July 28, 2019

3370 words 16 mins read

Paper Group ANR 289

Mobile Quantification and Therapy Course Tracking for Gait Rehabilitation. Low-Resource Neural Headline Generation. Generalized Rank Pooling for Activity Recognition. Information-Theoretic Representation Learning for Positive-Unlabeled Classification. An Adaptivity Hierarchy Theorem for Property Testing. LEARN: Learned Experts’ Assessment-based Rec …

Mobile Quantification and Therapy Course Tracking for Gait Rehabilitation


Title	Mobile Quantification and Therapy Course Tracking for Gait Rehabilitation
Authors	Javier Conte Alcaraz, Sanam Moghaddamnia, Jürgen Peissig
Abstract	This paper presents a novel autonomous quality metric to quantify the rehabilitations progress of subjects with knee/hip operations. The presented method supports digital analysis of human gait patterns using smartphones. The algorithm related to the autonomous metric utilizes calibrated acceleration, gyroscope and magnetometer signals from seven Inertial Measurement Unit attached on the lower body in order to classify and generate the grading system values. The developed Android application connects the seven Inertial Measurement Units via Bluetooth and performs the data acquisition and processing in real-time. In total nine features per acceleration direction and lower body joint angle are calculated and extracted in real-time to achieve a fast feedback to the user. We compare the classification accuracy and quantification capabilities of Linear Discriminant Analysis, Principal Component Analysis and Naive Bayes algorithms. The presented system is able to classify patients and control subjects with an accuracy of up to 100%. The outcomes can be saved on the device or transmitted to treating physicians for later control of the subject’s improvements and the efficiency of physiotherapy treatments in motor rehabilitation. The proposed autonomous quality metric solution bears great potential to be used and deployed to support digital healthcare and therapy.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.03275v1
PDF	http://arxiv.org/pdf/1707.03275v1.pdf
PWC	https://paperswithcode.com/paper/mobile-quantification-and-therapy-course
Repo
Framework

Low-Resource Neural Headline Generation


Title	Low-Resource Neural Headline Generation
Authors	Ottokar Tilk, Tanel Alumäe
Abstract	Recent neural headline generation models have shown great results, but are generally trained on very large datasets. We focus our efforts on improving headline quality on smaller datasets by the means of pretraining. We propose new methods that enable pre-training all the parameters of the model and utilize all available text, resulting in improvements by up to 32.4% relative in perplexity and 2.84 points in ROUGE.
Tasks
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09769v1
PDF	http://arxiv.org/pdf/1707.09769v1.pdf
PWC	https://paperswithcode.com/paper/low-resource-neural-headline-generation
Repo
Framework

Generalized Rank Pooling for Activity Recognition


Title	Generalized Rank Pooling for Activity Recognition
Authors	Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen Gould
Abstract	Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal order of the frames, which could otherwise be used for better recognition. Towards this end, we propose a novel pooling method, generalized rank pooling (GRP), that takes as input, features from the intermediate layers of a CNN that is trained on tiny sub-sequences, and produces as output the parameters of a subspace which (i) provides a low-rank approximation to the features and (ii) preserves their temporal order. We propose to use these parameters as a compact representation for the video sequence, which is then used in a classification setup. We formulate an objective for computing this subspace as a Riemannian optimization problem on the Grassmann manifold, and propose an efficient conjugate gradient scheme for solving it. Experiments on several activity recognition datasets show that our scheme leads to state-of-the-art performance.
Tasks	Activity Recognition, Temporal Action Localization
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02112v3
PDF	http://arxiv.org/pdf/1704.02112v3.pdf
PWC	https://paperswithcode.com/paper/generalized-rank-pooling-for-activity
Repo
Framework

Information-Theoretic Representation Learning for Positive-Unlabeled Classification


