitochondrial tethering systems to give precise control of mitochondrial delivery and localization to regions of high energy and calcium buffering requirements within neurons. [Copyright &y& Elsevier]

To design a smart card face verification system many key factors have to be considered. In this study we discuss the implementation of such a system and investigate the trade-off between performance and computational complexity. Two optimisation strategies are considered. The studies are performed on the XM2VTS, BANCA and FERET databases demonstrating that the judicial choice of spatial and grey level resolution as well as JPEG compression settings for face representation can optimise verification error. We show that the use of a fixed precision data type does not affect system performance very much but can speed up the verification process. Since the optimisation framework of such a system is very complicated, the search space is simplified by applying some heuristics to the problem. In the adopted suboptimal search strategy one or two parameters are optimised at a time. The system was evaluated using half total error rate (HTER) as the performance criterion. The conclusions reached on different databases indicate that the selection of the optimum parameters may call for different optimum operating points. [ABSTRACT FROM AUTHOR]

Abstract: Synaptic inhibition plays a key role in regulating neuronal excitability and information processing in the brain. The strength of synaptic inhibition is therefore an important determinant of both cellular and network activity levels in the central nervous system (CNS). γ-aminobutyric acid type A (GABAA) receptors are the major sites for fast inhibitory neurotransmission in the CNS and alterations in their trafficking, synaptic accumulation and function play a key role in regulating neuronal excitability. Synaptic receptor number is determined by the trafficking of GABAA receptors to and away from inhibitory synapses and by their stability and localization at the inhibitory postsynaptic domain. Here we discuss advances that have led to an improved understanding of the mechanisms that regulate the delivery and stabilization of GABAA receptors at inhibitory synapses and address the role of GABAA receptor trafficking, GABAA receptor associated proteins and post-translational modifications in regulating this process. [Copyright &y& Elsevier]

The regulation of the number of γ2-subunit-containing GABAA receptors (GABAARS) present at synapses is critical for correct synaptic inhibition and animal behavior. This regulation occurs, in part, by the controlled removal of receptors from the membrane in clathrin-coated vesicles, but it remains unclear how clathrin recruitment to surface γ2-subunit-containing GABAARS is regulated. Here, we identify a γ2-subunit-specific Yxxϕ-type-binding motif for the clathrin adaptor protein, AP2, which is located within a site for γ2-subunit tyrosine phosphorylation. Blocking GABAAR-AP2 interactions via this motif increases synaptic responses within minutes. Crystallographic and biochemical studies reveal that phosphorylation of the Yxxϕ motif inhibits AP2 binding, leading to increased surface receptor number. In addition, the crystal structure provides an explanation for the high affinity of this motif for AP2 and suggests that γ2-subunit-containing heteromeric GABAAR5 may be internalized as dimers or multimers. These data define a mechanism for tyrosine kinase regulation of GABAAR surface levels and synaptic inhibition. [ABSTRACT FROM AUTHOR]

We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object's appearance due to changing camera pose and lighting conditions. Canonical Correlations (also known as principal or canonical angles), which can be thought of as the angles between two d-dimensional subspaces, have recently attracted attention for image set matching. Canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the two main classical methods: parametric distribution-based and nonparametric sample-based matching of sets. Here, this is first demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning method over sets is proposed for set classification. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. Image sets transformed by the discriminant function are then compared by the canonical correlations. Classical orthogonal subspace method (OSM) is also investigated for the similar purpose and compared with the proposed method. The proposed method is evaluated on various object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of 500 general objects taken at different views. The method is also applied to object category recognition using ETH-80 database. The proposed method is shown to outperform the state-of-the-art methods in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

The article discusses various reports published within the issue, including one by Patrick Grother and Elham Tabassi on determining the quality of a biometric system and another by Sinjini Mitra, Marios Savvides and Anthony Brockwell on a new method of extrapolating the performance of a biometric system based on a random effects model.

