July 29, 2019

3106 words 15 mins read

Paper Group ANR 155

A Two-Phase Safe Vehicle Routing and Scheduling Problem: Formulations and Solution Algorithms. SmartPaste: Learning to Adapt Source Code. Sparse Approximation of 3D Meshes using the Spectral Geometry of the Hamiltonian Operator. Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos. Moderate Environmental Variation Promotes th …

A Two-Phase Safe Vehicle Routing and Scheduling Problem: Formulations and Solution Algorithms


Title	A Two-Phase Safe Vehicle Routing and Scheduling Problem: Formulations and Solution Algorithms
Authors	Aschkan Omidvar, Eren Erman Ozguven, O. Arda Vanli, R. Tavakkoli-Moghaddam
Abstract	We propose a two phase time dependent vehicle routing and scheduling optimization model that identifies the safest routes, as a substitute for the classical objectives given in the literature such as shortest distance or travel time, through (1) avoiding recurring congestions, and (2) selecting routes that have a lower probability of crash occurrences and non-recurring congestion caused by those crashes. In the first phase, we solve a mixed-integer programming model which takes the dynamic speed variations into account on a graph of roadway networks according to the time of day, and identify the routing of a fleet and sequence of nodes on the safest feasible paths. Second phase considers each route as an independent transit path (fixed route with fixed node sequences), and tries to avoid congestion by rescheduling the departure times of each vehicle from each node, and by adjusting the sub-optimal speed on each arc. A modified simulated annealing (SA) algorithm is formulated to solve both complex models iteratively, which is found to be capable of providing solutions in a considerably short amount of time.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.07147v1
PDF	http://arxiv.org/pdf/1710.07147v1.pdf
PWC	https://paperswithcode.com/paper/a-two-phase-safe-vehicle-routing-and
Repo
Framework

SmartPaste: Learning to Adapt Source Code


Title	SmartPaste: Learning to Adapt Source Code
Authors	Miltiadis Allamanis, Marc Brockschmidt
Abstract	Deep Neural Networks have been shown to succeed at a range of natural language tasks such as machine translation and text summarization. While tasks on source code (ie, formal languages) have been considered recently, most work in this area does not attempt to capitalize on the unique opportunities offered by its known syntax and structure. In this work, we introduce SmartPaste, a first task that requires to use such information. The task is a variant of the program repair problem that requires to adapt a given (pasted) snippet of code to surrounding, existing source code. As first solutions, we design a set of deep neural models that learn to represent the context of each variable location and variable usage in a data flow-sensitive way. Our evaluation suggests that our models can learn to solve the SmartPaste task in many cases, achieving 58.6% accuracy, while learning meaningful representation of variable usages.
Tasks	Machine Translation, Text Summarization
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07867v1
PDF	http://arxiv.org/pdf/1705.07867v1.pdf
PWC	https://paperswithcode.com/paper/smartpaste-learning-to-adapt-source-code
Repo
Framework

Sparse Approximation of 3D Meshes using the Spectral Geometry of the Hamiltonian Operator


Title	Sparse Approximation of 3D Meshes using the Spectral Geometry of the Hamiltonian Operator
Authors	Yoni Choukroun, Gautam Pai, Ron Kimmel
Abstract	The discrete Laplace operator is ubiquitous in spectral shape analysis, since its eigenfunctions are provably optimal in representing smooth functions defined on the surface of the shape. Indeed, subspaces defined by its eigenfunctions have been utilized for shape compression, treating the coordinates as smooth functions defined on the given surface. However, surfaces of shapes in nature often contain geometric structures for which the general smoothness assumption may fail to hold. At the other end, some explicit mesh compression algorithms utilize the order by which vertices that represent the surface are traversed, a property which has been ignored in spectral approaches. Here, we incorporate the order of vertices into an operator that defines a novel spectral domain. We propose a method for representing 3D meshes using the spectral geometry of the Hamiltonian operator, integrated within a sparse approximation framework. We adapt the concept of a potential function from quantum physics and incorporate vertex ordering information into the potential, yielding a novel data-dependent operator. The potential function modifies the spectral geometry of the Laplacian to focus on regions with finer details of the given surface. By sparsely encoding the geometry of the shape using the proposed data-dependent basis, we improve compression performance compared to previous results that use the standard Laplacian basis and spectral graph wavelets.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02120v2
PDF	http://arxiv.org/pdf/1707.02120v2.pdf
PWC	https://paperswithcode.com/paper/sparse-approximation-of-3d-meshes-using-the
Repo
Framework

Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos


Title	Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos
Authors	Jie Song, Limin Wang, Luc Van Gool, Otmar Hilliges
Abstract	Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no examples in training data sets. Temporal information can provide additional cues about the location of body joints and help to alleviate these issues. In this paper, we propose a deep structured model to estimate a sequence of human poses in unconstrained videos. This model can be efficiently trained in an end-to-end manner and is capable of representing appearance of body joints and their spatio-temporal relationships simultaneously. Domain knowledge about the human body is explicitly incorporated into the network providing effective priors to regularize the skeletal structure and to enforce temporal consistency. The proposed end-to-end architecture is evaluated on two widely used benchmarks (Penn Action dataset and JHMDB dataset) for video-based pose estimation. Our approach significantly outperforms the existing state-of-the-art methods.
Tasks	Pose Estimation
Published	2017-03-31
URL	http://arxiv.org/abs/1703.10898v1
PDF	http://arxiv.org/pdf/1703.10898v1.pdf
PWC	https://paperswithcode.com/paper/thin-slicing-network-a-deep-structured-model
Repo
Framework

Moderate Environmental Variation Promotes the Evolution of Robust Solutions


Title	Moderate Environmental Variation Promotes the Evolution of Robust Solutions
Authors	Nicola Milano, Jônata Tyska Carvalho, Stefano Nolfi
Abstract	Previous evolutionary studies demonstrated how evaluating evolving agents in variable environmental conditions enable them to develop solutions that are robust to environmental variation. We demonstrate how the robustness of the agents can be further improved by exposing them also to environmental variations throughout generations. These two types of environmental variations play partially distinct roles as demonstrated by the fact that agents evolved in environments that do not vary throughout generations display lower performance than agents evolved in varying environments independently from the amount of environmental variation experienced during evaluation. Moreover, our results demonstrate that performance increases when the amount of variations introduced during agents evaluation and the rate at which the environment varies throughout generations are moderate. This is explained by the fact that the probability to retain genetic variations, including non-neutral variations that alter the behavior of the agents, increases when the environment varies throughout generations but also when new environmental conditions persist over time long enough to enable genetic accommodation.
Tasks
Published	2017-10-22
URL	http://arxiv.org/abs/1710.07913v2
PDF	http://arxiv.org/pdf/1710.07913v2.pdf
PWC	https://paperswithcode.com/paper/moderate-environmental-variation-promotes-the
Repo
Framework

End-to-end 3D face reconstruction with deep neural networks


Title	End-to-end 3D face reconstruction with deep neural networks
Authors	Pengfei Dou, Shishir K. Shah, Ioannis A. Kakadiaris
Abstract	Monocular 3D facial shape reconstruction from a single 2D facial image has been an active research area due to its wide applications. Inspired by the success of deep neural networks (DNN), we propose a DNN-based approach for End-to-End 3D FAce Reconstruction (UH-E2FAR) from a single 2D image. Different from recent works that reconstruct and refine the 3D face in an iterative manner using both an RGB image and an initial 3D facial shape rendering, our DNN model is end-to-end, and thus the complicated 3D rendering process can be avoided. Moreover, we integrate in the DNN architecture two components, namely a multi-task loss function and a fusion convolutional neural network (CNN) to improve facial expression reconstruction. With the multi-task loss function, 3D face reconstruction is divided into neutral 3D facial shape reconstruction and expressive 3D facial shape reconstruction. The neutral 3D facial shape is class-specific. Therefore, higher layer features are useful. In comparison, the expressive 3D facial shape favors lower or intermediate layer features. With the fusion-CNN, features from different intermediate layers are fused and transformed for predicting the 3D expressive facial shape. Through extensive experiments, we demonstrate the superiority of our end-to-end framework in improving the accuracy of 3D face reconstruction.
Tasks	3D Face Reconstruction, Face Reconstruction
Published	2017-04-17
URL	http://arxiv.org/abs/1704.05020v1
PDF	http://arxiv.org/pdf/1704.05020v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-3d-face-reconstruction-with-deep
Repo
Framework