Title	Information-Theoretic Representation Learning for Positive-Unlabeled Classification
Authors	Tomoya Sakai, Gang Niu, Masashi Sugiyama
Abstract	Recent advances in weakly supervised classification allow us to train a classifier only from positive and unlabeled (PU) data. However, existing PU classification methods typically require an accurate estimate of the class-prior probability, which is a critical bottleneck particularly for high-dimensional data. This problem has been commonly addressed by applying principal component analysis in advance, but such unsupervised dimension reduction can collapse underlying class structure. In this paper, we propose a novel representation learning method from PU data based on the information-maximization principle. Our method does not require class-prior estimation and thus can be used as a preprocessing method for PU classification. Through experiments, we demonstrate that our method combined with deep neural networks highly improves the accuracy of PU class-prior estimation, leading to state-of-the-art PU classification performance.
Tasks	Dimensionality Reduction, Representation Learning
Published	2017-10-15
URL	http://arxiv.org/abs/1710.05359v3
PDF	http://arxiv.org/pdf/1710.05359v3.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-representation-learning
Repo
Framework

An Adaptivity Hierarchy Theorem for Property Testing


Title	An Adaptivity Hierarchy Theorem for Property Testing
Authors	Clement Canonne, Tom Gur
Abstract	Adaptivity is known to play a crucial role in property testing. In particular, there exist properties for which there is an exponential gap between the power of \emph{adaptive} testing algorithms, wherein each query may be determined by the answers received to prior queries, and their \emph{non-adaptive} counterparts, in which all queries are independent of answers obtained from previous queries. In this work, we investigate the role of adaptivity in property testing at a finer level. We first quantify the degree of adaptivity of a testing algorithm by considering the number of “rounds of adaptivity” it uses. More accurately, we say that a tester is $k$-(round) adaptive if it makes queries in $k+1$ rounds, where the queries in the $i$'th round may depend on the answers obtained in the previous $i-1$ rounds. Then, we ask the following question: Does the power of testing algorithms smoothly grow with the number of rounds of adaptivity? We provide a positive answer to the foregoing question by proving an adaptivity hierarchy theorem for property testing. Specifically, our main result shows that for every $n\in \mathbb{N}$ and $0 \le k \le n^{0.99}$ there exists a property $\mathcal{P}{n,k}$ of functions for which (1) there exists a $k$-adaptive tester for $\mathcal{P}{n,k}$ with query complexity $\tilde{O}(k)$, yet (2) any $(k-1)$-adaptive tester for $\mathcal{P}_{n,k}$ must make $\Omega(n)$ queries. In addition, we show that such a qualitative adaptivity hierarchy can be witnessed for testing natural properties of graphs.
Tasks
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05678v1
PDF	http://arxiv.org/pdf/1702.05678v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptivity-hierarchy-theorem-for-property
Repo
Framework

LEARN: Learned Experts’ Assessment-based Reconstruction Network for Sparse-data CT


Title	LEARN: Learned Experts’ Assessment-based Reconstruction Network for Sparse-data CT
Authors	Hu Chen, Yi Zhang, Yunjin Chen, Junfeng Zhang, Weihua Zhang, Huaiqiaing Sun, Yang Lv, Peixi Liao, Jiliu Zhou, Ge Wang
Abstract	Compressive sensing (CS) has proved effective for tomographic reconstruction from sparsely collected data or under-sampled measurements, which are practically important for few-view CT, tomosynthesis, interior tomography, and so on. To perform sparse-data CT, the iterative reconstruction commonly use regularizers in the CS framework. Currently, how to choose the parameters adaptively for regularization is a major open problem. In this paper, inspired by the idea of machine learning especially deep learning, we unfold a state-of-the-art “fields of experts” based iterative reconstruction scheme up to a number of iterations for data-driven training, construct a Learned Experts’ Assessment-based Reconstruction Network (“LEARN”) for sparse-data CT, and demonstrate the feasibility and merits of our LEARN network. The experimental results with our proposed LEARN network produces a competitive performance with the well-known Mayo Clinic Low-Dose Challenge Dataset relative to several state-of-the-art methods, in terms of artifact reduction, feature preservation, and computational speed. This is consistent to our insight that because all the regularization terms and parameters used in the iterative reconstruction are now learned from the training data, our LEARN network utilizes application-oriented knowledge more effectively and recovers underlying images more favorably than competing algorithms. Also, the number of layers in the LEARN network is only 12, reducing the computational complexity of typical iterative algorithms by orders of magnitude.
Tasks	Compressive Sensing
Published	2017-07-30
URL	http://arxiv.org/abs/1707.09636v3
PDF	http://arxiv.org/pdf/1707.09636v3.pdf
PWC	https://paperswithcode.com/paper/learn-learned-experts-assessment-based
Repo
Framework