We address the problem of pose-invariant face recognition based on a single model image. To cope with novel view face images, a model of the effect of pose changes on face appearance must be available. Face images at an arbitrary pose can be mapped to a reference pose by the model yielding view-invariant representation. Such a model typically relies on dense correspondences of different view face images, which are difficult to establish in practice. Errors in the correspondences seriously degrade the accuracy of any recognizer. Therefore, we assume only the minimal possible set of correspondences, given by the corresponding eye positions. We investigate a number of approaches to pose-invariant face recognition exploiting such a minimal set of facial features correspondences. Four different methods are proposed as pose-invariant face recognition "experts" and combined in a single framework of expert fusion. Each expert explicitly or implicitly realizes the three sequential functions jointly required to capture the nonlinear manifolds of face pose changes: representation, view transformation, and class discriminative feature extraction. Within this structure, the experts are designed for diversity. We compare a design in which the three stages are sequentially optimized with two methods which employ an overall single nonlinear function learnt from different view face images. We also propose an approach exploiting a three-dimensional face data. A lookup table storing facial feature correspondences between different pose images, found by 3-D face models, is constructed. The designed experts are different in their nature owing to different sources of information and architectures used. The proposed fusion architecture of the pose-invariant face experts achieves an impressive accuracy gain by virtue of the individual experts diversity. It is experimentally shown that the individual experts outperform the classical linear discriminant analysis (LDA) method on the XM2VTS face data set consisting of about 300 face classes. Further impressive performance gains are obtained by combining the outputs of the experts using different fusion strategies. [ABSTRACT FROM AUTHOR]

The dopamine D3 receptor, which is highly enriched in nucleus accumbens (NAc), has been suggested to play an important role in reinforcement and reward. To understand the potential cellular mechanism underlying D3 receptor functions, we examined the effect of D3 receptor activation on GABAA receptor (GABAAR)-mediated current and inhibitory synaptic transmission in medium spiny neurons of NAc. Application of PD128907 [(4aR, 10bR)-3,4a, 4, 10b-tetrahydro-4-propyl-2H,5H-[1]benzopyrano-[4,3-b]-1,4-oxazin-9-ol hydrochloride], a specific D3 receptor agonist, caused a significant reduction of GABAAR current in acutely dissociated NAc neurons and miniature IPSC amplitude in NAc slices. This effect was blocked by dialysis with a dynamin inhibitory peptide, which prevents the clathrin/activator protein 2 (AP2)-mediated GABAA receptor endocytosis. In addition, the D3 effect on GABAAR current was prevented by agents that manipulate protein kinase A (PKA) activity. Infusion of a peptide derived from GABAAR β subunits, which contains an atypical binding motif for the clathrin AP2 adaptor complex and the major PKA phosphorylation sites and binds with high affinity to AP2 only when dephosphorylated, diminished the D3 regulation of IPSC amplitude. The phosphorylated equivalent of the peptide was without effect. Moreover, PD128907 increased GABAAR internalization and reduced the surface expression of GABAA receptor β subunits in NAc slices, which was prevented by dynamin inhibitory peptide or cAMP treatment. Together, our results suggest that D3 receptor activation suppresses the efficacy of inhibitory synaptic transmission in NAc by increasing the phospho-dependent endocytosis of GABAA receptors. [ABSTRACT FROM AUTHOR]

The efficacy of synaptic inhibition depends on the number of γ-aminobutyric acid type A receptors (GABAARS) expressed on the cell surface of neurons. The clathrin adaptor protein 2 (AP2) complex is a critical regulator of GABAAR endocytosis and, hence, surface receptor number. Here, we identify a previously uncharacterized atypical AP2 binding motif conserved within the intracellular domains of all GABAAR β subunit isoforms. This AP2 binding motif (KTHLRRRSSQLK in the β3 subunit) incorporates the major sites of serine phosphorylation within receptor β subunits, and phosphorylation within this site inhibits AP2 binding. Furthermore, by using surface plasmon resonance, we establish that a peptide (pepβ3) corresponding to the AP2 binding motif in the GABAAR β3 subunit binds to AP2 with high affinity only when dephosphorylated. Moreover, the pepβ3 peptide, but not its phosphorylated equivalent (pepβ3-phos), enhanced the amplitude of miniature inhibitory synaptic current and whole cell GABAAR current. These effects of pepβ3 on GABAAR current were occluded by inhibitors of dynamin-dependent endocytosis supporting an action of pepβ3 on GABAAR endocytosis. Therefore phospho- dependent regulation of AP2 binding to GABAARS provides a mechanism to specify receptor cell surface number and the efficacy of inhibitory synaptic transmission. [ABSTRACT FROM AUTHOR]