Learning Sparse Structural Changes in High-dimensional Markov Networks: A Review on Methodologies and Theories


Title	Learning Sparse Structural Changes in High-dimensional Markov Networks: A Review on Methodologies and Theories
Authors	Song Liu, Kenji Fukumizu, Taiji Suzuki
Abstract	Recent years have seen an increasing popularity of learning the sparse \emph{changes} in Markov Networks. Changes in the structure of Markov Networks reflect alternations of interactions between random variables under different regimes and provide insights into the underlying system. While each individual network structure can be complicated and difficult to learn, the overall change from one network to another can be simple. This intuition gave birth to an approach that \emph{directly} learns the sparse changes without modelling and learning the individual (possibly dense) networks. In this paper, we review such a direct learning method with some latest developments along this line of research.
Tasks
Published	2017-01-06
URL	http://arxiv.org/abs/1701.01582v2
PDF	http://arxiv.org/pdf/1701.01582v2.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-structural-changes-in-high
Repo
Framework

Learning of state-space models with highly informative observations: a tempered Sequential Monte Carlo solution


Title	Learning of state-space models with highly informative observations: a tempered Sequential Monte Carlo solution
Authors	Andreas Svensson, Thomas B. Schön, Fredrik Lindsten
Abstract	Probabilistic (or Bayesian) modeling and learning offers interesting possibilities for systematic representation of uncertainty using probability theory. However, probabilistic learning often leads to computationally challenging problems. Some problems of this type that were previously intractable can now be solved on standard personal computers thanks to recent advances in Monte Carlo methods. In particular, for learning of unknown parameters in nonlinear state-space models, methods based on the particle filter (a Monte Carlo method) have proven very useful. A notoriously challenging problem, however, still occurs when the observations in the state-space model are highly informative, i.e. when there is very little or no measurement noise present, relative to the amount of process noise. The particle filter will then struggle in estimating one of the basic components for probabilistic learning, namely the likelihood $p($data$$parameters$)$. To this end we suggest an algorithm which initially assumes that there is substantial amount of artificial measurement noise present. The variance of this noise is sequentially decreased in an adaptive fashion such that we, in the end, recover the original problem or possibly a very close approximation of it. The main component in our algorithm is a sequential Monte Carlo (SMC) sampler, which gives our proposed method a clear resemblance to the SMC^2 method. Another natural link is also made to the ideas underlying the approximate Bayesian computation (ABC). We illustrate it with numerical examples, and in particular show promising results for a challenging Wiener-Hammerstein benchmark problem.
Tasks
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01618v2
PDF	http://arxiv.org/pdf/1702.01618v2.pdf
PWC	https://paperswithcode.com/paper/learning-of-state-space-models-with-highly
Repo
Framework

A Large-Scale Exploration of Factors Affecting Hand Hygiene Compliance Using Linear Predictive Models


