July 27, 2019

2976 words 14 mins read

Paper Group ANR 619

Information Density as a Factor for Variation in the Embedding of Relative Clauses. Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection. Characterizing optimal hierarchical policy inference on graphs via non-equilibrium thermodynamics. Diversity-aware Multi-Video Summarization. Parameter Estimation in Computational Biology by …

Information Density as a Factor for Variation in the Embedding of Relative Clauses


Title	Information Density as a Factor for Variation in the Embedding of Relative Clauses
Authors	Augustin Speyer, Robin Lemke
Abstract	In German, relative clauses can be positioned in-situ or extraposed. A potential factor for the variation might be information density. In this study, this hypothesis is tested with a corpus of 17th century German funeral sermons. For each referent in the relative clauses and their matrix clauses, the attention state was determined (first calculation). In a second calculation, for each word the surprisal values were determined, using a bi-gram language model. In a third calculation, the surprisal values were accommodated as to whether it is the first occurrence of the word in question or not. All three calculations pointed in the same direction: With in-situ relative clauses, the rate of new referents was lower and the average surprisal values were lower, especially the accommodated surprisal values, than with extraposed relative clauses. This indicated that in-formation density is a factor governing the choice between in-situ and extraposed relative clauses. The study also sheds light on the intrinsic relation-ship between the information theoretic concept of information density and in-formation structural concepts such as givenness which are used under a more linguistic perspective.
Tasks	Language Modelling
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06457v1
PDF	http://arxiv.org/pdf/1705.06457v1.pdf
PWC	https://paperswithcode.com/paper/information-density-as-a-factor-for-variation
Repo
Framework

Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection


Title	Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
Authors	Yuliang Liu, Lianwen Jin
Abstract	Detecting incidental scene text is a challenging task because of multi-orientation, perspective distortion, and variation of text size, color and scale. Retrospective research has only focused on using rectangular bounding box or horizontal sliding window to localize text, which may result in redundant background noise, unnecessary overlap or even information loss. To address these issues, we propose a new Convolutional Neural Networks (CNNs) based method, named Deep Matching Prior Network (DMPNet), to detect text with tighter quadrangle. First, we use quadrilateral sliding windows in several specific intermediate convolutional layers to roughly recall the text with higher overlapping area and then a shared Monte-Carlo method is proposed for fast and accurate computing of the polygonal areas. After that, we designed a sequential protocol for relative regression which can exactly predict text with compact quadrangle. Moreover, a auxiliary smooth Ln loss is also proposed for further regressing the position of text, which has better overall performance than L2 loss and smooth L1 loss in terms of robustness and stability. The effectiveness of our approach is evaluated on a public word-level, multi-oriented scene text database, ICDAR 2015 Robust Reading Competition Challenge 4 “Incidental scene text localization”. The performance of our method is evaluated by using F-measure and found to be 70.64%, outperforming the existing state-of-the-art method with F-measure 63.76%.
Tasks
Published	2017-03-04
URL	http://arxiv.org/abs/1703.01425v1
PDF	http://arxiv.org/pdf/1703.01425v1.pdf
PWC	https://paperswithcode.com/paper/deep-matching-prior-network-toward-tighter
Repo
Framework

Characterizing optimal hierarchical policy inference on graphs via non-equilibrium thermodynamics


Title	Characterizing optimal hierarchical policy inference on graphs via non-equilibrium thermodynamics
Authors	Daniel McNamee
Abstract	Hierarchies are of fundamental interest in both stochastic optimal control and biological control due to their facilitation of a range of desirable computational traits in a control algorithm and the possibility that they may form a core principle of sensorimotor and cognitive control systems. However, a theoretically justified construction of state-space hierarchies over all spatial resolutions and their evolution through a policy inference process remains elusive. Here, a formalism for deriving such normative representations of discrete Markov decision processes is introduced in the context of graphs. The resulting hierarchies correspond to a hierarchical policy inference algorithm approximating a discrete gradient flow between state-space trajectory densities generated by the prior and optimal policies.
Tasks
Published	2017-12-29
URL	http://arxiv.org/abs/1801.00048v1
PDF	http://arxiv.org/pdf/1801.00048v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-optimal-hierarchical-policy
Repo
Framework

