May 6, 2019

3082 words 15 mins read

Paper Group ANR 263

An artificial intelligence tool for heterogeneous team formation in the classroom. Online Learning of Portfolio Ensembles with Sector Exposure Regularization. HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor. Fast and Accurate Surface Normal Integration on Non-Rectangular Domains. A Gaussian Mixture MRF for Model-Based Iterative Reco …

An artificial intelligence tool for heterogeneous team formation in the classroom


Title	An artificial intelligence tool for heterogeneous team formation in the classroom
Authors	Juan M. Alberola, Elena Del Val, Victor Sanchez-Anguix, Alberto Palomares, Maria Dolores Teruel
Abstract	Nowadays, there is increasing interest in the development of teamwork skills in the educational context. This growing interest is motivated by its pedagogical effectiveness and the fact that, in labour contexts, enterprises organize their employees in teams to carry out complex projects. Despite its crucial importance in the classroom and industry, there is a lack of support for the team formation process. Not only do many factors influence team performance, but the problem becomes exponentially costly if teams are to be optimized. In this article, we propose a tool whose aim it is to cover such a gap. It combines artificial intelligence techniques such as coalition structure generation, Bayesian learning, and Belbin’s role theory to facilitate the generation of working groups in an educational context. This tool improves current state of the art proposals in three ways: i) it takes into account the feedback of other teammates in order to establish the most predominant role of a student instead of self-perception questionnaires; ii) it handles uncertainty with regard to each student’s predominant team role; iii) it is iterative since it considers information from several interactions in order to improve the estimation of role assignments. We tested the performance of the proposed tool in an experiment involving students that took part in three different team activities. The experiments suggest that the proposed tool is able to improve different teamwork aspects such as team dynamics and student satisfaction.
Tasks
Published	2016-04-16
URL	http://arxiv.org/abs/1604.04721v1
PDF	http://arxiv.org/pdf/1604.04721v1.pdf
PWC	https://paperswithcode.com/paper/an-artificial-intelligence-tool-for
Repo
Framework

Online Learning of Portfolio Ensembles with Sector Exposure Regularization


Title	Online Learning of Portfolio Ensembles with Sector Exposure Regularization
Authors	Guy Uziel, Ran El-Yaniv
Abstract	We consider online learning of ensembles of portfolio selection algorithms and aim to regularize risk by encouraging diversification with respect to a predefined risk-driven grouping of stocks. Our procedure uses online convex optimization to control capital allocation to underlying investment algorithms while encouraging non-sparsity over the given grouping. We prove a logarithmic regret for this procedure with respect to the best-in-hindsight ensemble. We applied the procedure with known mean-reversion portfolio selection algorithms using the standard GICS industry sector grouping. Empirical Experimental results showed an impressive percentage increase of risk-adjusted return (Sharpe ratio).
Tasks
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03266v1
PDF	http://arxiv.org/pdf/1604.03266v1.pdf
PWC	https://paperswithcode.com/paper/online-learning-of-portfolio-ensembles-with
Repo
Framework

HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor


Title	HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor
Authors	Shuda Li, Ankur Handa, Yang Zhang, Andrew Calway
Abstract	We describe a new method for comparing frame appearance in a frame-to-model 3-D mapping and tracking system using an low dynamic range (LDR) RGB-D camera which is robust to brightness changes caused by auto exposure. It is based on a normalised radiance measure which is invariant to exposure changes and not only robustifies the tracking under changing lighting conditions, but also enables the following exposure compensation perform accurately to allow online building of high dynamic range (HDR) maps. The latter facilitates the frame-to-model tracking to minimise drift as well as better capturing light variation within the scene. Results from experiments with synthetic and real data demonstrate that the method provides both improved tracking and maps with far greater dynamic range of luminosity.
Tasks
Published	2016-04-04
URL	http://arxiv.org/abs/1604.00895v1
PDF	http://arxiv.org/pdf/1604.00895v1.pdf
PWC	https://paperswithcode.com/paper/hdrfusion-hdr-slam-using-a-low-cost-auto
Repo
Framework

