January 28, 2020

3148 words 15 mins read

Paper Group ANR 862

Forensic Similarity for Digital Images. Self-supervised blur detection from synthetically blurred scenes. Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation. A stochastic game theory approach for the prediction of interfacial parameters in two-phase flow systems. Determining the Mechanical Properties of a New Composi …

Forensic Similarity for Digital Images


Title	Forensic Similarity for Digital Images
Authors	Owen Mayer, Matthew C. Stamm
Abstract	In this paper we introduce a new digital image forensics approach called forensic similarity, which determines whether two image patches contain the same forensic trace or different forensic traces. One benefit of this approach is that prior knowledge, e.g. training samples, of a forensic trace are not required to make a forensic similarity decision on it in the future. To do this, we propose a two part deep-learning system composed of a CNN-based feature extractor and a three-layer neural network, called the similarity network. This system maps pairs of image patches to a score indicating whether they contain the same or different forensic traces. We evaluated system accuracy of determining whether two image patches were 1) captured by the same or different camera model, 2) manipulated by the same or different editing operation, and 3) manipulated by the same or different manipulation parameter, given a particular editing operation. Experiments demonstrate applicability to a variety of forensic traces, and importantly show efficacy on “unknown” forensic traces that were not used to train the system. Experiments also show that the proposed system significantly improves upon prior art, reducing error rates by more than half. Furthermore, we demonstrated the utility of the forensic similarity approach in two practical applications: forgery detection and localization, and database consistency verification.
Tasks
Published	2019-02-13
URL	https://arxiv.org/abs/1902.04684v2
PDF	https://arxiv.org/pdf/1902.04684v2.pdf
PWC	https://paperswithcode.com/paper/forensic-similarity-for-digital-images
Repo
Framework

Self-supervised blur detection from synthetically blurred scenes


Title	Self-supervised blur detection from synthetically blurred scenes
Authors	Aitor Alvarez-Gila, Adrian Galdran, Estibaliz Garrote, Joost van de Weijer
Abstract	Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labour intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10638v1
PDF	https://arxiv.org/pdf/1908.10638v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-blur-detection-from
Repo
Framework

Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation


Title	Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation
Authors	Rania Briq, Andreas Doering, Juergen Gall
Abstract	We propose a joint model of human joint detection and association for 2D multi-person pose estimation (MPPE). The approach unifies training of joint detection and association without a need for further processing or sophisticated heuristics in order to associate the joints with people individually. The approach consists of two stages, where in the first stage joint detection heatmaps and association features are extracted, and in the second stage, whose input are the extracted features of the first stage, we introduce a recurrent neural network (RNN) which predicts the heatmaps of a single person’s joints in each iteration. In addition, the network learns a stopping criterion in order to halt once it has identified all individuals in the image. This approach allowed us to eliminate several heuristic assumptions and parameters needed for association which do not necessarily hold true. Additionally, such an end-to-end approach allows the final objective to be known and directly optimized over during training. We evaluated our model on the challenging MSCOCO dataset and obtained an improvement over the baseline, particularly in challenging scenes with occlusions.
Tasks	Multi-Person Pose Estimation, Pose Estimation
Published	2019-04-26
URL	http://arxiv.org/abs/1904.11864v1
PDF	http://arxiv.org/pdf/1904.11864v1.pdf
PWC	https://paperswithcode.com/paper/unifying-part-detection-and-association-for
Repo
Framework

A stochastic game theory approach for the prediction of interfacial parameters in two-phase flow systems


Title	A stochastic game theory approach for the prediction of interfacial parameters in two-phase flow systems
Authors	Zhuoran Dang
Abstract	The prediction of interfacial area properties in two-phase flow systems is difficult and challenging. In this paper, a conceptual idea of using single-agent reinforcement learning for the behaviors of two-phase flows and IAC behaviors is proposed. The basic assumption for this application is that the development of two-phase flow is considered to be a stochastic process with Markov property. The details of the design of simple Markov games are described and approaches of gaming solutions are adapted. The experiment shows that both of the steam fraction and IAC prediction processes converge. The model predictions are compared with the experimental results, and the tendency matches although some oscillations exist. The performances and prediction results can be improved by elaborating the game environment setup.
Tasks
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02750v1
PDF	https://arxiv.org/pdf/1908.02750v1.pdf
PWC	https://paperswithcode.com/paper/a-stochastic-game-theory-approach-for-the
Repo
Framework