Diversity-aware Multi-Video Summarization


Title	Diversity-aware Multi-Video Summarization
Authors	Rameswar Panda, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury
Abstract	Most video summarization approaches have focused on extracting a summary from a single video; we propose an unsupervised framework for summarizing a collection of videos. We observe that each video in the collection may contain some information that other videos do not have, and thus exploring the underlying complementarity could be beneficial in creating a diverse informative summary. We develop a novel diversity-aware sparse optimization method for multi-video summarization by exploring the complementarity within the videos. Our approach extracts a multi-video summary which is both interesting and representative in describing the whole video collection. To efficiently solve our optimization problem, we develop an alternating minimization algorithm that minimizes the overall objective function with respect to one video at a time while fixing the other videos. Moreover, we introduce a new benchmark dataset, Tour20, that contains 140 videos with multiple human created summaries, which were acquired in a controlled experiment. Finally, by extensive experiments on the new Tour20 dataset and several other multi-view datasets, we show that the proposed approach clearly outperforms the state-of-the-art methods on the two problems-topic-oriented video summarization and multi-view video summarization in a camera network.
Tasks	Video Summarization
Published	2017-06-09
URL	http://arxiv.org/abs/1706.03123v1
PDF	http://arxiv.org/pdf/1706.03123v1.pdf
PWC	https://paperswithcode.com/paper/diversity-aware-multi-video-summarization
Repo
Framework

Parameter Estimation in Computational Biology by Approximate Bayesian Computation coupled with Sensitivity Analysis


Title	Parameter Estimation in Computational Biology by Approximate Bayesian Computation coupled with Sensitivity Analysis
Authors	Xin Liu, Mahesan Niranjan
Abstract	We address the problem of parameter estimation in models of systems biology from noisy observations. The models we consider are characterized by simultaneous deterministic nonlinear differential equations whose parameters are either taken from in vitro experiments, or are hand-tuned during the model development process to reproduces observations from the system. We consider the family of algorithms coming under the Bayesian formulation of Approximate Bayesian Computation (ABC), and show that sensitivity analysis could be deployed to quantify the relative roles of different parameters in the system. Parameters to which a system is relatively less sensitive (known as sloppy parameters) need not be estimated to high precision, while the values of parameters that are more critical (stiff parameters) need to be determined with care. A tradeoff between computational complexity and the accuracy with which the posterior distribution may be probed is an important characteristic of this class of algorithms.
Tasks
Published	2017-04-28
URL	http://arxiv.org/abs/1704.09021v1
PDF	http://arxiv.org/pdf/1704.09021v1.pdf
PWC	https://paperswithcode.com/paper/parameter-estimation-in-computational-biology
Repo
Framework

A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval


Title	A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
Authors	Ruoyu Liu, Yao Zhao, Liang Zheng, Shikui Wei, Yi Yang
Abstract	This paper proposes a new evaluation protocol for cross-media retrieval which better fits the real-word applications. Both image-text and text-image retrieval modes are considered. Traditionally, class labels in the training and testing sets are identical. That is, it is usually assumed that the query falls into some pre-defined classes. However, in practice, the content of a query image/text may vary extensively, and the retrieval system does not necessarily know in advance the class label of a query. Considering the inconsistency between the real-world applications and laboratory assumptions, we think that the existing protocol that works under identical train/test classes can be modified and improved. This work is dedicated to addressing this problem by considering the protocol under an extendable scenario, \ie, the training and testing classes do not overlap. We provide extensive benchmarking results obtained by the existing protocol and the proposed new protocol on several commonly used datasets. We demonstrate a noticeable performance drop when the testing classes are unseen during training. Additionally, a trivial solution, \ie, directly using the predicted class label for cross-media retrieval, is tested. We show that the trivial solution is very competitive in traditional non-extendable retrieval, but becomes less so under the new settings. The train/test split, evaluation code, and benchmarking results are publicly available on our website.
Tasks	Image Retrieval
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03567v1
PDF	http://arxiv.org/pdf/1703.03567v1.pdf
PWC	https://paperswithcode.com/paper/a-new-evaluation-protocol-and-benchmarking
Repo
Framework

A comparative study of counterfactual estimators


Title	A comparative study of counterfactual estimators
Authors	Thomas Nedelec, Nicolas Le Roux, Vianney Perchet
Abstract	We provide a comparative study of several widely used off-policy estimators (Empirical Average, Basic Importance Sampling and Normalized Importance Sampling), detailing the different regimes where they are individually suboptimal. We then exhibit properties optimal estimators should possess. In the case where examples have been gathered using multiple policies, we show that fused estimators dominate basic ones but can still be improved.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00773v3
PDF	http://arxiv.org/pdf/1704.00773v3.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-of-counterfactual
Repo
Framework

Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks


Title	Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks
Authors	Akm Ashiquzzaman, Abdul Kawsar Tushar, Ashiqur Rahman
Abstract	Handwritten character recognition has been the center of research and a benchmark problem in the sector of pattern recognition and artificial intelligence, and it continues to be a challenging research topic. Due to its enormous application many works have been done in this field focusing on different languages. Arabic, being a diversified language has a huge scope of research with potential challenges. A convolutional neural network model for recognizing handwritten numerals in Arabic language is proposed in this paper, where the dataset is subject to various augmentation in order to add robustness needed for deep learning approach. The proposed method is empowered by the presence of dropout regularization to do away with the problem of data overfitting. Moreover, suitable change is introduced in activation function to overcome the problem of vanishing gradient. With these modifications, the proposed system achieves an accuracy of 99.4% which performs better than every previous work on the dataset.
Tasks	Data Augmentation
Published	2017-08-20
URL	http://arxiv.org/abs/1708.05969v4
PDF	http://arxiv.org/pdf/1708.05969v4.pdf
PWC	https://paperswithcode.com/paper/applying-data-augmentation-to-handwritten
Repo
Framework

Dictionary-Free MRI PERK: Parameter Estimation via Regression with Kernels


Title	Dictionary-Free MRI PERK: Parameter Estimation via Regression with Kernels
Authors	Gopal Nataraj, Jon-Fredrik Nielsen, Clayton Scott, Jeffrey A. Fessler
Abstract	This paper introduces a fast, general method for dictionary-free parameter estimation in quantitative magnetic resonance imaging (QMRI) via regression with kernels (PERK). PERK first uses prior distributions and the nonlinear MR signal model to simulate many parameter-measurement pairs. Inspired by machine learning, PERK then takes these parameter-measurement pairs as labeled training points and learns from them a nonlinear regression function using kernel functions and convex optimization. PERK admits a simple implementation as per-voxel nonlinear lifting of MRI measurements followed by linear minimum mean-squared error regression. We demonstrate PERK for $T_1,T_2$ estimation, a well-studied application where it is simple to compare PERK estimates against dictionary-based grid search estimates. Numerical simulations as well as single-slice phantom and in vivo experiments demonstrate that PERK and grid search produce comparable $T_1,T_2$ estimates in white and gray matter, but PERK is consistently at least $23\times$ faster. This acceleration factor will increase by several orders of magnitude for full-volume QMRI estimation problems involving more latent parameters per voxel.
Tasks
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02441v1
PDF	http://arxiv.org/pdf/1710.02441v1.pdf
PWC	https://paperswithcode.com/paper/dictionary-free-mri-perk-parameter-estimation
Repo
Framework

Speaker-independent machine lip-reading with speaker-dependent viseme classifiers


Title	Speaker-independent machine lip-reading with speaker-dependent viseme classifiers
Authors	Helen L. Bear, Stephen J. Cox, Richard W. Harvey
Abstract	In machine lip-reading, which is identification of speech from visual-only information, there is evidence to show that visual speech is highly dependent upon the speaker [1]. Here, we use a phoneme-clustering method to form new phoneme-to-viseme maps for both individual and multiple speakers. We use these maps to examine how similarly speakers talk visually. We conclude that broadly speaking, speakers have the same repertoire of mouth gestures, where they differ is in the use of the gestures.
Tasks
Published	2017-10-03
URL	http://arxiv.org/abs/1710.01122v1
PDF	http://arxiv.org/pdf/1710.01122v1.pdf
PWC	https://paperswithcode.com/paper/speaker-independent-machine-lip-reading-with
Repo
Framework

Texture Characterization by Using Shape Co-occurrence Patterns


Title	Texture Characterization by Using Shape Co-occurrence Patterns
Authors	Gui-Song Xia, Gang Liu, Xiang Bai, Liangpei Zhang
Abstract	Texture characterization is a key problem in image understanding and pattern recognition. In this paper, we present a flexible shape-based texture representation using shape co-occurrence patterns. More precisely, texture images are first represented by tree of shapes, each of which is associated with several geometrical and radiometric attributes. Then four typical kinds of shape co-occurrence patterns based on the hierarchical relationship of the shapes in the tree are learned as codewords. Three different coding methods are investigated to learn the codewords, with which, any given texture image can be encoded into a descriptive vector. In contrast with existing works, the proposed method not only inherits the strong ability to depict geometrical aspects of textures and the high robustness to variations of imaging conditions from the shape-based method, but also provides a flexible way to consider shape relationships and to compute high-order statistics on the tree. To our knowledge, this is the first time to use co-occurrence patterns of explicit shapes as a tool for texture analysis. Experiments on various texture datasets and scene datasets demonstrate the efficiency of the proposed method.
Tasks	Texture Classification
Published	2017-02-10
URL	http://arxiv.org/abs/1702.03115v1
PDF	http://arxiv.org/pdf/1702.03115v1.pdf
PWC	https://paperswithcode.com/paper/texture-characterization-by-using-shape-co
Repo
Framework