Fast and Accurate Surface Normal Integration on Non-Rectangular Domains


Title	Fast and Accurate Surface Normal Integration on Non-Rectangular Domains
Authors	Martin Bähr, Michael Breuß, Yvain Quéau, Ali Sharifi Boroujerdi, Jean-Denis Durou
Abstract	The integration of surface normals for the purpose of computing the shape of a surface in 3D space is a classic problem in computer vision. However, even nowadays it is still a challenging task to devise a method that combines the flexibility to work on non-trivial computational domains with high accuracy, robustness and computational efficiency. By uniting a classic approach for surface normal integration with modern computational techniques we construct a solver that fulfils these requirements. Building upon the Poisson integration model we propose to use an iterative Krylov subspace solver as a core step in tackling the task. While such a method can be very efficient, it may only show its full potential when combined with a suitable numerical preconditioning and a problem-specific initialisation. We perform a thorough numerical study in order to identify an appropriate preconditioner for our purpose. To address the issue of a suitable initialisation we propose to compute this initial state via a recently developed fast marching integrator. Detailed numerical experiments illuminate the benefits of this novel combination. In addition, we show on real-world photometric stereo datasets that the developed numerical framework is flexible enough to tackle modern computer vision applications.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06049v1
PDF	http://arxiv.org/pdf/1610.06049v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-surface-normal-integration
Repo
Framework

A Gaussian Mixture MRF for Model-Based Iterative Reconstruction with Applications to Low-Dose X-ray CT


Title	A Gaussian Mixture MRF for Model-Based Iterative Reconstruction with Applications to Low-Dose X-ray CT
Authors	Ruoqiao Zhang, Dong Hye Ye, Debashish Pal, Jean-Baptiste Thibault, Ken D. Sauer, Charles A. Bouman
Abstract	Markov random fields (MRFs) have been widely used as prior models in various inverse problems such as tomographic reconstruction. While MRFs provide a simple and often effective way to model the spatial dependencies in images, they suffer from the fact that parameter estimation is difficult. In practice, this means that MRFs typically have very simple structure that cannot completely capture the subtle characteristics of complex images. In this paper, we present a novel Gaussian mixture Markov random field model (GM-MRF) that can be used as a very expressive prior model for inverse problems such as denoising and reconstruction. The GM-MRF forms a global image model by merging together individual Gaussian-mixture models (GMMs) for image patches. In addition, we present a novel analytical framework for computing MAP estimates using the GM-MRF prior model through the construction of surrogate functions that result in a sequence of quadratic optimizations. We also introduce a simple but effective method to adjust the GM-MRF so as to control the sharpness in low- and high-contrast regions of the reconstruction separately. We demonstrate the value of the model with experiments including image denoising and low-dose CT reconstruction.
Tasks	Denoising, Image Denoising
Published	2016-05-12
URL	http://arxiv.org/abs/1605.04006v2
PDF	http://arxiv.org/pdf/1605.04006v2.pdf
PWC	https://paperswithcode.com/paper/a-gaussian-mixture-mrf-for-model-based
Repo
Framework

The BIN_COUNTS Constraint: Filtering and Applications


Title	The BIN_COUNTS Constraint: Filtering and Applications
Authors	Roberto Rossi, Özgür Akgün, Steven Prestwich, Armagan Tarim
Abstract	We introduce the BIN_COUNTS constraint, which deals with the problem of counting the number of decision variables in a set which are assigned values that lie in given bins. We illustrate a decomposition and a filtering algorithm that achieves generalised arc consistency. We contrast the filtering power of these two approaches and we discuss a number of applications. We show that BIN_COUNTS can be employed to develop a decomposition for the $\chi^2$ test constraint, a new statistical constraint that we introduce in this work. We also show how this new constraint can be employed in the context of the Balanced Academic Curriculum Problem and of the Balanced Nursing Workload Problem. For both these problems we carry out numerical studies involving our reformulations. Finally, we present a further application of the $\chi^2$ test constraint in the context of confidence interval analysis.
Tasks
Published	2016-11-28
URL	http://arxiv.org/abs/1611.08942v5
PDF	http://arxiv.org/pdf/1611.08942v5.pdf
PWC	https://paperswithcode.com/paper/the-bin_counts-constraint-filtering-and
Repo
Framework

A Compressed Sensing Based Decomposition of Electrodermal Activity Signals


Title	A Compressed Sensing Based Decomposition of Electrodermal Activity Signals
Authors	Swayambhoo Jain, Urvashi Oswal, Kevin S. Xu, Brian Eriksson, Jarvis Haupt
Abstract	The measurement and analysis of Electrodermal Activity (EDA) offers applications in diverse areas ranging from market research, to seizure detection, to human stress analysis. Unfortunately, the analysis of EDA signals is made difficult by the superposition of numerous components which can obscure the signal information related to a user’s response to a stimulus. We show how simple pre-processing followed by a novel compressed sensing based decomposition can mitigate the effects of the undesired noise components and help reveal the underlying physiological signal. The proposed framework allows for decomposition of EDA signals with provable bounds on the recovery of user responses. We test our procedure on both synthetic and real-world EDA signals from wearable sensors and demonstrate that our approach allows for more accurate recovery of user responses as compared to the existing techniques.
Tasks	Seizure Detection
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07754v2
PDF	http://arxiv.org/pdf/1602.07754v2.pdf
PWC	https://paperswithcode.com/paper/a-compressed-sensing-based-decomposition-of
Repo
Framework

Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation


Title	Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation
Authors	Holger R. Roth, Le Lu, Amal Farag, Andrew Sohn, Ronald M. Summers
Abstract	Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits traditional segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a holistic learning approach that integrates semantic mid-level cues of deeply-learned organ interior and boundary maps via robust spatial aggregation using random forest. Our method generates boundary preserving pixel-wise class labels for pancreas segmentation. Quantitative evaluation is performed on CT scans of 82 patients in 4-fold cross-validation. We achieve a (mean $\pm$ std. dev.) Dice Similarity Coefficient of 78.01% $\pm$ 8.2% in testing which significantly outperforms the previous state-of-the-art approach of 71.8% $\pm$ 10.7% under the same evaluation criterion.
Tasks	Automated Pancreas Segmentation, Pancreas Segmentation
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07830v1
PDF	http://arxiv.org/pdf/1606.07830v1.pdf
PWC	https://paperswithcode.com/paper/spatial-aggregation-of-holistically-nested
Repo
Framework

PupilNet: Convolutional Neural Networks for Robust Pupil Detection


Title	PupilNet: Convolutional Neural Networks for Robust Pupil Detection
Authors	Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Enkelejda Kasneci
Abstract	Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in real-world scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non centered and off-axis eye recording, and physiological eye characteristics. In this paper, we propose and evaluate a method based on a novel dual convolutional neural network pipeline. In its first stage the pipeline performs coarse pupil position identification using a convolutional neural network and subregions from a downscaled input image to decrease computational costs. Using subregions derived from a small window around the initial pupil position estimate, the second pipeline stage employs another convolutional neural network to refine this position, resulting in an increased pupil detection rate up to 25% in comparison with the best performing state-of-the-art algorithm. Annotated data sets can be made available upon request.
Tasks	Eye Tracking
Published	2016-01-19
URL	http://arxiv.org/abs/1601.04902v1
PDF	http://arxiv.org/pdf/1601.04902v1.pdf
PWC	https://paperswithcode.com/paper/pupilnet-convolutional-neural-networks-for
Repo
Framework

Unifying task specification in reinforcement learning


Title	Unifying task specification in reinforcement learning
Authors	Martha White
Abstract	Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we demonstrate the generality and utility of this formalism. Finally, we extend standard learning constructs, including Bellman operators, and extend some seminal theoretical results, including approximation errors bounds. Overall, we provide a well-understood and sound formalism on which to build theoretical results and simplify algorithm use and development.
Tasks
Published	2016-09-07
URL	http://arxiv.org/abs/1609.01995v3
PDF	http://arxiv.org/pdf/1609.01995v3.pdf
PWC	https://paperswithcode.com/paper/unifying-task-specification-in-reinforcement
Repo
Framework

Disentangled Representations in Neural Models


Title	Disentangled Representations in Neural Models
Authors	William Whitney
Abstract	Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to reuse and interpret, and they do a poor job of capturing the sparsity which is present in real- world transformations. In this paper, I describe methods for learning disentangled representations in the two domains of graphics and computation. These methods allow neural methods to learn representations which are easy to interpret and reuse, yet they incur little or no penalty to performance. In the Graphics section, I demonstrate the ability of these methods to infer the generating parameters of images and rerender those images under novel conditions. In the Computation section, I describe a model which is able to factorize a multitask learning problem into subtasks and which experiences no catastrophic forgetting. Together these techniques provide the tools to design a wide range of models that learn disentangled representations and better model the factors of variation in the real world.
Tasks	Representation Learning
Published	2016-02-07
URL	http://arxiv.org/abs/1602.02383v1
PDF	http://arxiv.org/pdf/1602.02383v1.pdf
PWC	https://paperswithcode.com/paper/disentangled-representations-in-neural-models
Repo
Framework

Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation


Title	Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
Authors	Qi Ye, Shanxin Yuan, Tae-Kyun Kim
Abstract	Discriminative methods often generate hand poses kinematically implausible, then generative methods are used to correct (or verify) these results in a hybrid method. Estimating 3D hand pose in a hierarchy, where the high-dimensional output space is decomposed into smaller ones, has been shown effective. Existing hierarchical methods mainly focus on the decomposition of the output space while the input space remains almost the same along the hierarchy. In this paper, a hybrid hand pose estimation method is proposed by applying the kinematic hierarchy strategy to the input space (as well as the output space) of the discriminative method by a spatial attention mechanism and to the optimization of the generative method by hierarchical Particle Swarm Optimization (PSO). The spatial attention mechanism integrates cascaded and hierarchical regression into a CNN framework by transforming both the input(and feature space) and the output space, which greatly reduces the viewpoint and articulation variations. Between the levels in the hierarchy, the hierarchical PSO forces the kinematic constraints to the results of the CNNs. The experimental results show that our method significantly outperforms four state-of-the-art methods and three baselines on three public benchmarks.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03334v2
PDF	http://arxiv.org/pdf/1604.03334v2.pdf
PWC	https://paperswithcode.com/paper/spatial-attention-deep-net-with-partial-pso
Repo
Framework

