January 29, 2020

2919 words 14 mins read

Paper Group ANR 747

Your Gameplay Says It All: Modelling Motivation in Tom Clancy’s The Division. Solving the Reaction-Diffusion equation based on analytical methods and deep learning algorithm; the Case study of sulfate attack to concrete. A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing. High-speed Video from Asynchronous Camera A …

Your Gameplay Says It All: Modelling Motivation in Tom Clancy’s The Division


Title	Your Gameplay Says It All: Modelling Motivation in Tom Clancy’s The Division
Authors	David Melhart, Ahmad Azadvar, Alessandro Canossa, Antonios Liapis, Georgios N. Yannakakis
Abstract	Is it possible to predict the motivation of players just by observing their gameplay data? Even if so, how should we measure motivation in the first place? To address the above questions, on the one end, we collect a large dataset of gameplay data from players of the popular game Tom Clancy’s The Division. On the other end, we ask them to report their levels of competence, autonomy, relatedness and presence using the Ubisoft Perceived Experience Questionnaire. After processing the survey responses in an ordinal fashion we employ preference learning methods based on support vector machines to infer the mapping between gameplay and the reported four motivation factors. Our key findings suggest that gameplay features are strong predictors of player motivation as the best obtained models reach accuracies of near certainty, from 92% up to 94% on unseen players.
Tasks
Published	2019-01-31
URL	https://arxiv.org/abs/1902.00040v2
PDF	https://arxiv.org/pdf/1902.00040v2.pdf
PWC	https://paperswithcode.com/paper/your-gameplay-says-it-all-modelling
Repo
Framework

Solving the Reaction-Diffusion equation based on analytical methods and deep learning algorithm; the Case study of sulfate attack to concrete


Title	Solving the Reaction-Diffusion equation based on analytical methods and deep learning algorithm; the Case study of sulfate attack to concrete
Authors	Amin Karimi Monsefi, Rana Bakhtiyarzade
Abstract	The reaction-diffusion equation is one of the cornerstones equations in applied science and engineering. In the present study, a deep neural network has been trained in order to predict the solution of the equation with different coefficients using the numerical solution of this equation and the utility of deep learning. Analytical solution of the Reaction-Diffusion equation also has been conducted by taking advantage of the Danckwerts method. The accuracy of deep learning results was compared with the analytical solutions. In order to decrease the learning time and to find out similar equations solutions, such as pure diffusion and pure reaction, dimensional analysis technique has been performed. It was demonstrated that deep learning can accurately estimate the Partial Differential Equations solutionin the case of the reaction-diffusion equation with a constant coefficient.
Tasks
Published	2019-12-07
URL	https://arxiv.org/abs/1912.05452v1
PDF	https://arxiv.org/pdf/1912.05452v1.pdf
PWC	https://paperswithcode.com/paper/solving-the-reaction-diffusion-equation-based
Repo
Framework

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing


Title	A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
Authors	Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Ian Reid
Abstract	Image smoothing is a fundamental procedure in applications of both computer vision and graphics. The required smoothing properties can be different or even contradictive among different tasks. Nevertheless, the inherent smoothing nature of one smoothing operator is usually fixed and thus cannot meet the various requirements of different applications. In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved. To this end, we first introduce the truncated Huber penalty function which has seldom been used in image smoothing. A robust framework is then proposed. When combined with the strong flexibility of the truncated Huber penalty function, our framework is capable of a range of applications and can outperform the state-of-the-art approaches in several tasks. In addition, an efficient numerical solution is provided and its convergence is theoretically guaranteed even the optimization framework is non-convex and non-smooth. The effectiveness and superior performance of our approach are validated through comprehensive experimental results in a range of applications.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09642v4
PDF	https://arxiv.org/pdf/1907.09642v4.pdf
PWC	https://paperswithcode.com/paper/a-generalized-framework-for-edge-preserving
Repo
Framework