Determining the Mechanical Properties of a New Composite Material Using Artificial Neural Networks


Title	Determining the Mechanical Properties of a New Composite Material Using Artificial Neural Networks
Authors	Emilia Ciupan, Mihai Ciupan, Daniela-Corina Jucan
Abstract	The paper studies the possibility of using artificial neural networks (ANN) to determine certain mechanical properties of a new composite material. This new material is obtained by a mixture of hemp and polypropylene fibres. The material was developed for the industry of upholstered furniture. Specifically, it is intended for the making of elements of the support structure of some upholstered goods (chairs, armchairs, sofa sides) with the objective of replacing wood. The paper aims to calculate the following mechanical properties: maximum tensile strength and maximum elongation.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.10050v1
PDF	http://arxiv.org/pdf/1901.10050v1.pdf
PWC	https://paperswithcode.com/paper/determining-the-mechanical-properties-of-a
Repo
Framework

Natural Language Processing, Sentiment Analysis and Clinical Analytics


Title	Natural Language Processing, Sentiment Analysis and Clinical Analytics
Authors	Adil Rajput
Abstract	Recent advances in Big Data has prompted health care practitioners to utilize the data available on social media to discern sentiment and emotions expression. Health Informatics and Clinical Analytics depend heavily on information gathered from diverse sources. Traditionally, a healthcare practitioner will ask a patient to fill out a questionnaire that will form the basis of diagnosing the medical condition. However, medical practitioners have access to many sources of data including the patients writings on various media. Natural Language Processing (NLP) allows researchers to gather such data and analyze it to glean the underlying meaning of such writings. The field of sentiment analysis (applied to many other domains) depend heavily on techniques utilized by NLP. This work will look into various prevalent theories underlying the NLP field and how they can be leveraged to gather users sentiments on social media. Such sentiments can be culled over a period of time thus minimizing the errors introduced by data input and other stressors. Furthermore, we look at some applications of sentiment analysis and application of NLP to mental health. The reader will also learn about the NLTK toolkit that implements various NLP theories and how they can make the data scavenging process a lot easier.
Tasks	Sentiment Analysis
Published	2019-02-02
URL	http://arxiv.org/abs/1902.00679v1
PDF	http://arxiv.org/pdf/1902.00679v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-processing-sentiment
Repo
Framework

Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise


Title	Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
Authors	Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh
Abstract	Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous neural network framework called Neural Stochastic Differential Equation (Neural SDE) network, which naturally incorporates various commonly used regularization mechanisms based on random noise injection. Our framework can model various types of noise injection frequently used in discrete networks for regularization purpose, such as dropout and additive/multiplicative noise in each block. We provide theoretical analysis explaining the improved robustness of Neural SDE models against input perturbations/adversarial attacks. Furthermore, we demonstrate that the Neural SDE network can achieve better generalization than the Neural ODE and is more resistant to adversarial and non-adversarial input perturbations.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02355v1
PDF	https://arxiv.org/pdf/1906.02355v1.pdf
PWC	https://paperswithcode.com/paper/neural-sde-stabilizing-neural-ode-networks
Repo
Framework

Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction


Title	Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction
Authors	Joseph A. Morrone, Jeffrey K. Weber, Tien Huynh, Heng Luo, Wendy D. Cornell
Abstract	We present a simple, modular graph-based convolutional neural network that takes structural information from protein-ligand complexes as input to generate models for activity and binding mode prediction. Complex structures are generated by a standard docking procedure and fed into a dual-graph architecture that includes separate sub-networks for the ligand bonded topology and the ligand-protein contact map. This network division allows contributions from ligand identity to be distinguished from effects of protein-ligand interactions on classification. We show, in agreement with recent literature, that dataset bias drives many of the promising results on virtual screening that have previously been reported. However, we also show that our neural network is capable of learning from protein structural information when, as in the case of binding mode prediction, an unbiased dataset is constructed. We develop a deep learning model for binding mode prediction that uses docking ranking as input in combination with docking structures. This strategy mirrors past consensus models and outperforms the baseline docking program in a variety of tests, including on cross-docking datasets that mimic real-world docking use cases. Furthermore, the magnitudes of network predictions serve as reliable measures of model confidence
Tasks
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02845v1
PDF	https://arxiv.org/pdf/1910.02845v1.pdf
PWC	https://paperswithcode.com/paper/combining-docking-pose-rank-and-structure
Repo
Framework

