May 6, 2019

2652 words 13 mins read

Paper Group ANR 255

The distribution of information content in English sentences. CogALex-V Shared Task: ROOT18. From Multiview Image Curves to 3D Drawings. Ordinal Conditional Functions for Nearly Counterfactual Revision. Combined Classifiers for Invariant Face Recognition. On the Existence of a Sample Mean in Dynamic Time Warping Spaces. Multimodal Latent Variable A …

The distribution of information content in English sentences


Title	The distribution of information content in English sentences
Authors	Shuiyuan Yu, Jin Cong, Junying Liang, Haitao Liu
Abstract	Sentence is a basic linguistic unit, however, little is known about how information content is distributed across different positions of a sentence. Based on authentic language data of English, the present study calculated the entropy and other entropy-related statistics for different sentence positions. The statistics indicate a three-step staircase-shaped distribution pattern, with entropy in the initial position lower than the medial positions (positions other than the initial and final), the medial positions lower than the final position and the medial positions showing no significant difference. The results suggest that: (1) the hypotheses of Constant Entropy Rate and Uniform Information Density do not hold for the sentence-medial positions; (2) the context of a word in a sentence should not be simply defined as all the words preceding it in the same sentence; and (3) the contextual information content in a sentence does not accumulate incrementally but follows a pattern of “the whole is greater than the sum of parts”.
Tasks
Published	2016-09-24
URL	http://arxiv.org/abs/1609.07681v1
PDF	http://arxiv.org/pdf/1609.07681v1.pdf
PWC	https://paperswithcode.com/paper/the-distribution-of-information-content-in
Repo
Framework

CogALex-V Shared Task: ROOT18


Title	CogALex-V Shared Task: ROOT18
Authors	Emmanuele Chersoni, Giulia Rambelli, Enrico Santus
Abstract	In this paper, we describe ROOT 18, a classifier using the scores of several unsupervised distributional measures as features to discriminate between semantically related and unrelated words, and then to classify the related pairs according to their semantic relation (i.e. synonymy, antonymy, hypernymy, part-whole meronymy). Our classifier participated in the CogALex-V Shared Task, showing a solid performance on the first subtask, but a poor performance on the second subtask. The low scores reported on the second subtask suggest that distributional measures are not sufficient to discriminate between multiple semantic relations at once.
Tasks
Published	2016-11-03
URL	http://arxiv.org/abs/1611.01101v1
PDF	http://arxiv.org/pdf/1611.01101v1.pdf
PWC	https://paperswithcode.com/paper/cogalex-v-shared-task-root18
Repo
Framework

From Multiview Image Curves to 3D Drawings


Title	From Multiview Image Curves to 3D Drawings
Authors	Anil Usumezbas, Ricardo Fabbri, Benjamin B. Kimia
Abstract	Reconstructing 3D scenes from multiple views has made impressive strides in recent years, chiefly by correlating isolated feature points, intensity patterns, or curvilinear structures. In the general setting - without controlled acquisition, abundant texture, curves and surfaces following specific models or limiting scene complexity - most methods produce unorganized point clouds, meshes, or voxel representations, with some exceptions producing unorganized clouds of 3D curve fragments. Ideally, many applications require structured representations of curves, surfaces and their spatial relationships. This paper presents a step in this direction by formulating an approach that combines 2D image curves into a collection of 3D curves, with topological connectivity between them represented as a 3D graph. This results in a 3D drawing, which is complementary to surface representations in the same sense as a 3D scaffold complements a tent taut over it. We evaluate our results against truth on synthetic and real datasets.
Tasks
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05561v1
PDF	http://arxiv.org/pdf/1609.05561v1.pdf
PWC	https://paperswithcode.com/paper/from-multiview-image-curves-to-3d-drawings
Repo
Framework

Ordinal Conditional Functions for Nearly Counterfactual Revision


Title	Ordinal Conditional Functions for Nearly Counterfactual Revision
Authors	Aaron Hunter
Abstract	We are interested in belief revision involving conditional statements where the antecedent is almost certainly false. To represent such problems, we use Ordinal Conditional Functions that may take infinite values. We model belief change in this context through simple arithmetical operations that allow us to capture the intuition that certain antecedents can not be validated by any number of observations. We frame our approach as a form of finite belief improvement, and we propose a model of conditional belief revision in which only the “right” hypothetical levels of implausibility are revised.
Tasks
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09429v1
PDF	http://arxiv.org/pdf/1603.09429v1.pdf
PWC	https://paperswithcode.com/paper/ordinal-conditional-functions-for-nearly
Repo
Framework