Information Potential Auto-Encoders


Title	Information Potential Auto-Encoders
Authors	Yan Zhang, Mete Ozay, Zhun Sun, Takayuki Okatani
Abstract	In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and encoding variables of AEs during the training phase. In order to estimate the entropy of the encoding variables and the mutual information, we propose a non-parametric method. We also give an information theoretic view of Variational AEs (VAEs), which suggests that VAEs can be considered as parametric methods that estimate entropy. Experimental results show that the proposed non-parametric models have more degree of freedom in terms of representation learning of features drawn from complex distributions such as Mixture of Gaussians, compared to methods which estimate entropy using parametric approaches, such as Variational AEs.
Tasks	Representation Learning
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04635v2
PDF	http://arxiv.org/pdf/1706.04635v2.pdf
PWC	https://paperswithcode.com/paper/information-potential-auto-encoders
Repo
Framework

Recovery Conditions and Sampling Strategies for Network Lasso


Title	Recovery Conditions and Sampling Strategies for Network Lasso
Authors	Alexandru Mara, Alexander Jung
Abstract	The network Lasso is a recently proposed convex optimization method for machine learning from massive network structured datasets, i.e., big data over networks. It is a variant of the well-known least absolute shrinkage and selection operator (Lasso), which is underlying many methods in learning and signal processing involving sparse models. Highly scalable implementations of the network Lasso can be obtained by state-of-the art proximal methods, e.g., the alternating direction method of multipliers (ADMM). By generalizing the concept of the compatibility condition put forward by van de Geer and Buehlmann as a powerful tool for the analysis of plain Lasso, we derive a sufficient condition, i.e., the network compatibility condition, on the underlying network topology such that network Lasso accurately learns a clustered underlying graph signal. This network compatibility condition relates the location of the sampled nodes with the clustering structure of the network. In particular, the NCC informs the choice of which nodes to sample, or in machine learning terms, which data points provide most information if labeled.
Tasks
Published	2017-09-03
URL	http://arxiv.org/abs/1709.01402v1
PDF	http://arxiv.org/pdf/1709.01402v1.pdf
PWC	https://paperswithcode.com/paper/recovery-conditions-and-sampling-strategies
Repo
Framework

Semi-Global Stereo Matching with Surface Orientation Priors


Title	Semi-Global Stereo Matching with Surface Orientation Priors
Authors	Daniel Scharstein, Tatsunori Taniai, Sudipta N. Sinha
Abstract	Semi-Global Matching (SGM) is a widely-used efficient stereo matching technique. It works well for textured scenes, but fails on untextured slanted surfaces due to its fronto-parallel smoothness assumption. To remedy this problem, we propose a simple extension, termed SGM-P, to utilize precomputed surface orientation priors. Such priors favor different surface slants in different 2D image regions or 3D scene regions and can be derived in various ways. In this paper we evaluate plane orientation priors derived from stereo matching at a coarser resolution and show that such priors can yield significant performance gains for difficult weakly-textured scenes. We also explore surface normal priors derived from Manhattan-world assumptions, and we analyze the potential performance gains using oracle priors derived from ground-truth data. SGM-P only adds a minor computational overhead to SGM and is an attractive alternative to more complex methods employing higher-order smoothness terms.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00818v1
PDF	http://arxiv.org/pdf/1712.00818v1.pdf
PWC	https://paperswithcode.com/paper/semi-global-stereo-matching-with-surface
Repo
Framework

