Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation

We develop a method for the estimation of articulated pose, such as that of the human body or the human hand, from a single (monocular) image. Pose estimation is formulated as a statistical inference problem, where the goal is to find a posterior probability distribution over poses as well as a maximum a posteriori (MAP) estimate. The method combines two modeling approaches, one discriminative and the other generative. The discriminative model consists of a set of mapping functions that are constructed automatically from a labeled training set of body poses and their respective image features. The discriminative formulation allows for modeling ambiguous, one-to-many mappings (through the use of multi-modal distributions) that may yield multiple valid articulated pose hypotheses from a single image. The generative model is defined in terms of a computer graphics rendering of poses. While the generative model offers an accurate way to relate observed (image features) and hidden (body pose) random variables, it is difficult to use it directly in pose estimation, since inference is computationally intractable. In contrast, inference with the discriminative model is tractable, but considerably less accurate for the problem of interest. A combined discriminative/generative formulation is derived that leverages the complimentary strengths of both models in a principled framework for articulated pose inference. Two efficient MAP pose estimation algorithms are derived from this formulation; the first is deterministic and the second non-deterministic. Performance of the framework is quantitatively evaluated in estimating articulated pose of both the human hand and human body. Most of this work was done while the first author was with Boston University.     

A framework for heading-guided recognition of human activity

A combined 2D, 3D approach is presented that allows for robust tracking of moving people and recognition of actions. It is assumed that the system observes multiple moving objects via a single, uncalibrated video camera. Low-level features are often insufficient for detection, segmentation, and tracking of non-rigid moving objects. Therefore, an improved mechanism is proposed that integrates low-level (image processing), mid-level (recursive 3D trajectory estimation), and high-level (action recognition) processes. A novel extended Kalman filter formulation is used in estimating the relative 3D motion trajectories up to a scale factor. The recursive estimation process provides a prediction and error measure that is exploited in higher-level stages of action recognition. Conversely, higher-level mechanisms provide feedback that allows the system to reliably segment and maintain the tracking of moving objects before, during, and after occlusion. Heading-guided recognition (HGR) is proposed as an efficient method for adaptive classification of activity. The HGR approach is demonstrated using “motion history images” that are then recognized via a mixture-of-Gaussians classifier. The system is tested in recognizing various dynamic human outdoor activities: running, walking, roller blading, and cycling. In addition, experiments with real and synthetic data sets are used to evaluate stability of the trajectory estimator with respect to noise.     

Computational speed and high-frequency trading profitability: an ecological perspective

High-frequency traders (HFTs) account for a considerable component of equity trading but we know little about the source of their trading profits and to what extend IT based differentiators such as news processing power and ultra-low latency has contributed to competitive advantage within HFT realm. Given a fairly modest amount of empirical evidence on the subject, we study the effects of computational speed on HFTs’ profits through an experimental artificial agent-based equity market. Our approach relies on an ecological modelling inspired from the r/K selection theory, and is designed to assess the relative financial performance of two classes of aggressive HFT agents endowed with dissimilar computational capabilities. We use a discrete-event news simulation system to capture the information processing disparity and order transfer delay, and simulate the dynamics of the market. Through Monte Carlo simulation we obtain in our empirical setting robust estimates of the expected outcome.     

Associative memory with dynamic synapses

We have examined a role of dynamic synapses in the stochastic Hopfield-like network behavior. Our results demonstrate an appearance of a novel phase characterized by quick transitions from one memory state to another. The network is able to retrieve memorized patterns corresponding to classical ferromagnetic states but switches between memorized patterns with an intermittent type of behavior. This phenomenon might reflect the flexibility of real neural systems and their readiness to receive and respond to novel and changing external stimuli.     

Salient Object Subitizing

We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.     

How do practitioners use conceptual modeling in practice?

