May 6, 2019

3021 words 15 mins read

Paper Group ANR 261

Towards Empathetic Human-Robot Interactions. Modeling and Estimation of Discrete-Time Reciprocal Processes via Probabilistic Graphical Models. Adaptive Regularization in Convex Composite Optimization for Variational Imaging Problems. Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection. Meta-Path Guided Embedding for Similar …

Towards Empathetic Human-Robot Interactions


Title	Towards Empathetic Human-Robot Interactions
Authors	Pascale Fung, Dario Bertero, Yan Wan, Anik Dey, Ricky Ho Yin Chan, Farhad Bin Siddique, Yang Yang, Chien-Sheng Wu, Ruixi Lin
Abstract	Since the late 1990s when speech companies began providing their customer-service software in the market, people have gotten used to speaking to machines. As people interact more often with voice and gesture controlled machines, they expect the machines to recognize different emotions, and understand other high level communication features such as humor, sarcasm and intention. In order to make such communication possible, the machines need an empathy module in them which can extract emotions from human speech and behavior and can decide the correct response of the robot. Although research on empathetic robots is still in the early stage, we described our approach using signal processing techniques, sentiment analysis and machine learning algorithms to make robots that can “understand” human emotion. We propose Zara the Supergirl as a prototype system of empathetic robots. It is a software based virtual android, with an animated cartoon character to present itself on the screen. She will get “smarter” and more empathetic through its deep learning algorithms, and by gathering more data and learning from it. In this paper, we present our work so far in the areas of deep learning of emotion and sentiment recognition, as well as humor recognition. We hope to explore the future direction of android development and how it can help improve people’s lives.
Tasks	Sentiment Analysis
Published	2016-05-13
URL	http://arxiv.org/abs/1605.04072v1
PDF	http://arxiv.org/pdf/1605.04072v1.pdf
PWC	https://paperswithcode.com/paper/towards-empathetic-human-robot-interactions
Repo
Framework

Modeling and Estimation of Discrete-Time Reciprocal Processes via Probabilistic Graphical Models


Title	Modeling and Estimation of Discrete-Time Reciprocal Processes via Probabilistic Graphical Models
Authors	Francesca Paola Carli
Abstract	Reciprocal processes are acausal generalizations of Markov processes introduced by Bernstein in 1932. In the literature, a significant amount of attention has been focused on developing dynamical models for reciprocal processes. In this paper, we provide a probabilistic graphical model for reciprocal processes. This leads to a principled solution of the smoothing problem via message passing algorithms. For the finite state space case, convergence analysis is revisited via the Hilbert metric.
Tasks
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04419v3
PDF	http://arxiv.org/pdf/1603.04419v3.pdf
PWC	https://paperswithcode.com/paper/modeling-and-estimation-of-discrete-time
Repo
Framework

Adaptive Regularization in Convex Composite Optimization for Variational Imaging Problems


Title	Adaptive Regularization in Convex Composite Optimization for Variational Imaging Problems
Authors	Byung-Woo Hong, Ja-Keoung Koo, Hendrik Dirks, Martin Burger
Abstract	We propose an adaptive regularization scheme in a variational framework where a convex composite energy functional is optimized. We consider a number of imaging problems including denoising, segmentation and motion estimation, which are considered as optimal solutions of the energy functionals that mainly consist of data fidelity, regularization and a control parameter for their trade-off. We presents an algorithm to determine the relative weight between data fidelity and regularization based on the residual that measures how well the observation fits the model. Our adaptive regularization scheme is designed to locally control the regularization at each pixel based on the assumption that the diversity of the residual of a given imaging model spatially varies. The energy optimization is presented in the alternating direction method of multipliers (ADMM) framework where the adaptive regularization is iteratively applied along with mathematical analysis of the proposed algorithm. We demonstrate the robustness and effectiveness of our adaptive regularization through experimental results presenting that the qualitative and quantitative evaluation results of each imaging task are superior to the results with a constant regularization scheme. The desired properties, robustness and effectiveness, of the regularization parameter selection in a variational framework for imaging problems are achieved by merely replacing the static regularization parameter with our adaptive one.
Tasks	Denoising, Motion Estimation
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02356v2
PDF	http://arxiv.org/pdf/1609.02356v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-regularization-in-convex-composite
Repo
Framework

Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection


Title	Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection
Authors	Zhenhao Ge, Sudhendu R. Sharma, Mark J. T. Smith
Abstract	Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students studying foreign languages. Here we propose a Hidden Markov Model (HMM)-based method to detect mispronunciations. Exploiting the specific dialog scripting employed in language learning software, HMMs are trained for different pronunciations. New adaptive features have been developed and obtained through an adaptive warping of the frequency scale prior to computing the cepstral coefficients. The optimization criterion used for the warping function is to maximize separation of two major groups of pronunciations (native and non-native) in terms of classification rate. Experimental results show that the adaptive frequency scale yields a better coefficient representation leading to higher classification rates in comparison with conventional HMMs using Mel-frequency cepstral coefficients.
Tasks	Speech Recognition
Published	2016-02-25
URL	http://arxiv.org/abs/1602.08132v1
PDF	http://arxiv.org/pdf/1602.08132v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-frequency-cepstral-coefficients-for
Repo
Framework

Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks


Title	Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
Authors	Jingbo Shang, Meng Qu, Jialu Liu, Lance M. Kaplan, Jiawei Han, Jian Peng
Abstract	Most real-world data can be modeled as heterogeneous information networks (HINs) consisting of vertices of multiple types and their relationships. Search for similar vertices of the same type in large HINs, such as bibliographic networks and business-review networks, is a fundamental problem with broad applications. Although similarity search in HINs has been studied previously, most existing approaches neither explore rich semantic information embedded in the network structures nor take user’s preference as a guidance. In this paper, we re-examine similarity search in HINs and propose a novel embedding-based framework. It models vertices as low-dimensional vectors to explore network structure-embedded similarity. To accommodate user preferences at defining similarity semantics, our proposed framework, ESim, accepts user-defined meta-paths as guidance to learn vertex vectors in a user-preferred embedding space. Moreover, an efficient and parallel sampling-based optimization algorithm has been developed to learn embeddings in large-scale HINs. Extensive experiments on real-world large-scale HINs demonstrate a significant improvement on the effectiveness of ESim over several state-of-the-art algorithms as well as its scalability.
Tasks
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09769v1
PDF	http://arxiv.org/pdf/1610.09769v1.pdf
PWC	https://paperswithcode.com/paper/meta-path-guided-embedding-for-similarity
Repo
Framework

Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits


Title	Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Authors	Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Abstract	We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i.i.d. or the sequence of contexts is known a priori, but where the losses are picked adversarially. Our algorithm is computationally efficient, assuming access to an offline optimization oracle, and enjoys a regret of order $O((KT)^{\frac{2}{3}}(\log N)^{\frac{1}{3}})$, where $K$ is the number of actions, $T$ is the number of iterations and $N$ is the number of baseline policies. Our result is the first to break the $O(T^{\frac{3}{4}})$ barrier that is achieved by recently introduced algorithms. Breaking this barrier was left as a major open problem. Our analysis is based on the recent relaxation based approach of (Rakhlin and Sridharan, 2016).
Tasks	Multi-Armed Bandits
Published	2016-06-01
URL	http://arxiv.org/abs/1606.00313v1
PDF	http://arxiv.org/pdf/1606.00313v1.pdf
PWC	https://paperswithcode.com/paper/improved-regret-bounds-for-oracle-based
Repo
Framework

Understanding Symmetric Smoothing Filters: A Gaussian Mixture Model Perspective


Title	Understanding Symmetric Smoothing Filters: A Gaussian Mixture Model Perspective
Authors	Stanley H. Chan, Todd Zickler, Yue M. Lu
Abstract	Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn-Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly-stochastic matrix. However, a complete understanding of the performance gain phenomenon is still lacking. In this paper, we study the performance gain phenomenon from a statistical learning perspective. We show that Sinkhorn-Knopp is equivalent to an Expectation-Maximization (EM) algorithm of learning a Gaussian mixture model of the image patches. By establishing the correspondence between the steps of Sinkhorn-Knopp and the EM algorithm, we provide a geometrical interpretation of the symmetrization process. This observation allows us to develop a new denoising algorithm called Gaussian mixture model symmetric smoothing filter (GSF). GSF is an extension of the Sinkhorn-Knopp and is a generalization of the original smoothing filters. Despite its simple formulation, GSF outperforms many existing smoothing filters and has a similar performance compared to several state-of-the-art denoising algorithms.
Tasks	Denoising, Image Denoising
Published	2016-01-01
URL	http://arxiv.org/abs/1601.00088v2
PDF	http://arxiv.org/pdf/1601.00088v2.pdf
PWC	https://paperswithcode.com/paper/understanding-symmetric-smoothing-filters-a
Repo
Framework

Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environments


Title	Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environments
Authors	Liu Liu, Hongdong Li, Yuchao Dai
Abstract	This paper studies the relative pose problem for autonomous vehicle driving in highly dynamic and possibly cluttered environments. This is a challenging scenario due to the existence of multiple, large, and independently moving objects in the environment, which often leads to excessive portion of outliers and results in erroneous motion estimation. Existing algorithms cannot cope with such situations well. This paper proposes a new algorithm for relative pose using a multi-camera system with multiple non-overlapping individual cameras. The method works robustly even when the numbers of outliers are overwhelming. By exploiting specific prior knowledge of driving scene we have developed an efficient 4-point algorithm for multi-camera relative pose, which admits analytic solutions by solving a polynomial root-finding equation, and runs extremely fast (at about 0.5$u$s per root). When the solver is used in combination with RANSAC, we are able to quickly prune unpromising hypotheses, significantly improve the chance of finding inliers. Experiments on synthetic data have validated the performance of the proposed algorithm. Tests on real data further confirm the method’s practical relevance.
Tasks	Motion Estimation
Published	2016-05-12
URL	http://arxiv.org/abs/1605.03689v1
PDF	http://arxiv.org/pdf/1605.03689v1.pdf
PWC	https://paperswithcode.com/paper/robust-and-efficient-relative-pose-with-a
Repo
Framework

Learning Weighted Association Rules in Human Phenotype Ontology


Title	Learning Weighted Association Rules in Human Phenotype Ontology
Authors	Pietro Hiram Guzzi, Giuseppe Agapito, Marianna Milano, Mario Cannataro
Abstract	The Human Phenotype Ontology (HPO) is a structured repository of concepts (HPO Terms) that are associated to one or more diseases. The process of association is referred to as annotation. The relevance and the specificity of both HPO terms and annotations are evaluated by a measure defined as Information Content (IC). The analysis of annotated data is thus an important challenge for bioinformatics. There exist different approaches of analysis. From those, the use of Association Rules (AR) may provide useful knowledge, and it has been used in some applications, e.g. improving the quality of annotations. Nevertheless classical association rules algorithms do not take into account the source of annotation nor the importance yielding to the generation of candidate rules with low IC. This paper presents HPO-Miner (Human Phenotype Ontology-based Weighted Association Rules) a methodology for extracting Weighted Association Rules. HPO-Miner can extract relevant rules from a biological point of view. A case study on using of HPO-Miner on publicly available HPO annotation datasets is used to demonstrate the effectiveness of our methodology.
Tasks
Published	2016-12-31
URL	http://arxiv.org/abs/1701.00077v1
PDF	http://arxiv.org/pdf/1701.00077v1.pdf
PWC	https://paperswithcode.com/paper/learning-weighted-association-rules-in-human
Repo
Framework

Mixture of Bilateral-Projection Two-dimensional Probabilistic Principal Component Analysis


Title	Mixture of Bilateral-Projection Two-dimensional Probabilistic Principal Component Analysis
Authors	Fujiao Ju, Yanfeng Sun, Junbin Gao, Simeng Liu, Yongli Hu
Abstract	The probabilistic principal component analysis (PPCA) is built upon a global linear mapping, with which it is insufficient to model complex data variation. This paper proposes a mixture of bilateral-projection probabilistic principal component analysis model (mixB2DPPCA) on 2D data. With multi-components in the mixture, this model can be seen as a soft cluster algorithm and has capability of modeling data with complex structures. A Bayesian inference scheme has been proposed based on the variational EM (Expectation-Maximization) approach for learning model parameters. Experiments on some publicly available databases show that the performance of mixB2DPPCA has been largely improved, resulting in more accurate reconstruction errors and recognition rates than the existing PCA-based algorithms.
Tasks	Bayesian Inference
Published	2016-01-07
URL	http://arxiv.org/abs/1601.01431v1
PDF	http://arxiv.org/pdf/1601.01431v1.pdf
PWC	https://paperswithcode.com/paper/mixture-of-bilateral-projection-two
Repo
Framework

On the inconsistency of $\ell_1$-penalised sparse precision matrix estimation


Title	On the inconsistency of $\ell_1$-penalised sparse precision matrix estimation
Authors	Otte Heinävaara, Janne Leppä-aho, Jukka Corander, Antti Honkela
Abstract	Various $\ell_1$-penalised estimation methods such as graphical lasso and CLIME are widely used for sparse precision matrix estimation. Many of these methods have been shown to be consistent under various quantitative assumptions about the underlying true covariance matrix. Intuitively, these conditions are related to situations where the penalty term will dominate the optimisation. In this paper, we explore the consistency of $\ell_1$-based methods for a class of sparse latent variable -like models, which are strongly motivated by several types of applications. We show that all $\ell_1$-based methods fail dramatically for models with nearly linear dependencies between the variables. We also study the consistency on models derived from real gene expression data and note that the assumptions needed for consistency never hold even for modest sized gene networks and $\ell_1$-based methods also become unreliable in practice for larger networks.
Tasks
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02532v1
PDF	http://arxiv.org/pdf/1603.02532v1.pdf
PWC	https://paperswithcode.com/paper/on-the-inconsistency-of-ell_1-penalised
Repo
Framework

Transport-based analysis, modeling, and learning from signal and data distributions


