July 26, 2019

2957 words 14 mins read

Paper Group ANR 766

Mitigating the Curse of Correlation in Security Games by Entropy Maximization. A deep learning approach to diabetic blood glucose prediction. Price and Profit Awareness in Recommender Systems. A Minimal Span-Based Neural Constituency Parser. A Real-time Hand Gesture Recognition and Human-Computer Interaction System. Deep representation learning for …

Mitigating the Curse of Correlation in Security Games by Entropy Maximization


Title	Mitigating the Curse of Correlation in Security Games by Entropy Maximization
Authors	Haifeng Xu, Milind Tambe, Shaddin Dughmi, Venil Loyd Noronha
Abstract	In Stackelberg security games, a defender seeks to randomly allocate limited security resources to protect critical targets from an attack. In this paper, we study a fundamental, yet underexplored, phenomenon in security games, which we term the \emph{Curse of Correlation} (CoC). Specifically, we observe that there are inevitable correlations among the protection status of different targets. Such correlation is a crucial concern, especially in \emph{spatio-temporal} domains like conservation area patrolling, where attackers can surveil patrollers at certain areas and then infer their patrolling routes using such correlations. To mitigate this issue, we propose to design entropy-maximizing defending strategies for spatio-temporal security games, which frequently suffer from CoC. We prove that the problem is #P-hard in general. However, it admits efficient algorithms in well-motivated special settings. Our experiments show significant advantages of max-entropy algorithms over previous algorithms. A scalable implementation of our algorithm is currently under pre-deployment testing for integration into FAMS software to improve the scheduling of US federal air marshals.
Tasks
Published	2017-03-11
URL	http://arxiv.org/abs/1703.03912v2
PDF	http://arxiv.org/pdf/1703.03912v2.pdf
PWC	https://paperswithcode.com/paper/mitigating-the-curse-of-correlation-in
Repo
Framework

A deep learning approach to diabetic blood glucose prediction


Title	A deep learning approach to diabetic blood glucose prediction
Authors	H. N. Mhaskar, S. V. Pereverzyev, M. D. van der Walt
Abstract	We consider the question of 30-minute prediction of blood glucose levels measured by continuous glucose monitoring devices, using clinical data. While most studies of this nature deal with one patient at a time, we take a certain percentage of patients in the data set as training data, and test on the remainder of the patients; i.e., the machine need not re-calibrate on the new patients in the data set. We demonstrate how deep learning can outperform shallow networks in this example. One novelty is to demonstrate how a parsimonious deep representation can be constructed using domain knowledge.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05828v1
PDF	http://arxiv.org/pdf/1707.05828v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-approach-to-diabetic-blood
Repo
Framework

Price and Profit Awareness in Recommender Systems


Title	Price and Profit Awareness in Recommender Systems
Authors	Dietmar Jannach, Gediminas Adomavicius
Abstract	Academic research in the field of recommender systems mainly focuses on the problem of maximizing the users’ utility by trying to identify the most relevant items for each user. However, such items are not necessarily the ones that maximize the utility of the service provider (e.g., an online retailer) in terms of the business value, such as profit. One approach to increasing the providers’ utility is to incorporate purchase-oriented information, e.g., the price, sales probabilities, and the resulting profit, into the recommendation algorithms. In this paper we specifically focus on price- and profit-aware recommender systems. We provide a brief overview of the relevant literature and use numerical simulations to illustrate the potential business benefit of such approaches.
Tasks	Recommendation Systems
Published	2017-07-25
URL	http://arxiv.org/abs/1707.08029v1
PDF	http://arxiv.org/pdf/1707.08029v1.pdf
PWC	https://paperswithcode.com/paper/price-and-profit-awareness-in-recommender
Repo
Framework

A Minimal Span-Based Neural Constituency Parser


Title	A Minimal Span-Based Neural Constituency Parser
Authors	Mitchell Stern, Jacob Andreas, Dan Klein
Abstract	In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with classical dynamic programming techniques, but also admits a novel greedy top-down inference algorithm based on recursive partitioning of the input. We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving state-of-the-art single-model performance on the Penn Treebank (91.79 F1) and strong performance on the French Treebank (82.23 F1).
Tasks	Constituency Parsing
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03919v1
PDF	http://arxiv.org/pdf/1705.03919v1.pdf
PWC	https://paperswithcode.com/paper/a-minimal-span-based-neural-constituency
Repo
Framework