We seek to quantify both the classification performance and estimation error robustness of the authors' tomographic classifier fusion methodology by contrasting it in field tests and model scenarios with the sum and product classifier fusion methodologies. In particular, we seek to confirm that the tomographic methodology represents a generally optimal strategy across the entire range of problem dimensionalities, and at a sufficient margin to justify the general advocation of its use. Final results indicate, in particular, a near 25% improvement on the next nearest performing combination scheme at the extremity of the tested dimensional range. [ABSTRACT FROM AUTHOR]

We present a novel method of nonlinear discriminant analysis involving a set of locally linear transformations called "Locally Linear Discriminant Analysis (LLDA)." The underlying idea is that global nonlinear data structures are locally linear and local structures can be linearly aligned. Input vectors are projected into each local feature space by linear transformations found to yield locally linearly transformed classes that maximize the between-class covariance while minimizing the within-class covariance. In face recognition, linear discriminant analysis (LDA) has been widely adopted owing to its efficiency, but it does not capture nonlinear manifolds of faces which exhibit pose variations. Conventional nonlinear classification methods based on kernels such as generalized discriminant analysis (GDA) and support vector machine (SVM) have been developed to overcome the shortcomings of the linear method, but they have the drawback of high computational cost of classification and over fitting. Our method is for multi class nonlinear discrimination and it is computationally highly efficient as compared to GDA. The method does not suffer from over fitting by virtue of the linear base structure of the solution. A novel gradient-based learning algorithm is proposed for finding the optimal set of local linear bases. The optimization does not exhibit a local-maxima problem. The transformation functions facilitate robust face recognition in a low-dimensional subspace, under pose variations, using a single model image. The classification results are given for both synthetic and real face data. [ABSTRACT FROM AUTHOR]

Abstract: Object recognition using graph-matching techniques can be viewed as a two-stage process: extracting suitable object primitives from an image and corresponding models, and matching graphs constructed from these two sets of object primitives. In this paper we concentrate mainly on the latter issue of graph matching, for which we derive a technique based on probabilistic relaxation graph labelling. The new method was evaluated on two standard data sets, SOIL-47 and COIL-100, in both of which objects must be recognised from a variety of different views. The results indicated that our method is comparable with the best of other current object recognition techniques. The potential of the method was also demonstrated on challenging examples of object recognition in cluttered scenes. [Copyright &y& Elsevier]

GABAA receptors mediate the majority of fast synaptic inhibition in the mammalian central nervous system. GABAA receptors associate with a number of cytosolic proteins important for regulating their function including the GABAA receptor γ2 subunit associated protein GABARAP. Here we show GABARAP associates with the synaptic PDZ domain containing protein GRIP1. GRIP1 has been localized to inhibitory synapses however the role of this protein with respect to neuronal inhibition remains unclear. Using in vitro protein interaction assays we show that GABARAP interacts directly with PDZ domains 4–6 of GRIP1. Furthermore, using coimmunoprecipitation assays we show that GABARAP interacts with GRIP1 in vivo. Finally, we show that GRIP1 colocalizes with γ2 subunit containing GABAA receptors in cultured hippocampal neurons. Our findings provide evidence that GRIP1 can associate with proteins important for regulating GABAA receptor function and suggest that GRIP1 may play a role at inhibitory synapses. [Copyright &y& Elsevier]

Generalized linear discriminant analysis has been successfully used as a dimensionality reduction technique in many classification tasks. An analytical method for finding the optimal set of generalized discriminant vectors is proposed in this paper. Compared with other methods, the proposed method has the advantage of requiring less computational time and achieving higher recognition rates. The results of experiments conducted on the Olivetti Research Lab facial database show the effectiveness of the proposed method. [Copyright &y& Elsevier]