Combined Classifiers for Invariant Face Recognition


Title	Combined Classifiers for Invariant Face Recognition
Authors	Ahmad H. A. Eid
Abstract	No single classifier can alone solve the complex problem of face recognition. Researchers found that combining some base classifiers usually enhances their recognition rate. The weaknesses of the base classifiers are reflected on the resulting combined system. In this work, a system for combining unstable, low performance classifiers is proposed. The system is applied to face images of 392 persons. The system shows remarkable stability and high recognition rate using a reduced number of parameters. The system illustrates the possibility of designing a combined system that benefits from the strengths of its base classifiers while avoiding many of their weaknesses.
Tasks	Face Recognition
Published	2016-07-23
URL	http://arxiv.org/abs/1607.06973v1
PDF	http://arxiv.org/pdf/1607.06973v1.pdf
PWC	https://paperswithcode.com/paper/combined-classifiers-for-invariant-face
Repo
Framework

On the Existence of a Sample Mean in Dynamic Time Warping Spaces


Title	On the Existence of a Sample Mean in Dynamic Time Warping Spaces
Authors	Brijnesh J. Jain, David Schultz
Abstract	The concept of sample mean in dynamic time warping (DTW) spaces has been successfully applied to improve pattern recognition systems and generalize centroid-based clustering algorithms. Its existence has neither been proved nor challenged. This article presents sufficient conditions for existence of a sample mean in DTW spaces. The proposed result justifies prior work on approximate mean algorithms, sets the stage for constructing exact mean algorithms, and is a first step towards a statistical theory of DTW spaces.
Tasks
Published	2016-10-14
URL	http://arxiv.org/abs/1610.04460v3
PDF	http://arxiv.org/pdf/1610.04460v3.pdf
PWC	https://paperswithcode.com/paper/on-the-existence-of-a-sample-mean-in-dynamic
Repo
Framework

Multimodal Latent Variable Analysis


Title	Multimodal Latent Variable Analysis
Authors	Vardan Papyan, Ronen Talmon
Abstract	Consider a set of multiple, multimodal sensors capturing a complex system or a physical phenomenon of interest. Our primary goal is to distinguish the underlying sources of variability manifested in the measured data. The first step in our analysis is to find the common source of variability present in all sensor measurements. We base our work on a recent paper, which tackles this problem with alternating diffusion (AD). In this work, we suggest to further the analysis by extracting the sensor-specific variables in addition to the common source. We propose an algorithm, which we analyze theoretically, and then demonstrate on three different applications: a synthetic example, a toy problem, and the task of fetal ECG extraction.
Tasks
Published	2016-11-25
URL	http://arxiv.org/abs/1611.08472v1
PDF	http://arxiv.org/pdf/1611.08472v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-latent-variable-analysis
Repo
Framework

A Grothendieck-type inequality for local maxima


Title	A Grothendieck-type inequality for local maxima
Authors	Andrea Montanari
Abstract	A large number of problems in optimization, machine learning, signal processing can be effectively addressed by suitable semidefinite programming (SDP) relaxations. Unfortunately, generic SDP solvers hardly scale beyond instances with a few hundreds variables (in the underlying combinatorial problem). On the other hand, it has been observed empirically that an effective strategy amounts to introducing a (non-convex) rank constraint, and solving the resulting smooth optimization problem by ascent methods. This non-convex problem has –generically– a large number of local maxima, and the reason for this success is therefore unclear. This paper provides rigorous support for this approach. For the problem of maximizing a linear functional over the elliptope, we prove that all local maxima are within a small gap from the SDP optimum. In several problems of interest, arbitrarily small relative error can be achieved by taking the rank constraint $k$ to be of order one, independently of the problem size.
Tasks
Published	2016-03-13
URL	http://arxiv.org/abs/1603.04064v1
PDF	http://arxiv.org/pdf/1603.04064v1.pdf
PWC	https://paperswithcode.com/paper/a-grothendieck-type-inequality-for-local
Repo
Framework