A Real-time Hand Gesture Recognition and Human-Computer Interaction System


Title	A Real-time Hand Gesture Recognition and Human-Computer Interaction System
Authors	Pei Xu
Abstract	In this project, we design a real-time human-computer interaction system based on hand gesture. The whole system consists of three components: hand detection, gesture recognition and human-computer interaction (HCI) based on recognition; and realizes the robust control of mouse and keyboard events with a higher accuracy of gesture recognition. Specifically, we use the convolutional neural network (CNN) to recognize gestures and makes it attainable to identify relatively complex gestures using only one cheap monocular camera. We introduce the Kalman filter to estimate the hand position based on which the mouse cursor control is realized in a stable and smooth way. During the HCI stage, we develop a simple strategy to avoid the false recognition caused by noises - mostly transient, false gestures, and thus to improve the reliability of interaction. The developed system is highly extendable and can be used in human-robotic or other human-machine interaction scenarios with more complex command formats rather than just mouse and keyboard events.
Tasks	Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07296v1
PDF	http://arxiv.org/pdf/1704.07296v1.pdf
PWC	https://paperswithcode.com/paper/a-real-time-hand-gesture-recognition-and
Repo
Framework

Deep representation learning for human motion prediction and classification


Title	Deep representation learning for human motion prediction and classification
Authors	Judith Bütepage, Michael Black, Danica Kragic, Hedvig Kjellström
Abstract	Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.
Tasks	Action Classification, Motion Capture, motion prediction, Representation Learning
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07486v2
PDF	http://arxiv.org/pdf/1702.07486v2.pdf
PWC	https://paperswithcode.com/paper/deep-representation-learning-for-human-motion
Repo
Framework

Stigmergy-based modeling to discover urban activity patterns from positioning data


Title	Stigmergy-based modeling to discover urban activity patterns from positioning data
Authors	Antonio L. Alfeo, Mario G. C. A. Cimino, Sara Egidi, Bruno Lepri, Alex Pentland, Gigliola Vaglini
Abstract	Positioning data offer a remarkable source of information to analyze crowds urban dynamics. However, discovering urban activity patterns from the emergent behavior of crowds involves complex system modeling. An alternative approach is to adopt computational techniques belonging to the emergent paradigm, which enables self-organization of data and allows adaptive analysis. Specifically, our approach is based on stigmergy. By using stigmergy each sample position is associated with a digital pheromone deposit, which progressively evaporates and aggregates with other deposits according to their spatiotemporal proximity. Based on this principle, we exploit positioning data to identify high density areas (hotspots) and characterize their activity over time. This characterization allows the comparison of dynamics occurring in different days, providing a similarity measure exploitable by clustering techniques. Thus, we cluster days according to their activity behavior, discovering unexpected urban activity patterns. As a case study, we analyze taxi traces in New York City during 2015.
Tasks
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03667v2
PDF	http://arxiv.org/pdf/1704.03667v2.pdf
PWC	https://paperswithcode.com/paper/stigmergy-based-modeling-to-discover-urban
Repo
Framework

Exploring the significance of using perceptually relevant image decolorization method for scene classification


Title	Exploring the significance of using perceptually relevant image decolorization method for scene classification
Authors	V. Sowmya, D. Govind, K. P. Soman
Abstract	A color image contains luminance and chrominance components representing the intensity and color information respectively. The objective of the work presented in this paper is to show the significance of incorporating the chrominance information for the task of scene classification. An improved color-to-grayscale image conversion algorithm by effectively incorporating the chrominance information is proposed using color-to-gay structure similarity index (C2G-SSIM) and singular value decomposition (SVD) to improve the perceptual quality of the converted grayscale images. The experimental result analysis based on the image quality assessment for image decolorization called C2G-SSIM and success rate (Cadik and COLOR250 datasets) shows that the proposed image decolorization technique performs better than 8 existing benchmark algorithms for image decolorization. In the second part of the paper, the effectiveness of incorporating the chrominance component in scene classification task is demonstrated using the deep belief network (DBN) based image classification system developed using dense scale invariant feature transform (SIFT) as features. The levels of chrominance information incorporated by the proposed image decolorization technique is confirmed by the improvement in the overall scene classification accuracy . Also, the overall scene classification performance is improved by the combination of models obtained using the proposed and the conventional decolorization methods.
Tasks	Image Classification, Image Quality Assessment, Scene Classification
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10152v1
PDF	http://arxiv.org/pdf/1712.10152v1.pdf
PWC	https://paperswithcode.com/paper/exploring-the-significance-of-using
Repo
Framework

Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks


Title	Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks
Authors	Joan Serrà, Alexandros Karatzoglou
Abstract	Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these algorithms tend to have large input and output dimensionalities that dominate their overall size. This makes them difficult to train, due to the limited memory of graphical processing units, and difficult to deploy on mobile devices with limited hardware. To address these difficulties, we propose Bloom embeddings, a compression technique that can be applied to the input and output of neural network models dealing with sparse high-dimensional binary-coded instances. Bloom embeddings are computationally efficient, and do not seriously compromise the accuracy of the model up to 1/5 compression ratios. In some cases, they even improve over the original accuracy, with relative increases up to 12%. We evaluate Bloom embeddings on 7 data sets and compare it against 4 alternative methods, obtaining favorable results. We also discuss a number of further advantages of Bloom embeddings, such as ‘on-the-fly’ constant-time operation, zero or marginal space requirements, training time speedups, or the fact that they do not require any change to the core model architecture or training configuration.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.03993v1
PDF	http://arxiv.org/pdf/1706.03993v1.pdf
PWC	https://paperswithcode.com/paper/getting-deep-recommenders-fit-bloom
Repo
Framework

Nonlinear Interference Mitigation via Deep Neural Networks


Title	Nonlinear Interference Mitigation via Deep Neural Networks
Authors	Christian Häger, Henry D. Pfister
Abstract	A neural-network-based approach is presented to efficiently implement digital backpropagation (DBP). For a 32x100 km fiber-optic link, the resulting “learned” DBP significantly reduces the complexity compared to conventional DBP implementations.
Tasks
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06234v1
PDF	http://arxiv.org/pdf/1710.06234v1.pdf
PWC	https://paperswithcode.com/paper/nonlinear-interference-mitigation-via-deep
Repo
Framework

Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations


Title	Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
Authors	Upol Ehsan, Brent Harrison, Larry Chan, Mark O. Riedl
Abstract	We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translation to translate internal state-action representations of an autonomous agent into natural language. We evaluate our technique in the Frogger game environment, training an autonomous game playing agent to rationalize its action choices using natural language. A natural language training corpus is collected from human players thinking out loud as they play the game. We motivate the use of rationalization as an approach to explanation generation and show the results of two experiments evaluating the effectiveness of rationalization. Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.
Tasks	Machine Translation
Published	2017-02-25
URL	http://arxiv.org/abs/1702.07826v2
PDF	http://arxiv.org/pdf/1702.07826v2.pdf
PWC	https://paperswithcode.com/paper/rationalization-a-neural-machine-translation
Repo
Framework

High Performance Novel Skin Segmentation Algorithm for Images With Complex Background


Title	High Performance Novel Skin Segmentation Algorithm for Images With Complex Background
Authors	Mohammad Reza Mahmoodi
Abstract	Skin Segmentation is widely used in biometric applications such as face detection, face recognition, face tracking, and hand gesture recognition. However, several challenges such as nonlinear illumination, equipment effects, personal interferences, ethnicity variations, etc., are involved in detection process that result in the inefficiency of color based methods. Even though many ideas have already been proposed, the problem has not been satisfactorily solved yet. This paper introduces a technique that addresses some limitations of the previous works. The proposed algorithm consists of three main steps including initial seed generation of skin map, Otsu segmentation in color images, and finally a two-stage diffusion. The initial seed of skin pixels is provided based on the idea of ternary image as there are certain pixels in images which are associated to human complexion with very high probability. The Otsu segmentation is performed on several color channels in order to identify homogeneous regions. The result accompanying with the edge map of the image is utilized in two consecutive diffusion steps in order to annex initially unidentified skin pixels to the seed. Both quantitative and qualitative results demonstrate the effectiveness of the proposed system in compare with the state-of-the-art works.
Tasks	Face Detection, Face Recognition, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2017-01-19
URL	http://arxiv.org/abs/1701.05588v1
PDF	http://arxiv.org/pdf/1701.05588v1.pdf
PWC	https://paperswithcode.com/paper/high-performance-novel-skin-segmentation
Repo
Framework

RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment


Title	RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
Authors	Hongyu Ren, Diqi Chen, Yizhou Wang
Abstract	Inspired by the free-energy brain theory, which implies that human visual system (HVS) tends to reduce uncertainty and restore perceptual details upon seeing a distorted image, we propose restorative adversarial net (RAN), a GAN-based model for no-reference image quality assessment (NR-IQA). RAN, which mimics the process of HVS, consists of three components: a restorator, a discriminator and an evaluator. The restorator restores and reconstructs input distorted image patches, while the discriminator distinguishes the reconstructed patches from the pristine distortion-free patches. After restoration, we observe that the perceptual distance between the restored and the distorted patches is monotonic with respect to the distortion level. We further define Gain of Restoration (GoR) based on this phenomenon. The evaluator predicts perceptual score by extracting feature representations from the distorted and restored patches to measure GoR. Eventually, the quality score of an input image is estimated by weighted sum of the patch scores. Experimental results on Waterloo Exploration, LIVE and TID2013 show the effectiveness and generalization ability of RAN compared to the state-of-the-art NR-IQA models.
Tasks	Image Quality Assessment, No-Reference Image Quality Assessment
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05444v1
PDF	http://arxiv.org/pdf/1712.05444v1.pdf
PWC	https://paperswithcode.com/paper/ran4iqa-restorative-adversarial-nets-for-no
Repo
Framework

An iterative closest point method for measuring the level of similarity of 3d log scans in wood industry


Title	An iterative closest point method for measuring the level of similarity of 3d log scans in wood industry
Authors	Cyrine Selma, Hind Haouzi, Philippe Thomas, Jonathan Gaudreault, Michael Morin
Abstract	In the Canadian’s lumber industry, simulators are used to predict the lumbers resulting from the sawing of a log at a given sawmill. Giving a log or several logs’ 3D scans as input, simulators perform a real-time job to predict the lumbers. These simulators, however, tend to be slow at processing large volume of wood. We thus explore an alternative approximation techniques based on the Iterative Closest Point (ICP) algorithm to identify the already processed log to which an unseen log resembles the most. The main benefit of the ICP approach is that it can easily handle 3D scans with a variable number of points. We compare this ICP-based nearest neighbor predictor, to predictors built using machine learning algorithms such as the K-nearest-neighbor (kNN) and Random Forest (RF). The implemented ICP-based predictor enabled us to identify key points in using the 3D scans directly for distance calculation. The long-term goal of this ongoing research is to integrated ICP distance calculations and machine learning.
Tasks
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08135v1
PDF	http://arxiv.org/pdf/1710.08135v1.pdf
PWC	https://paperswithcode.com/paper/an-iterative-closest-point-method-for
Repo
Framework

Collaborative Deep Learning in Fixed Topology Networks


Title	Collaborative Deep Learning in Fixed Topology Networks
Authors	Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar
Abstract	There is significant recent interest to parallelize deep learning algorithms in order to handle the enormous growth in data and model sizes. While most advances focus on model parallelization and engaging multiple computing agents via using a central parameter server, aspect of data parallelization along with decentralized computation has not been explored sufficiently. In this context, this paper presents a new consensus-based distributed SGD (CDSGD) (and its momentum variant, CDMSGD) algorithm for collaborative deep learning over fixed topology networks that enables data parallelization as well as decentralized computation. Such a framework can be extremely useful for learning agents with access to only local/private data in a communication constrained environment. We analyze the convergence properties of the proposed algorithm with strongly convex and nonconvex objective functions with fixed and diminishing step sizes using concepts of Lyapunov function construction. We demonstrate the efficacy of our algorithms in comparison with the baseline centralized SGD and the recently proposed federated averaging algorithm (that also enables data parallelism) based on benchmark datasets such as MNIST, CIFAR-10 and CIFAR-100.
Tasks
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07880v1
PDF	http://arxiv.org/pdf/1706.07880v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-deep-learning-in-fixed-topology
Repo
Framework