Constraint Answer Set Solver EZCSP and Why Integration Schemas Matter


Title	Constraint Answer Set Solver EZCSP and Why Integration Schemas Matter
Authors	Marcello Balduccini, Yuliya Lierler
Abstract	Researchers in answer set programming and constraint programming have spent significant efforts in the development of hybrid languages and solving algorithms combining the strengths of these traditionally separate fields. These efforts resulted in a new research area: constraint answer set programming. Constraint answer set programming languages and systems proved to be successful at providing declarative, yet efficient solutions to problems involving hybrid reasoning tasks. One of the main contributions of this paper is the first comprehensive account of the constraint answer set language and solver EZCSP, a mainstream representative of this research area that has been used in various successful applications. We also develop an extension of the transition systems proposed by Nieuwenhuis et al. in 2006 to capture Boolean satisfiability solvers. We use this extension to describe the EZCSP algorithm and prove formal claims about it. The design and algorithmic details behind EZCSP clearly demonstrate that the development of the hybrid systems of this kind is challenging. Many questions arise when one faces various design choices in an attempt to maximize system’s benefits. One of the key decisions that a developer of a hybrid solver makes is settling on a particular integration schema within its implementation. Thus, another important contribution of this paper is a thorough case study based on EZCSP, focused on the various integration schemas that it provides. Under consideration in Theory and Practice of Logic Programming (TPLP).
Tasks
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04047v3
PDF	http://arxiv.org/pdf/1702.04047v3.pdf
PWC	https://paperswithcode.com/paper/constraint-answer-set-solver-ezcsp-and-why
Repo
Framework

Using Phone Sensors and an Artificial Neural Network to Detect Gait Changes During Drinking Episodes in the Natural Environment


Title	Using Phone Sensors and an Artificial Neural Network to Detect Gait Changes During Drinking Episodes in the Natural Environment
Authors	Brian Suffoletto, Pedram Gharani, Tammy Chung, Hassan Karimi
Abstract	Phone sensors could be useful in assessing changes in gait that occur with alcohol consumption. This study determined (1) feasibility of collecting gait-related data during drinking occasions in the natural environment, and (2) how gait-related features measured by phone sensors relate to estimated blood alcohol concentration (eBAC). Ten young adult heavy drinkers were prompted to complete a 5-step gait task every hour from 8pm to 12am over four consecutive weekends. We collected 3-xis accelerometer, gyroscope, and magnetometer data from phone sensors, and computed 24 gait-related features using a sliding window technique. eBAC levels were calculated at each time point based on Ecological Momentary Assessment (EMA) of alcohol use. We used an artificial neural network model to analyze associations between sensor features and eBACs in training (70% of the data) and validation and test (30% of the data) datasets. We analyzed 128 data points where both eBAC and gait-related sensor data was captured, either when not drinking (n=60), while eBAC was ascending (n=55) or eBAC was descending (n=13). 21 data points were captured at times when the eBAC was greater than the legal limit (0.08 mg/dl). Using a Bayesian regularized neural network, gait-related phone sensor features showed a high correlation with eBAC (Pearson’s r > 0.9), and >95% of estimated eBAC would fall between -0.012 and +0.012 of actual eBAC. It is feasible to collect gait-related data from smartphone sensors during drinking occasions in the natural environment. Sensor-based features can be used to infer gait changes associated with elevated blood alcohol content.
Tasks
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03410v2
PDF	http://arxiv.org/pdf/1711.03410v2.pdf
PWC	https://paperswithcode.com/paper/using-phone-sensors-and-an-artificial-neural
Repo
Framework