High-speed Video from Asynchronous Camera Array


Title	High-speed Video from Asynchronous Camera Array
Authors	Si Lu
Abstract	This paper presents a method for capturing high-speed video using an asynchronous camera array. Our method sequentially fires each sensor in a camera array with a small time offset and assembles captured frames into a high-speed video according to the time stamps. The resulting video, however, suffers from parallax jittering caused by the viewpoint difference among sensors in the camera array. To address this problem, we develop a dedicated novel view synthesis algorithm that transforms the video frames as if they were captured by a single reference sensor. Specifically, for any frame from a non-reference sensor, we find the two temporally neighboring frames captured by the reference sensor. Using these three frames, we render a new frame with the same time stamp as the non-reference frame but from the viewpoint of the reference sensor. Specifically, we segment these frames into super-pixels and then apply local content-preserving warping to warp them to form the new frame. We employ a multi-label Markov Random Field method to blend these warped frames. Our experiments show that our method can produce high-quality and high-speed video of a wide variety of scenes with large parallax, scene dynamics, and camera motion and outperforms several baseline and state-of-the-art approaches.
Tasks	Novel View Synthesis
Published	2019-01-17
URL	http://arxiv.org/abs/1901.06034v1
PDF	http://arxiv.org/pdf/1901.06034v1.pdf
PWC	https://paperswithcode.com/paper/high-speed-video-from-asynchronous-camera
Repo
Framework

Backward-Forward Algorithm: An Improvement towards Extreme Learning Machine


Title	Backward-Forward Algorithm: An Improvement towards Extreme Learning Machine
Authors	Dibyasundar Das, Deepak Ranjan Nayak, Ratnakar Dash, Banshidhar Majhi
Abstract	The extreme learning machine needs a large number of hidden nodes to generalize a single hidden layer neural network for a given training data-set. The need for more number of hidden nodes suggests that the neural-network is memorizing rather than generalizing the model. Hence, a supervised learning method is described here that uses Moore-Penrose approximation to determine both input-weight and output-weight in two epochs, namely, backward-pass and forward-pass. The proposed technique has an advantage over the back-propagation method in terms of iterations required and is superior to the extreme learning machine in terms of the number of hidden units necessary for generalization.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10282v4
PDF	https://arxiv.org/pdf/1907.10282v4.pdf
PWC	https://paperswithcode.com/paper/backward-forward-algorithm-an-improvement
Repo
Framework

Universal approximations of permutation invariant/equivariant functions by deep neural networks


Title	Universal approximations of permutation invariant/equivariant functions by deep neural networks
Authors	Akiyoshi Sannai, Yuuki Takai, Matthieu Cordonnier
Abstract	In this paper, we develop a theory about the relationship between $G$-invariant/equivariant functions and deep neural networks for finite group $G$. Especially, for a given $G$-invariant/equivariant function, we construct its universal approximator by deep neural network whose layers equip $G$-actions and each affine transformations are $G$-equivariant/invariant. Due to representation theory, we can show that this approximator has exponentially fewer free parameters than usual models.
Tasks
Published	2019-03-05
URL	https://arxiv.org/abs/1903.01939v3
PDF	https://arxiv.org/pdf/1903.01939v3.pdf
PWC	https://paperswithcode.com/paper/universal-approximations-of-permutation
Repo
Framework

Evolutionary Deep Learning to Identify Galaxies in the Zone of Avoidance


Title	Evolutionary Deep Learning to Identify Galaxies in the Zone of Avoidance
Authors	David Jones, Anja Schroeder, Geoff Nitschke
Abstract	The Zone of Avoidance makes it difficult for astronomers to catalogue galaxies at low latitudes to our galactic plane due to high star densities and extinction. However, having a complete sky map of galaxies is important in a number of fields of research in astronomy. There are many unclassified sources of light in the Zone of Avoidance and it is therefore important that there exists an accurate automated system to identify and classify galaxies in this region. This study aims to evaluate the efficiency and accuracy of using an evolutionary algorithm to evolve the topology and configuration of Convolutional Neural Network (CNNs) to automatically identify galaxies in the Zone of Avoidance. A supervised learning method is used with data containing near-infrared images. Input image resolution and number of near-infrared passbands needed by the evolutionary algorithm is also analyzed while the accuracy of the best evolved CNN is compared to other CNN variants.
Tasks
Published	2019-03-06
URL	http://arxiv.org/abs/1903.07461v2
PDF	http://arxiv.org/pdf/1903.07461v2.pdf
PWC	https://paperswithcode.com/paper/evolutionary-deep-learning-to-identify
Repo
Framework

A Simple and Effective Approach for Fine Tuning Pre-trained Word Embeddings for Improved Text Classification