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion


Title	Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
Authors	Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang Song, Tao Zhang
Abstract	Incompleteness is a common problem for existing knowledge graphs (KGs), and the completion of KG which aims to predict links between entities is challenging. Most existing KG completion methods only consider the direct relation between nodes and ignore the relation paths which contain useful information for link prediction. Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning. In addition, these path-based models always ignore nonlinear contributions of path features for link prediction. To solve these problems, we propose a novel KG completion method named OPTransE. Instead of embedding both entities of a relation into the same latent space as in previous methods, we project the head entity and the tail entity of each relation into different spaces to guarantee the order of relations in the path. Meanwhile, we adopt a pooling strategy to extract nonlinear and complex features of different paths to further improve the performance of link prediction. Experimental results on two benchmark datasets show that the proposed model OPTransE performs better than state-of-the-art methods.
Tasks	Knowledge Graph Completion, Knowledge Graphs, Link Prediction, Representation Learning
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11864v1
PDF	https://arxiv.org/pdf/1909.11864v1.pdf
PWC	https://paperswithcode.com/paper/representation-learning-with-ordered-relation
Repo
Framework

Semi-bandit Optimization in the Dispersed Setting


Title	Semi-bandit Optimization in the Dispersed Setting
Authors	Maria-Florina Balcan, Travis Dick, Wesley Pegden
Abstract	In this work, we study the problem of online optimization of piecewise Lipschitz functions with semi-bandit feedback. This challenging class of non-convex optimization problems often arises in algorithm selection problems for combinatorial settings, where the goal is to find the best algorithm from a large algorithm family for a specific application domain. In these settings, each evaluation of the loss functions in the optimization problem can be computationally expensive, often requiring the learner to run a combinatorial algorithm to measure its performance. Combined with the fact that small differences between similar algorithms in the family can lead to cascading changes in algorithm behavior, efficient online optimization in these settings is a challenging problem. However, we show that in many applications, evaluating the loss function for one algorithm choice can sometimes reveal the loss for a range of similar algorithms, essentially for free. We develop online optimization algorithms capable of using this kind of extra information by working in the semi-bandit feedback setting. Our algorithms achieve regret bounds that are essentially as good as algorithms under full-information feedback and are significantly more computationally efficient. We apply our semi-bandit optimization results to obtain online algorithm selection procedures for two rich families of combinatorial algorithms. We provide the first provable guarantees for online algorithm selection for clustering problems using a family of clustering algorithms containing classic linkage procedures. We also show how to select algorithms from a family of greedy knapsack algorithms with simultaneously lower computational complexity and stronger regret bounds than the best algorithm selection procedures from prior work.
Tasks
Published	2019-04-18
URL	https://arxiv.org/abs/1904.09014v2
PDF	https://arxiv.org/pdf/1904.09014v2.pdf
PWC	https://paperswithcode.com/paper/semi-bandit-optimization-in-the-dispersed
Repo
Framework

Let Me Know What to Ask: Interrogative-Word-Aware Question Generation


Title	Let Me Know What to Ask: Interrogative-Word-Aware Question Generation
Authors	Junmo Kang, Haritz Puerto San Roman, Sung-Hyon Myaeng
Abstract	Question Generation (QG) is a Natural Language Processing (NLP) task that aids advances in Question Answering (QA) and conversational assistants. Existing models focus on generating a question based on a text and possibly the answer to the generated question. They need to determine the type of interrogative word to be generated while having to pay attention to the grammar and vocabulary of the question. In this work, we propose Interrogative-Word-Aware Question Generation (IWAQG), a pipelined system composed of two modules: an interrogative word classifier and a QG model. The first module predicts the interrogative word that is provided to the second module to create the question. Owing to an increased recall of deciding the interrogative words to be used for the generated questions, the proposed model achieves new state-of-the-art results on the task of QG in SQuAD, improving from 46.58 to 47.69 in BLEU-1, 17.55 to 18.53 in BLEU-4, 21.24 to 22.33 in METEOR, and from 44.53 to 46.94 in ROUGE-L.
Tasks	Question Answering, Question Generation
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13794v1
PDF	https://arxiv.org/pdf/1910.13794v1.pdf
PWC	https://paperswithcode.com/paper/let-me-know-what-to-ask-interrogative-word
Repo
Framework