Title	Transport-based analysis, modeling, and learning from signal and data distributions
Authors	Soheil Kolouri, Serim Park, Matthew Thorpe, Dejan Slepčev, Gustavo K. Rohde
Abstract	Transport-based techniques for signal and data analysis have received increased attention recently. Given their abilities to provide accurate generative models for signal intensities and other data distributions, they have been used in a variety of applications including content-based retrieval, cancer detection, image super-resolution, and statistical machine learning, to name a few, and shown to produce state of the art in several applications. Moreover, the geometric characteristics of transport-related metrics have inspired new kinds of algorithms for interpreting the meaning of data distributions. Here we provide an overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, as well as a review, with demonstrations, of several applications.
Tasks	Image Super-Resolution, Super-Resolution
Published	2016-09-15
URL	http://arxiv.org/abs/1609.04767v1
PDF	http://arxiv.org/pdf/1609.04767v1.pdf
PWC	https://paperswithcode.com/paper/transport-based-analysis-modeling-and
Repo
Framework

Scalable Machine Translation in Memory Constrained Environments


Title	Scalable Machine Translation in Memory Constrained Environments
Authors	Paul Baltescu
Abstract	Machine translation is the discipline concerned with developing automated tools for translating from one human language to another. Statistical machine translation (SMT) is the dominant paradigm in this field. In SMT, translations are generated by means of statistical models whose parameters are learned from bilingual data. Scalability is a key concern in SMT, as one would like to make use of as much data as possible to train better translation systems. In recent years, mobile devices with adequate computing power have become widely available. Despite being very successful, mobile applications relying on NLP systems continue to follow a client-server architecture, which is of limited use because access to internet is often limited and expensive. The goal of this dissertation is to show how to construct a scalable machine translation system that can operate with the limited resources available on a mobile device. The main challenge for porting translation systems on mobile devices is memory usage. The amount of memory available on a mobile device is far less than what is typically available on the server side of a client-server application. In this thesis, we investigate alternatives for the two components which prevent standard translation systems from working on mobile devices due to high memory usage. We show that once these standard components are replaced with our proposed alternatives, we obtain a scalable translation system that can work on a device with limited memory.
Tasks	Machine Translation
Published	2016-10-06
URL	http://arxiv.org/abs/1610.02003v1
PDF	http://arxiv.org/pdf/1610.02003v1.pdf
PWC	https://paperswithcode.com/paper/scalable-machine-translation-in-memory
Repo
Framework

Better safe than sorry: Risky function exploitation through safe optimization


Title	Better safe than sorry: Risky function exploitation through safe optimization
Authors	Eric Schulz, Quentin J. M. Huys, Dominik R. Bach, Maarten Speekenbrink, Andreas Krause
Abstract	Exploration-exploitation of functions, that is learning and optimizing a mapping between inputs and expected outputs, is ubiquitous to many real world situations. These situations sometimes require us to avoid certain outcomes at all cost, for example because they are poisonous, harmful, or otherwise dangerous. We test participants’ behavior in scenarios in which they have to find the optimum of a function while at the same time avoid outputs below a certain threshold. In two experiments, we find that Safe-Optimization, a Gaussian Process-based exploration-exploitation algorithm, describes participants’ behavior well and that participants seem to care firstly whether a point is safe and then try to pick the optimal point from all such safe points. This means that their trade-off between exploration and exploitation can be seen as an intelligent, approximate, and homeostasis-driven strategy.
Tasks
Published	2016-02-02
URL	http://arxiv.org/abs/1602.01052v2
PDF	http://arxiv.org/pdf/1602.01052v2.pdf
PWC	https://paperswithcode.com/paper/better-safe-than-sorry-risky-function
Repo
Framework

Truth Discovery with Memory Network


Title	Truth Discovery with Memory Network
Authors	Luyang Li, Bing Qin, Wenjing Ren, Ting Liu
Abstract	Truth discovery is to resolve conflicts and find the truth from multiple-source statements. Conventional methods mostly research based on the mutual effect between the reliability of sources and the credibility of statements, however, pay no attention to the mutual effect among the credibility of statements about the same object. We propose memory network based models to incorporate these two ideas to do the truth discovery. We use feedforward memory network and feedback memory network to learn the representation of the credibility of statements which are about the same object. Specially, we adopt memory mechanism to learn source reliability and use it through truth prediction. During learning models, we use multiple types of data (categorical data and continuous data) by assigning different weights automatically in the loss function based on their own effect on truth discovery prediction. The experiment results show that the memory network based models much outperform the state-of-the-art method and other baseline methods.
Tasks
Published	2016-11-07
URL	http://arxiv.org/abs/1611.01868v1
PDF	http://arxiv.org/pdf/1611.01868v1.pdf
PWC	https://paperswithcode.com/paper/truth-discovery-with-memory-network
Repo
Framework