Title	A Simple and Effective Approach for Fine Tuning Pre-trained Word Embeddings for Improved Text Classification
Authors	Amr Al-Khatib, Samhaa R. El-Beltagy
Abstract	This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning process, and contributes to the final word vector for that term. As a result, words that are used distinctively within a particular class, will bear vectors that are closer to each other in the embedding space and will be more discriminative towards that class. To validate this novel approach, it was applied to three Arabic and two English datasets that have been previously used for text classification tasks such as sentiment analysis and emotion detection. In the vast majority of cases, the results obtained using the proposed approach, improved considerably.
Tasks	Sentiment Analysis, Text Classification, Word Embeddings
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02579v2
PDF	https://arxiv.org/pdf/1908.02579v2.pdf
PWC	https://paperswithcode.com/paper/a-simple-and-effective-approach-for-fine
Repo
Framework

In-training Matrix Factorization for Parameter-frugal Neural Machine Translation


Title	In-training Matrix Factorization for Parameter-frugal Neural Machine Translation
Authors	Zachary Kaden, Teven Le Scao, Raphael Olivier
Abstract	In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation. Using in-training matrix factorization, parameter matrices may be decomposed into the products of smaller matrices, which can compress large machine translation architectures by vastly reducing the number of learnable parameters. We apply in-training matrix factorization to different layers of standard neural architectures and show that in-training factorization is capable of reducing nearly 50% of learnable parameters without any associated loss in BLEU score. Further, we find that in-training matrix factorization is especially powerful on embedding layers, providing a simple and effective method to curtail the number of parameters with minimal impact on model performance, and, at times, an increase in performance.
Tasks	Machine Translation
Published	2019-09-27
URL	https://arxiv.org/abs/1910.06393v2
PDF	https://arxiv.org/pdf/1910.06393v2.pdf
PWC	https://paperswithcode.com/paper/in-training-matrix-factorization-for-1
Repo
Framework

A Deep Learning Approach for Tweet Classification and Rescue Scheduling for Effective Disaster Management


Title	A Deep Learning Approach for Tweet Classification and Rescue Scheduling for Effective Disaster Management
Authors	Md. Yasin Kabir, Sanjay Madria
Abstract	It is a challenging and complex task to acquire information from different regions of a disaster-affected area in a timely fashion. The extensive spread and reach of social media and networks allow people to share information in real-time. However, the processing of social media data and gathering of valuable information require a series of operations such as (1) processing each specific tweet for a text classification, (2) possible location determination of people needing help based on tweets, and (3) priority calculations of rescue tasks based on the classification of tweets. These are three primary challenges in developing an effective rescue scheduling operation using social media data. In this paper, first, we propose a deep learning model combining attention based Bi-directional Long Short-Term Memory (BLSTM) and Convolutional Neural Network (CNN) to classify the tweets under different categories. We use pre-trained crisis word vectors and global vectors for word representation (GLoVe) for capturing semantic meaning from tweets. Next, we perform feature engineering to create an auxiliary feature map which dramatically increases the model accuracy. In our experiments using real data sets from Hurricanes Harvey and Irma, it is observed that our proposed approach performs better compared to other classification methods based on Precision, Recall, F1-score, and Accuracy, and is highly effective to determine the correct priority of a tweet. Furthermore, to evaluate the effectiveness and robustness of the proposed classification model a merged dataset comprises of 4 different datasets from CrisisNLP and another 15 different disasters data from CrisisLex are used. Finally, we develop an adaptive multitask hybrid scheduling algorithm considering resource constraints to perform an effective rescue scheduling operation considering different rescue priorities.
Tasks	Feature Engineering, Text Classification
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01456v1
PDF	https://arxiv.org/pdf/1908.01456v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-approach-for-tweet
Repo
Framework

Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks


Title	Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks
Authors	Jenna Kanerva, Filip Ginter, Tapio Salakoski
Abstract	In this paper we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 60 out of 76 treebanks reducing errors on average by 18% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.
Tasks	Data Augmentation, Lemmatization
Published	2019-02-03
URL	http://arxiv.org/abs/1902.00972v1
PDF	http://arxiv.org/pdf/1902.00972v1.pdf
PWC	https://paperswithcode.com/paper/universal-lemmatizer-a-sequence-to-sequence
Repo
Framework