Direction matters: hand pose estimation from local surface normals


Title	Direction matters: hand pose estimation from local surface normals
Authors	Chengde Wan, Angela Yao, Luc Van Gool
Abstract	We present a hierarchical regression framework for estimating hand joint positions from single depth images based on local surface normals. The hierarchical regression follows the tree structured topology of hand from wrist to finger tips. We propose a conditional regression forest, i.e., the Frame Conditioned Regression Forest (FCRF) which uses a new normal difference feature. At each stage of the regression, the frame of reference is established from either the local surface normal or previously estimated hand joints. By making the regression with respect to the local frame, the pose estimation is more robust to rigid transformations. We also introduce a new efficient approximation to estimate surface normals. We verify the effectiveness of our method by conducting experiments on two challenging real-world datasets and show consistent improvements over previous discriminative pose estimation methods.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2016-04-10
URL	http://arxiv.org/abs/1604.02657v1
PDF	http://arxiv.org/pdf/1604.02657v1.pdf
PWC	https://paperswithcode.com/paper/direction-matters-hand-pose-estimation-from
Repo
Framework

Inferring Cognitive Models from Data using Approximate Bayesian Computation


Title	Inferring Cognitive Models from Data using Approximate Bayesian Computation
Authors	Antti Kangasrääsiö, Kumaripaba Athukorala, Andrew Howes, Jukka Corander, Samuel Kaski, Antti Oulasvirta
Abstract	An important problem for HCI researchers is to estimate the parameter values of a cognitive model from behavioral data. This is a difficult problem, because of the substantial complexity and variety in human behavioral strategies. We report an investigation into a new approach using approximate Bayesian computation (ABC) to condition model parameters to data and prior knowledge. As the case study we examine menu interaction, where we have click time data only to infer a cognitive model that implements a search behaviour with parameters such as fixation duration and recall probability. Our results demonstrate that ABC (i) improves estimates of model parameter values, (ii) enables meaningful comparisons between model variants, and (iii) supports fitting models to individual users. ABC provides ample opportunities for theoretical HCI research by allowing principled inference of model parameter values and their uncertainty.
Tasks
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00653v2
PDF	http://arxiv.org/pdf/1612.00653v2.pdf
PWC	https://paperswithcode.com/paper/inferring-cognitive-models-from-data-using
Repo
Framework

Mixing Times and Structural Inference for Bernoulli Autoregressive Processes


Title	Mixing Times and Structural Inference for Bernoulli Autoregressive Processes
Authors	Dimitrios Katselis, Carolyn L. Beck, R. Srikant
Abstract	We introduce a novel multivariate random process producing Bernoulli outputs per dimension, that can possibly formalize binary interactions in various graphical structures and can be used to model opinion dynamics, epidemics, financial and biological time series data, etc. We call this a Bernoulli Autoregressive Process (BAR). A BAR process models a discrete-time vector random sequence of $p$ scalar Bernoulli processes with autoregressive dynamics and corresponds to a particular Markov Chain. The benefit from the autoregressive dynamics is the description of a $2^p\times 2^p$ transition matrix by at most $pd$ effective parameters for some $d\ll p$ or by two sparse matrices of dimensions $p\times p^2$ and $p\times p$, respectively, parameterizing the transitions. Additionally, we show that the BAR process mixes rapidly, by proving that the mixing time is $O(\log p)$. The hidden constant in the previous mixing time bound depends explicitly on the values of the chain parameters and implicitly on the maximum allowed in-degree of a node in the corresponding graph. For a network with $p$ nodes, where each node has in-degree at most $d$ and corresponds to a scalar Bernoulli process generated by a BAR, we provide a greedy algorithm that can efficiently learn the structure of the underlying directed graph with a sample complexity proportional to the mixing time of the BAR process. The sample complexity of the proposed algorithm is nearly order-optimal as it is only a $\log p$ factor away from an information-theoretic lower bound. We present simulation results illustrating the performance of our algorithm in various setups, including a model for a biological signaling network.
Tasks	Time Series
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06061v1
PDF	http://arxiv.org/pdf/1612.06061v1.pdf
PWC	https://paperswithcode.com/paper/mixing-times-and-structural-inference-for
Repo
Framework