γ-aminobutyric acid type A receptors (GABAARs) are the major sites of fast synaptic inhibition in the brain. An essential determinant for the efficacy of synaptic inhibition is the regulation of GABAAR cell surface stability. Here, we have examined the regulation of GABAAR endocytic sorting, a critical regulator of cell surface receptor number. In neurons, rapid constitutive endocytosis of GABAARs was evident. Internalized receptors were then either rapidly recycled back to the cell surface, or on a slower time scale, targeted for lysosomal degradation. This sorting decision was regulated by a direct interaction of GABAARs with Huntingtin-associated protein 1 (HAP1). HAP1 modulated synaptic GABAAR number by inhibiting receptor degradation and facilitating receptor recycling. Together these observations have identified a role for HAP1 in regulating GABAAR sorting, suggesting an important role for this protein in the construction and maintenance of inhibitory synapses. [ABSTRACT FROM AUTHOR]

When combining outputs from multiple classifiers, many combination rules are available. Although easy to implement, fixed combination rules are optimal only in restrictive conditions. We discuss and evaluate their performance when the optimality conditions are not fulfilled. Fixed combination rules are then compared with trainable combination rules on real data in the context of face-based identity verification. The face images are classified by combining the outputs of five different face verification experts. It is demonstrated that a reduction in the error rates of up to 50% over the best single expert is achieved on the XM2VTS database, using either fixed or trainable combination rules. [Copyright &y& Elsevier]

GABAA receptors are the major mediators of fast synaptic inhibition in the brain. These receptors are ionotropic, hetero-pentameric, ligand-gated ion channels, which are predominantly composed of α, β, and γ2 subunits. Here, we reveal that the γ2 subunit of neuronal and recombinant GABAA receptors is palmitoylated. We further establish that palymitoylation of the γ2 subunit occurs on multiple cysteine residues within the major intracellular domain of this receptor subunit. In cultured hippocampal neurons, inhibitors of protein palymitoylation reduced the synaptic clustering of GABAA receptors and steady-state cell surface receptor number. These effects are likely to be mediated by direct palmitoylation of the γ2 subunit, as mutation of palmitoylation sites within this protein reduces GABAA receptor clustering. Taken together, these results suggest that palmitoylation of GABAA receptors plays an essential role in regulating the clustering of these receptors at synaptic sites. [Copyright &y& Elsevier]

We propose a graph-based representation for the elliptic region shape descriptors introduced by Tuytelaars et al.13 In this representation we use image profiles to describe the relation between a pair of image regions. This new representation and a graph matching technique proposed in Ref. 1 are the basis of an object recognition method. An experimental comparative study between the original method and the new graph-based method is carried out. The results show that the graph-based method is more robust to scaling than the original method. Moreover, the misclassification rate using the graph-based method is considerably lower than that yielded by the original method. [ABSTRACT FROM AUTHOR]

Fast synaptic inhibition in the brain is largely mediated by GABAA receptors. These ligand-gated ion channels are crucial in the control of cell and network activity. Therefore, modulating their function or cell surface stability will have major consequences for neuronal excitation. It has become clear that the stability and activity of GABAA receptors at synapses can be dynamically modulated by receptor trafficking and phosphorylation. Here, we discuss these regulatory mechanisms, and their consequences for the efficacy of GABAA receptor mediated synaptic inhibition. [Copyright &y& Elsevier]

We specify an analogy in which the various classifier combination methodologies are interpreted as the implicit reconstruction, by tomographic means, of the composite probability density function spanning the entirety of the pattern space, the process of feature selection in this scenario amounting to an extremely bandwidth-limited Radon transformation of the training data. This metaphor, once elaborated, immediately suggests techniques for improving the process, ultimately defining, in reconstructive terms, an optimal performance criterion for such combinatorial approaches. [ABSTRACT FROM AUTHOR]

Controlling the number of functional γ-aminobutyric acid A (GABAA) receptors in neuronal membranes is a crucial factor for the efficacy of inhibitory neurotransmission. Here we describe the direct interaction of GABAA receptors with the ubiquitin-like protein Plic-1. Furthermore, Plic-1 is enriched at inhibitory synapses and is associated with subsynaptic membranes. Functionally, Plic-1 facilitates GABAA receptor cell surface expression without affecting the rate of receptor internalization. Plic-1 also enhances the stability of intracellular GABAA receptor subunits, increasing the number of receptors available for insertion into the plasma membrane. Our study identifies a previously unknown role for Plic-1, a modulation of GABAA receptor cell surface number, which suggests that Plic-1 facilitates accumulation of these receptors in dendritic membranes. [ABSTRACT FROM AUTHOR]