Linear Dynamics: Clustering without identification


Title	Linear Dynamics: Clustering without identification
Authors	Chloe Ching-Yun Hsu, Michaela Hardt, Moritz Hardt
Abstract	Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical system is a venerable task, permitting provably efficient solutions only in special cases. This work shows that the eigenspectrum of unknown linear dynamics can be identified without full system identification. We analyze a computationally efficient and provably convergent algorithm to estimate the eigenvalues of the state-transition matrix in a linear dynamical system. When applied to time series clustering, our algorithm can efficiently cluster multi-dimensional time series with temporal offsets and varying lengths, under the assumption that the time series are generated from linear dynamical systems. Evaluating our algorithm on both synthetic data and real electrocardiogram (ECG) signals, we see improvements in clustering quality over existing baselines.
Tasks	Time Series, Time Series Clustering
Published	2019-08-02
URL	https://arxiv.org/abs/1908.01039v3
PDF	https://arxiv.org/pdf/1908.01039v3.pdf
PWC	https://paperswithcode.com/paper/linear-dynamics-clustering-without
Repo
Framework

Improving Long Distance Slot Carryover in Spoken Dialogue Systems


Title	Improving Long Distance Slot Carryover in Spoken Dialogue Systems
Authors	Tongfei Chen, Chetan Naik, Hua He, Pushpendre Rastogi, Lambert Mathias
Abstract	Tracking the state of the conversation is a central component in task-oriented spoken dialogue systems. One such approach for tracking the dialogue state is slot carryover, where a model makes a binary decision if a slot from the context is relevant to the current turn. Previous work on the slot carryover task used models that made independent decisions for each slot. A close analysis of the results show that this approach results in poor performance over longer context dialogues. In this paper, we propose to jointly model the slots. We propose two neural network architectures, one based on pointer networks that incorporate slot ordering information, and the other based on transformer networks that uses self attention mechanism to model the slot interdependencies. Our experiments on an internal dialogue benchmark dataset and on the public DSTC2 dataset demonstrate that our proposed models are able to resolve longer distance slot references and are able to achieve competitive performance.
Tasks	Spoken Dialogue Systems
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01149v1
PDF	https://arxiv.org/pdf/1906.01149v1.pdf
PWC	https://paperswithcode.com/paper/improving-long-distance-slot-carryover-in
Repo
Framework

Time-Aware Prospective Modeling of Users for Online Display Advertising


Title	Time-Aware Prospective Modeling of Users for Online Display Advertising
Authors	Djordje Gligorijevic, Jelena Gligorijevic, Aaron Flores
Abstract	Prospective display advertising poses a great challenge for large advertising platforms as the strongest predictive signals of users are not eligible to be used in the conversion prediction systems. To that end efforts are made to collect as much information as possible about each user from various data sources and to design powerful models that can capture weaker signals ultimately obtaining good quality of conversion prediction probability estimates. In this study we propose a novel time-aware approach to model heterogeneous sequences of users’ activities and capture implicit signals of users’ conversion intents. On two real-world datasets we show that our approach outperforms other, previously proposed approaches, while providing interpretability of signal impact to conversion probability.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05100v1
PDF	https://arxiv.org/pdf/1911.05100v1.pdf
PWC	https://paperswithcode.com/paper/time-aware-prospective-modeling-of-users-for
Repo
Framework

Detecting Robotic Affordances on Novel Objects with Regional Attention and Attributes


Title	Detecting Robotic Affordances on Novel Objects with Regional Attention and Attributes
Authors	Fu-Jen Chu, Ruinian Xu, Patricio A. Vela
Abstract	This paper presents a framework for predicting affordances of object parts of unseen categories, with application to robot manipulation. The framework generates affordance maps of novel objects within an image via region-based affordance segmentation. Earlier work used category priors while jointly optimizing detection and segmentation to boost accuracy with limited ability to generalize to unknown categories. This work integrates a category-agnostic region proposal network for proposing instance regions of an image across categories. A self-attention mechanism trained to interpret each proposal learns to capture rich contextual dependencies through the region. To further guide affordance learning in the absence of category priors, an auxiliary task of object attribute inference improves local feature learning. Experimental results show that the trained deep network architecture achieves state-of-the-art performance on affordance segmentation of novel objects and outperforms several baselines. An ablation study quantifies the effectiveness and contributions of each proposed component. Experiments demonstrate the use of affordance detection on novel objects for vision tasks and for manipulation.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05770v1
PDF	https://arxiv.org/pdf/1909.05770v1.pdf
PWC	https://paperswithcode.com/paper/detecting-robotic-affordances-on-novel
Repo
Framework