Title	A Large-Scale Exploration of Factors Affecting Hand Hygiene Compliance Using Linear Predictive Models
Authors	Michael T. Lash, Jason Slater, Philip M. Polgreen, Alberto M. Segre
Abstract	This large-scale study, consisting of 24.5 million hand hygiene opportunities spanning 19 distinct facilities in 10 different states, uses linear predictive models to expose factors that may affect hand hygiene compliance. We examine the use of features such as temperature, relative humidity, influenza severity, day/night shift, federal holidays and the presence of new residents in predicting daily hand hygiene compliance. The results suggest that colder temperatures and federal holidays have an adverse effect on hand hygiene compliance rates, and that individual cultures and attitudes regarding hand hygiene seem to exist among facilities.
Tasks
Published	2017-05-06
URL	http://arxiv.org/abs/1705.03540v2
PDF	http://arxiv.org/pdf/1705.03540v2.pdf
PWC	https://paperswithcode.com/paper/a-large-scale-exploration-of-factors
Repo
Framework

Detection and Analysis of Human Emotions through Voice and Speech Pattern Processing


Title	Detection and Analysis of Human Emotions through Voice and Speech Pattern Processing
Authors	Poorna Banerjee Dasgupta
Abstract	The ability to modulate vocal sounds and generate speech is one of the features which set humans apart from other living beings. The human voice can be characterized by several attributes such as pitch, timbre, loudness, and vocal tone. It has often been observed that humans express their emotions by varying different vocal attributes during speech generation. Hence, deduction of human emotions through voice and speech analysis has a practical plausibility and could potentially be beneficial for improving human conversational and persuasion skills. This paper presents an algorithmic approach for detection and analysis of human emotions with the help of voice and speech processing. The proposed approach has been developed with the objective of incorporation with futuristic artificial intelligence systems for improving human-computer interactions.
Tasks
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10198v1
PDF	http://arxiv.org/pdf/1710.10198v1.pdf
PWC	https://paperswithcode.com/paper/detection-and-analysis-of-human-emotions
Repo
Framework

Accelerating Training of Deep Neural Networks via Sparse Edge Processing


Title	Accelerating Training of Deep Neural Networks via Sparse Edge Processing
Authors	Sourya Dey, Yinan Shao, Keith M. Chugg, Peter A. Beerel
Abstract	We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational requirements. This novel architecture introduces the notion of edge-processing to provide flexibility and combines junction pipelining and operational parallelization to speed up training. The overall effect is to reduce network complexity by factors up to 30x and training time by up to 35x relative to GPUs, while maintaining high fidelity of inference results. This has the potential to enable extensive parameter searches and development of the largely unexplored theoretical foundation of DNNs. The architecture automatically adapts itself to different network sizes given available hardware resources. As proof of concept, we show results obtained for different bit widths.
Tasks
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01343v1
PDF	http://arxiv.org/pdf/1711.01343v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-training-of-deep-neural-networks-1
Repo
Framework

End-to-end learning potentials for structured attribute prediction


Title	End-to-end learning potentials for structured attribute prediction
Authors	Kota Yamaguchi, Takayuki Okatani, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo
Abstract	We present a structured inference approach in deep neural networks for multiple attribute prediction. In attribute prediction, a common approach is to learn independent classifiers on top of a good feature representation. However, such classifiers assume conditional independence on features and do not explicitly consider the dependency between attributes in the inference process. We propose to formulate attribute prediction in terms of marginal inference in the conditional random field. We model potential functions by deep neural networks and apply the sum-product algorithm to solve for the approximate marginal distribution in feed-forward networks. Our message passing layer implements sparse pairwise potentials by a softplus-linear function that is equivalent to a higher-order classifier, and learns all the model parameters by end-to-end back propagation. The experimental results using SUN attributes and CelebA datasets suggest that the structured inference improves the attribute prediction performance, and possibly uncovers the hidden relationship between attributes.
Tasks
Published	2017-08-06
URL	http://arxiv.org/abs/1708.01892v1
PDF	http://arxiv.org/pdf/1708.01892v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-learning-potentials-for-structured
Repo
Framework