Addressing the Data Sparsity Issue in Neural AMR Parsing


Title	Addressing the Data Sparsity Issue in Neural AMR Parsing
Authors	Xiaochang Peng, Chuan Wang, Daniel Gildea, Nianwen Xue
Abstract	Neural attention models have achieved great success in different NLP tasks. How- ever, they have not fulfilled their promise on the AMR parsing task due to the data sparsity issue. In this paper, we de- scribe a sequence-to-sequence model for AMR parsing and present different ways to tackle the data sparsity problem. We show that our methods achieve significant improvement over a baseline neural atten- tion model and our results are also compet- itive against state-of-the-art systems that do not use extra linguistic resources.
Tasks	Amr Parsing
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05053v1
PDF	http://arxiv.org/pdf/1702.05053v1.pdf
PWC	https://paperswithcode.com/paper/addressing-the-data-sparsity-issue-in-neural
Repo
Framework


Title	Mixture modeling on related samples by $ψ$-stick breaking and kernel perturbation
Authors	Jacopo Soriano, Li Ma
Abstract	There has been great interest recently in applying nonparametric kernel mixtures in a hierarchical manner to model multiple related data samples jointly. In such settings several data features are commonly present: (i) the related samples often share some, if not all, of the mixture components but with differing weights, (ii) only some, not all, of the mixture components vary across the samples, and (iii) often the shared mixture components across samples are not aligned perfectly in terms of their location and spread, but rather display small misalignments either due to systematic cross-sample difference or more often due to uncontrolled, extraneous causes. Properly incorporating these features in mixture modeling will enhance the efficiency of inference, whereas ignoring them not only reduces efficiency but can jeopardize the validity of the inference due to issues such as confounding. We introduce two techniques for incorporating these features in modeling related data samples using kernel mixtures. The first technique, called $\psi$-stick breaking, is a joint generative process for the mixing weights through the breaking of both a stick shared by all the samples for the components that do not vary in size across samples and an idiosyncratic stick for each sample for those components that do vary in size. The second technique is to imbue random perturbation into the kernels, thereby accounting for cross-sample misalignment. These techniques can be used either separately or together in both parametric and nonparametric kernel mixtures. We derive efficient Bayesian inference recipes based on MCMC sampling for models featuring these techniques, and illustrate their work through both simulated data and a real flow cytometry data set in prediction/estimation, cross-sample calibration, and testing multi-sample differences.
Tasks	Bayesian Inference, Calibration
Published	2017-04-17
URL	http://arxiv.org/abs/1704.04839v1
PDF	http://arxiv.org/pdf/1704.04839v1.pdf
PWC	https://paperswithcode.com/paper/mixture-modeling-on-related-samples-by-stick
Repo
Framework

Random Forest Ensemble of Support Vector Regression Models for Solar Power Forecasting


Title	Random Forest Ensemble of Support Vector Regression Models for Solar Power Forecasting
Authors	Mohamed Abuella, Badrul Chowdhury
Abstract	To mitigate the uncertainty of variable renewable resources, two off-the-shelf machine learning tools are deployed to forecast the solar power output of a solar photovoltaic system. The support vector machines generate the forecasts and the random forest acts as an ensemble learning method to combine the forecasts. The common ensemble technique in wind and solar power forecasting is the blending of meteorological data from several sources. In this study though, the present and the past solar power forecasts from several models, as well as the associated meteorological data, are incorporated into the random forest to combine and improve the accuracy of the day-ahead solar power forecasts. The performance of the combined model is evaluated over the entire year and compared with other combining techniques.
Tasks
Published	2017-04-27
URL	http://arxiv.org/abs/1705.00033v1
PDF	http://arxiv.org/pdf/1705.00033v1.pdf
PWC	https://paperswithcode.com/paper/random-forest-ensemble-of-support-vector
Repo
Framework

Adversarial Attribute-Image Person Re-identification


Title	Adversarial Attribute-Image Person Re-identification
Authors	Zhou Yin, Wei-Shi Zheng, Ancong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jianhuang Lai
Abstract	While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task. However, how to find a set of person images according to a given attribute description, which is very practical in many surveillance applications, remains a rarely investigated cross-modality matching problem in person Re-ID. In this work, we present this challenge and formulate this task as a joint space learning problem. By imposing an attribute-guided attention mechanism for images and a semantic consistent adversary strategy for attributes, each modality, i.e., images and attributes, successfully learns semantically correlated concepts under the guidance of the other. We conducted extensive experiments on three attribute datasets and demonstrated that the proposed joint space learning method is so far the most effective method for the attribute-image cross-modality person Re-ID problem.
Tasks	Multi-Task Learning, Person Re-Identification
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01493v3
PDF	http://arxiv.org/pdf/1712.01493v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-attribute-image-person-re
Repo
Framework