Much research has been devoted over the years to investigating and advancing the techniques and tools used by analysts when they model. As opposed to what academics, software providers and their resellers promote as should be happening, the aim of this research was to determine whether practitioners still embraced conceptual modeling seriously. In addition, what are the most popular techniques and tools used for conceptual modeling? What are the major purposes for which conceptual modeling is used? The study found that the top six most frequently used modeling techniques and methods were ER diagramming, data flow diagramming, systems flowcharting, workflow modeling, UML, and structured charts. Modeling technique use was found to decrease significantly from smaller to medium-sized organizations, but then to increase significantly in larger organizations (proxying for large, complex projects). Technique use was also found to significantly follow an inverted U-shaped curve, contrary to some prior explanations. Additionally, an important contribution of this study was the identification of the factors that uniquely influence the decision of analysts to continue to use modeling, viz., communication (using diagrams) to/from stakeholders, internal knowledge (lack of) of techniques, user expectations management, understanding models’ integration into the business, and tool/software deficiencies. The highest ranked purposes for which modeling was undertaken were database design and management, business process documentation, business process improvement, and software development.     

Multi-stage modeling using fuzzy multi-criteria feature selection to improve survival prediction of ICU septic shock patients

In many binary medical classification problems, the cost of misclassifying one category is higher than the other, and in these applications it is desirable to employ a classifier with selective sensitivity or specificity. This work explores the utility of a fuzzy multi–criteria function for performance evaluation during knowledge–based medical classification and prediction. The method presented here uses fuzzy optimization to combine the sensitivity, specificity, and accuracy of classification as goals in a single objective function. This approach is used to assign flexible goals, which can be used to maximize the outcome in terms of each one of the goals. The proposed approach significantly increases the sensitivity and the specificity while maintaining or increasing accuracy. The versatility of the method is further exploited in a multi-model approach, using individual structures of multi-objective optimization of sensitivity and specificity separately, and then combining their outcomes through a decision-making module. Among various medical benefits derived from applying this technique, the divergent feature sets selected by high sensitivity and specificity models lend insight into factors more integrally connected to what causes risk of death for patients.     

On the Relation of Job Insecurity,Job Autonomy,Innovative Work Behaviour and the Mediating Effect of Work Engagement

European policy is focusing on innovation as a way out of the economic crisis. At the same time, job insecurity is rising as Europe is still in crisis. In this paper, we examine whether job insecurity affects the innovative work behaviour of employees by focusing on the relation between job insecurity, job autonomy, work engagement and innovative work behaviour (IWB). Using employee level survey data, we use structural equation modelling to disentangle the relations between these variables. The partially mediated model shows the best fit with the data. This model shows that job insecurity and autonomy are both directly and indirectly, through work engagement, related with IWB. For autonomy these relations are positive, while they are negative (and smaller) for job insecurity. Moreover, a negative covariance is observed between job insecurity and autonomy.     

A fast and noise resilient cluster-based anomaly detection

Clustering, while systematically applied in anomaly detection, has a direct impact on the accuracy of the detection methods. Existing cluster-based anomaly detection methods are mainly based on spherical shape clustering. In this paper, we focus on arbitrary shape clustering methods to increase the accuracy of the anomaly detection. However, since the main drawback of arbitrary shape clustering is its high memory complexity, we propose to summarize clusters first. For this, we design an algorithm, called Summarization based on Gaussian Mixture Model (SGMM), to summarize clusters and represent them as Gaussian Mixture Models (GMMs). After GMMs are constructed, incoming new samples are presented to the GMMs, and their membership values are calculated, based on which the new samples are labeled as “normal” or “anomaly.” Additionally, to address the issue of noise in the data, instead of labeling samples individually, they are clustered first, and then each cluster is labeled collectively. For this, we present a new approach, called Collective Probabilistic Anomaly Detection (CPAD), in which, the distance of the incoming new samples and the existing SGMMs is calculated, and then the new cluster is labeled the same as of the closest cluster. To measure the distance of two GMM-based clusters, we propose a modified version of the Kullback–Libner measure. We run several experiments to evaluate the performances of the proposed SGMM and CPAD methods and compare them against some of the well-known algorithms including ABACUS, local outlier factor (LOF), and one-class support vector machine (SVM). The performance of SGMM is compared with ABACUS using Dunn and DB metrics, and the results indicate that the SGMM performs superior in terms of summarizing clusters. Moreover, the proposed CPAD method is compared with the LOF and one-class SVM considering the performance criteria of (a) false alarm rate, (b) detection rate, and (c) memory efficiency. The experimental results show that the CPAD method is noise resilient, memory efficient, and its accuracy is higher than the other methods.