Stepwise regression for unsupervised learning


Title	Stepwise regression for unsupervised learning
Authors	Jonathan Landy
Abstract	I consider unsupervised extensions of the fast stepwise linear regression algorithm \cite{efroymson1960multiple}. These extensions allow one to efficiently identify highly-representative feature variable subsets within a given set of jointly distributed variables. This in turn allows for the efficient dimensional reduction of large data sets via the removal of redundant features. Fast search is effected here through the avoidance of repeat computations across trial fits, allowing for a full representative-importance ranking of a set of feature variables to be carried out in $O(n^2 m)$ time, where $n$ is the number of variables and $m$ is the number of data samples available. This runtime complexity matches that needed to carry out a single regression and is $O(n^2)$ faster than that of naive implementations. I present pseudocode suitable for efficient forward, reverse, and forward-reverse unsupervised feature selection. To illustrate the algorithm’s application, I apply it to the problem of identifying representative stocks within a given financial market index – a challenge relevant to the design of Exchange Traded Funds (ETFs). I also characterize the growth of numerical error with iteration step in these algorithms, and finally demonstrate and rationalize the observation that the forward and reverse algorithms return exactly inverted feature orderings in the weakly-correlated feature set regime.
Tasks	Feature Selection
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03265v1
PDF	http://arxiv.org/pdf/1706.03265v1.pdf
PWC	https://paperswithcode.com/paper/stepwise-regression-for-unsupervised-learning
Repo
Framework

Improving Object Detection with Region Similarity Learning


Title	Improving Object Detection with Region Similarity Learning
Authors	Feng Gao, Yihang Lou, Yan Bai, Shiqi Wang, Tiejun Huang, Ling-Yu Duan
Abstract	Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant progress of object proposal and convolutional neural networks (CNNs). Most promising detectors involve multi-task learning with an optimization objective of softmax loss and regression loss. The first is for multi-class categorization, while the latter is for improving localization accuracy. However, few of them attempt to further investigate the hardness of distinguishing different sorts of distracting background regions (i.e., negatives) from true object regions (i.e., positives). To improve the performance of classifying positive object regions vs. a variety of negative background regions, we propose to incorporate triplet embedding into learning objective. The triplet units are formed by assigning each negative region to a meaningful object class and establishing class- specific negatives, followed by triplets construction. Over the benchmark PASCAL VOC 2007, the proposed triplet em- bedding has improved the performance of well-known FastRCNN model with a mAP gain of 2.1%. In particular, the state-of-the-art approach OHEM can benefit from the triplet embedding and has achieved a mAP improvement of 1.2%.
Tasks	Multi-Task Learning, Object Detection
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00234v1
PDF	http://arxiv.org/pdf/1703.00234v1.pdf
PWC	https://paperswithcode.com/paper/improving-object-detection-with-region
Repo
Framework

Performing Stance Detection on Twitter Data using Computational Linguistics Techniques


Title	Performing Stance Detection on Twitter Data using Computational Linguistics Techniques
Authors	Gourav G. Shenoy, Erika H. Dsouza, Sandra Kübler
Abstract	As humans, we can often detect from a persons utterances if he or she is in favor of or against a given target entity (topic, product, another person, etc). But from the perspective of a computer, we need means to automatically deduce the stance of the tweeter, given just the tweet text. In this paper, we present our results of performing stance detection on twitter data using a supervised approach. We begin by extracting bag-of-words to perform classification using TIMBL, then try and optimize the features to improve stance detection accuracy, followed by extending the dataset with two sets of lexicons - arguing, and MPQA subjectivity; next we explore the MALT parser and construct features using its dependency triples, finally we perform analysis using Scikit-learn Random Forest implementation.
Tasks	Stance Detection
Published	2017-03-06
URL	http://arxiv.org/abs/1703.02019v1
PDF	http://arxiv.org/pdf/1703.02019v1.pdf
PWC	https://paperswithcode.com/paper/performing-stance-detection-on-twitter-data
Repo
Framework