Boundary conditions for Shape from Shading


Title	Boundary conditions for Shape from Shading
Authors	Lyes Abada, Saliha Aouat, Omar el farouk Bourahla
Abstract	The Shape From Shading is one of a computer vision field. It studies the 3D reconstruction of an object from a single grayscale image. The difficulty of this field can be expressed in the local ambiguity (convex / concave). J.Shi and Q.Zhu have proposed a method (Global View) to solve the local ambiguity. This method based on the graph theory and the relationship between the singular points. In this work we will show that the use of singular points is not sufficient and requires further information on the object to resolve this ambiguity.
Tasks	3D Reconstruction
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03289v1
PDF	http://arxiv.org/pdf/1607.03289v1.pdf
PWC	https://paperswithcode.com/paper/boundary-conditions-for-shape-from-shading
Repo
Framework

On Valid Optimal Assignment Kernels and Applications to Graph Classification


Title	On Valid Optimal Assignment Kernels and Applications to Graph Classification
Authors	Nils M. Kriege, Pierre-Louis Giscard, Richard C. Wilson
Abstract	The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their parts and sums over all pairs of parts. Assignment kernels, in contrast, are obtained from an optimal bijection between parts, which can provide a more valid notion of similarity. In general however, optimal assignments yield indefinite functions, which complicates their use in kernel methods. We characterize a class of base kernels used to compare parts that guarantees positive semidefinite optimal assignment kernels. These base kernels give rise to hierarchies from which the optimal assignment kernels are computed in linear time by histogram intersection. We apply these results by developing the Weisfeiler-Lehman optimal assignment kernel for graphs. It provides high classification accuracy on widely-used benchmark data sets improving over the original Weisfeiler-Lehman kernel.
Tasks	Graph Classification
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01141v3
PDF	http://arxiv.org/pdf/1606.01141v3.pdf
PWC	https://paperswithcode.com/paper/on-valid-optimal-assignment-kernels-and
Repo
Framework

Compressive Holographic Video


Title	Compressive Holographic Video
Authors	Zihao Wang, Leonidas Spinoulas, Kuan He, Huaijin Chen, Lei Tian, Aggelos K. Katsaggelos, Oliver Cossairt
Abstract	Compressed sensing has been discussed separately in spatial and temporal domains. Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image. Coded exposure is a temporal compressed sensing method for high speed video acquisition. In this work, we combine compressive holography and coded exposure techniques and extend the discussion to 4D reconstruction in space and time from one coded captured image. In our prototype, digital in-line holography was used for imaging macroscopic, fast moving objects. The pixel-wise temporal modulation was implemented by a digital micromirror device. In this paper we demonstrate $10\times$ temporal super resolution with multiple depths recovery from a single image. Two examples are presented for the purpose of recording subtle vibrations and tracking small particles within 5 ms.
Tasks	Super-Resolution
Published	2016-10-27
URL	http://arxiv.org/abs/1610.09013v1
PDF	http://arxiv.org/pdf/1610.09013v1.pdf
PWC	https://paperswithcode.com/paper/compressive-holographic-video
Repo
Framework

Machine Learning on Human Connectome Data from MRI


Title	Machine Learning on Human Connectome Data from MRI
Authors	Colin J Brown, Ghassan Hamarneh
Abstract	Functional MRI (fMRI) and diffusion MRI (dMRI) are non-invasive imaging modalities that allow in-vivo analysis of a patient’s brain network (known as a connectome). Use of these technologies has enabled faster and better diagnoses and treatments of neurological disorders and a deeper understanding of the human brain. Recently, researchers have been exploring the application of machine learning models to connectome data in order to predict clinical outcomes and analyze the importance of subnetworks in the brain. Connectome data has unique properties, which present both special challenges and opportunities when used for machine learning. The purpose of this work is to review the literature on the topic of applying machine learning models to MRI-based connectome data. This field is growing rapidly and now encompasses a large body of research. To summarize the research done to date, we provide a comparative, structured summary of 77 relevant works, tabulated according to different criteria, that represent the majority of the literature on this topic. (We also published a living version of this table online at http://connectomelearning.cs.sfu.ca that the community can continue to contribute to.) After giving an overview of how connectomes are constructed from dMRI and fMRI data, we discuss the variety of machine learning tasks that have been explored with connectome data. We then compare the advantages and drawbacks of different machine learning approaches that have been employed, discussing different feature selection and feature extraction schemes, as well as the learning models and regularization penalties themselves. Throughout this discussion, we focus particularly on how the methods are adapted to the unique nature of graphical connectome data. Finally, we conclude by summarizing the current state of the art and by outlining what we believe are strategic directions for future research.
Tasks	Feature Selection
Published	2016-11-26
URL	http://arxiv.org/abs/1611.08699v1
PDF	http://arxiv.org/pdf/1611.08699v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-on-human-connectome-data
Repo
Framework

Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients


Title	Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients
Authors	Amir Hosein Zamanian, Abdolreza Ohadi
Abstract	The features of non-stationary multi-component signals are often difficult to be extracted for expert systems. In this paper, a new method for feature extraction that is based on maximization of local Gaussian correlation function of wavelet coefficients and signal is presented. The effect of empirical mode decomposition (EMD) to decompose multi-component signals to intrinsic mode functions (IMFs), before using of local Gaussian correlation is discussed. The experimental vibration signals from two gearbox systems are used to show the efficiency of the presented method. Linear support vector machine (SVM) is utilized to classify feature sets extracted with the presented method. The obtained results show that the features extracted in this method have excellent ability to classify faults without any additional feature selection; it is also shown that EMD can improve or degrade features according to the utilized feature reduction method.
Tasks	Feature Selection
Published	2016-06-26
URL	http://arxiv.org/abs/1606.07981v1
PDF	http://arxiv.org/pdf/1606.07981v1.pdf
PWC	https://paperswithcode.com/paper/gear-fault-diagnosis-based-on-gaussian
Repo
Framework

Template Adaptation for Face Verification and Identification


Title	Template Adaptation for Face Verification and Identification
Authors	Nate Crosswhite, Jeffrey Byrne, Omkar M. Parkhi, Chris Stauffer, Qiong Cao, Andrew Zisserman
Abstract	Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset for imagery and the YouTubeFaces dataset for videos. In contrast, the newly released IJB-A face recognition dataset unifies evaluation of one-to-many face identification with one-to-one face verification over templates, or sets of imagery and videos for a subject. In this paper, we study the problem of template adaptation, a form of transfer learning to the set of media in a template. Extensive performance evaluations on IJB-A show a surprising result, that perhaps the simplest method of template adaptation, combining deep convolutional network features with template specific linear SVMs, outperforms the state-of-the-art by a wide margin. We study the effects of template size, negative set construction and classifier fusion on performance, then compare template adaptation to convolutional networks with metric learning, 2D and 3D alignment. Our unexpected conclusion is that these other methods, when combined with template adaptation, all achieve nearly the same top performance on IJB-A for template-based face verification and identification.
Tasks	Face Identification, Face Recognition, Face Verification, Metric Learning, Transfer Learning
Published	2016-03-12
URL	http://arxiv.org/abs/1603.03958v3
PDF	http://arxiv.org/pdf/1603.03958v3.pdf
PWC	https://paperswithcode.com/paper/template-adaptation-for-face-verification-and
Repo
Framework

Information Theoretic Limits of Data Shuffling for Distributed Learning


Title	Information Theoretic Limits of Data Shuffling for Distributed Learning
Authors	Mohamed Attia, Ravi Tandon
Abstract	Data shuffling is one of the fundamental building blocks for distributed learning algorithms, that increases the statistical gain for each step of the learning process. In each iteration, different shuffled data points are assigned by a central node to a distributed set of workers to perform local computations, which leads to communication bottlenecks. The focus of this paper is on formalizing and understanding the fundamental information-theoretic trade-off between storage (per worker) and the worst-case communication overhead for the data shuffling problem. We completely characterize the information theoretic trade-off for $K=2$, and $K=3$ workers, for any value of storage capacity, and show that increasing the storage across workers can reduce the communication overhead by leveraging coding. We propose a novel and systematic data delivery and storage update strategy for each data shuffle iteration, which preserves the structural properties of the storage across the workers, and aids in minimizing the communication overhead in subsequent data shuffling iterations.
Tasks
Published	2016-09-16
URL	http://arxiv.org/abs/1609.05181v1
PDF	http://arxiv.org/pdf/1609.05181v1.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-limits-of-data
Repo
Framework