Bayesian Pitch Tracking Based on the Harmonic Model


Title	Bayesian Pitch Tracking Based on the Harmonic Model
Authors	Liming Shi, Jesper Kjaer Nielsen, Jesper Rindom Jensen, Max A. Little, Mads Graesboll Christensen
Abstract	Fundamental frequency is one of the most important characteristics of speech and audio signals. Harmonic model-based fundamental frequency estimators offer a higher estimation accuracy and robustness against noise than the widely used autocorrelation-based methods. However, the traditional harmonic model-based estimators do not take the temporal smoothness of the fundamental frequency, the model order, and the voicing into account as they process each data segment independently. In this paper, a fully Bayesian fundamental frequency tracking algorithm based on the harmonic model and a first-order Markov process model is proposed. Smoothness priors are imposed on the fundamental frequencies, model orders, and voicing using first-order Markov process models. Using these Markov models, fundamental frequency estimation and voicing detection errors can be reduced. Using the harmonic model, the proposed fundamental frequency tracker has an improved robustness to noise. An analytical form of the likelihood function, which can be computed efficiently, is derived. Compared to the state-of-the-art neural network and non-parametric approaches, the proposed fundamental frequency tracking algorithm reduces the mean absolute errors and gross errors by 15% and 20% on the Keele pitch database and 36% and 26% on sustained /a/ sounds from a database of Parkinson’s disease voices under 0 dB white Gaussian noise. A MATLAB version of the proposed algorithm is made freely available for reproduction of the results\footnote{An implementation of the proposed algorithm using MATLAB may be found in \url{https://tinyurl.com/yxn4a543}
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08557v1
PDF	https://arxiv.org/pdf/1905.08557v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-pitch-tracking-based-on-the-harmonic
Repo
Framework

LIBRE: Learning Interpretable Boolean Rule Ensembles


Title	LIBRE: Learning Interpretable Boolean Rule Ensembles
Authors	Graziano Mita, Paolo Papotti, Maurizio Filippone, Pietro Michiardi
Abstract	We present a novel method - LIBRE - to learn an interpretable classifier, which materializes as a set of Boolean rules. LIBRE uses an ensemble of bottom-up weak learners operating on a random subset of features, which allows for the learning of rules that generalize well on unseen data even in imbalanced settings. Weak learners are combined with a simple union so that the final ensemble is also interpretable. Experimental results indicate that LIBRE efficiently strikes the right balance between prediction accuracy, which is competitive with black box methods, and interpretability, which is often superior to alternative methods from the literature.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06537v1
PDF	https://arxiv.org/pdf/1911.06537v1.pdf
PWC	https://paperswithcode.com/paper/libre-learning-interpretable-boolean-rule
Repo
Framework

Training GANs with Centripetal Acceleration


Title	Training GANs with Centripetal Acceleration
Authors	Wei Peng, Yuhong Dai, Hui Zhang, Lizhi Cheng
Abstract	Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.
Tasks
Published	2019-02-24
URL	http://arxiv.org/abs/1902.08949v1
PDF	http://arxiv.org/pdf/1902.08949v1.pdf
PWC	https://paperswithcode.com/paper/training-gans-with-centripetal-acceleration
Repo
Framework

Towards Best Experiment Design for Evaluating Dialogue System Output


Title	Towards Best Experiment Design for Evaluating Dialogue System Output
Authors	Sashank Santhanam, Samira Shaikh
Abstract	To overcome the limitations of automated metrics (e.g. BLEU, METEOR) for evaluating dialogue systems, researchers typically use human judgments to provide convergent evidence. While it has been demonstrated that human judgments can suffer from the inconsistency of ratings, extant research has also found that the design of the evaluation task affects the consistency and quality of human judgments. We conduct a between-subjects study to understand the impact of four experiment conditions on human ratings of dialogue system output. In addition to discrete and continuous scale ratings, we also experiment with a novel application of Best-Worst scaling to dialogue evaluation. Through our systematic study with 40 crowdsourced workers in each task, we find that using continuous scales achieves more consistent ratings than Likert scale or ranking-based experiment design. Additionally, we find that factors such as time taken to complete the task and no prior experience of participating in similar studies of rating dialogue system output positively impact consistency and agreement amongst raters
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10122v1
PDF	https://arxiv.org/pdf/1909.10122v1.pdf
PWC	https://paperswithcode.com/paper/190910122
Repo
Framework