Modulation of the strength of synapses is thought to be one of the mechanisms that underlies learning and memory and is also likely to be important in processes of neuropathology and drug tolerance. This review focuses on the emerging role of postsynaptic neurotransmitter receptor trafficking as an essential mechanism underlying the dynamic regulation of synaptic strength. [ABSTRACT FROM AUTHOR]

The robustness of visual object tracking is reflected not only in the accuracy of the target localisation in every single frame, but also in the smoothness of the predicted motion of the tracked object across consecutive frames. From the perspective of appearance modelling, the success of the state-of-the-art Transformer-based trackers derives from their ability to adaptively associate the representations of related spatial regions. However, the absence of attention in the channel dimension hinders the realisation of their potential tracking capacity. To cope with the commonly occurring misalignment of the spatial scale between the template and a search patch, we propose a novel cross channel correlation mechanism. Accordingly, the relevance of multi-channel features in the channel Transformer is modelled using two different sources of information. The result is a novel spatial-channel Transformer, which integrates information conveyed by features along both, the spatial and channel directions. For temporal modelling, to quantify the temporal smoothness, we propose a jitter metric that measures the cross-frame variation of the predicted bounding boxes as a function of the parameters such as centre displacement, area, and aspect ratio. As the changes of an object between consecutive frames are limited, the proposed jitter loss can be used to monitor the temporal behaviour of the tracking results and penalise erroneus predictions during the training stage, thus enhancing the temporal stability of an appearance-based tracker. Extensive experiments on several well-known benchmarking datasets demonstrate the robustness of the proposed tracker. [ABSTRACT FROM AUTHOR]

Discusses a method for solving the problem of automatic color shade grading for industrial inspection of randomly textured multicolored ceramic tiles. Comparison of color histograms; Emergence of linear correlation coefficient; Factors contributing to the poor signal-to-noise-ratio in color shade grading.

Provides information on the development of a theoretical framework for combining classifiers which use distinct pattern representations. Comparison of the different classifier combinations schemes; Investigation of the sensitivity analysis of the schemes; Results of the analysis.

Presents a method designed to solve the problem of automatic color grading for industrial inspection of plain and patterned ceramic tiles. Image aquisition; Illumination corrections; Experiments; Two-colored tiles; Conclusions.

Skeleton representation has attracted a great deal of attention recently as an extremely robust feature for human action recognition. However, its non-Euclidean structural characteristics raise new challenges for conventional solutions. Recent studies have shown that there is a native superiority in modeling spatiotemporal skeleton information with a Graph Convolutional Network (GCN). Nevertheless, the skeleton graph modeling normally focuses on the physical adjacency of the elements of the human skeleton sequence, which contrasts with the requirement to provide a perceptually meaningful representation. To address this problem, in this paper, we propose a perceptually-enriched graph learning method by introducing innovative features to spatial and temporal skeleton graph modeling. For the spatial information modeling, we incorporate a Local-Global Graph Convolutional Network (LG-GCN) that builds a multifaceted spatial perceptual representation. This helps to overcome the limitations caused by over-reliance on the spatial adjacency relationships in the skeleton. For temporal modeling, we present a Region-Aware Graph Convolutional Network (RA-GCN), which directly embeds the regional relationships conveyed by a skeleton sequence into a temporal graph model. This innovation mitigates the deficiency of the original skeleton graph models. In addition, we strengthened the ability of the proposed channel modeling methods to extract multi-scale representations. These innovations result in a lightweight graph convolutional model, referred to as Graph2Net, that simultaneously extends the spatial and temporal perceptual fields, and thus enhances the capacity of the graph model to represent skeleton sequences. We conduct extensive experiments on NTU-RGB+D 60&120, Northwestern-UCLA, and Kinetics-400 datasets to show that our results surpass the performance of several mainstream methods while limiting the model complexity and computational overhead. [ABSTRACT FROM AUTHOR]