Robust Visual SLAM with Point and Line Features


Title	Robust Visual SLAM with Point and Line Features
Authors	Xingxing Zuo, Xiaojia Xie, Yong Liu, Guoquan Huang
Abstract	In this paper, we develop a robust efficient visual SLAM system that utilizes heterogeneous point and line features. By leveraging ORB-SLAM [1], the proposed system consists of stereo matching, frame tracking, local mapping, loop detection, and bundle adjustment of both point and line features. In particular, as the main theoretical contributions of this paper, we, for the first time, employ the orthonormal representation as the minimal parameterization to model line features along with point features in visual SLAM and analytically derive the Jacobians of the re-projection errors with respect to the line parameters, which significantly improves the SLAM solution. The proposed SLAM has been extensively tested in both synthetic and real-world experiments whose results demonstrate that the proposed system outperforms the state-of-the-art methods in various scenarios.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08654v1
PDF	http://arxiv.org/pdf/1711.08654v1.pdf
PWC	https://paperswithcode.com/paper/robust-visual-slam-with-point-and-line
Repo
Framework

Vision Recognition using Discriminant Sparse Optimization Learning


Title	Vision Recognition using Discriminant Sparse Optimization Learning
Authors	Qingxiang Feng, Yicong Zhou
Abstract	To better select the correct training sample and obtain the robust representation of the query sample, this paper proposes a discriminant-based sparse optimization learning model. This learning model integrates discriminant and sparsity together. Based on this model, we then propose a classifier called locality-based discriminant sparse representation (LDSR). Because discriminant can help to increase the difference of samples in different classes and to decrease the difference of samples within the same class, LDSR can obtain better sparse coefficients and constitute a better sparse representation for classification. In order to take advantages of kernel techniques, discriminant and sparsity, we further propose a nonlinear classifier called kernel locality-based discriminant sparse representation (KLDSR). Experiments on several well-known databases prove that the performance of LDSR and KLDSR is better than that of several state-of-the-art methods including deep learning based methods.
Tasks
Published	2017-11-19
URL	http://arxiv.org/abs/1712.01645v1
PDF	http://arxiv.org/pdf/1712.01645v1.pdf
PWC	https://paperswithcode.com/paper/vision-recognition-using-discriminant-sparse
Repo
Framework

Rapid-Rate: A Framework for Semi-supervised Real-time Sentiment Trend Detection in Unstructured Big Data


Title	Rapid-Rate: A Framework for Semi-supervised Real-time Sentiment Trend Detection in Unstructured Big Data
Authors	Vineet John
Abstract	Commercial establishments like restaurants, service centres and retailers have several sources of customer feedback about products and services, most of which need not be as structured as rated reviews provided by services like Yelp, or Amazon, in terms of sentiment conveyed. For instance, Amazon provides a fine-grained score on a numeric scale for product reviews. Some sources, however, like social media (Twitter, Facebook), mailing lists (Google Groups) and forums (Quora) contain text data that is much more voluminous, but unstructured and unlabelled. It might be in the best interests of a business establishment to assess the general sentiment towards their brand on these platforms as well. This text could be pipelined into a system with a built-in prediction model, with the objective of generating real-time graphs on opinion and sentiment trends. Although such tasks like the one described about have been explored with respect to document classification problems in the past, the implementation described in this paper, by virtue of learning a continuous function rather than a discrete one, offers a lot more depth of insight as compared to document classification approaches. This study aims to explore the validity of such a continuous function predicting model to quantify sentiment about an entity, without the additional overhead of manual labelling, and computational preprocessing & feature extraction. This research project also aims to design and implement a re-usable document regression pipeline as a framework, Rapid-Rate, that can be used to predict document scores in real-time.
Tasks	Document Classification
Published	2017-03-23
URL	http://arxiv.org/abs/1703.08088v2
PDF	http://arxiv.org/pdf/1703.08088v2.pdf
PWC	https://paperswithcode.com/paper/rapid-rate-a-framework-for-semi-supervised
Repo
Framework

Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation


Title	Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
Authors	Mohsen Ghafoorian, Alireza Mehrtash, Tina Kapur, Nico Karssemeijer, Elena Marchiori, Mehran Pesteie, Charles R. G. Guttmann, Frank-Erik de Leeuw, Clare M. Tempany, Bram van Ginneken, Andriy Fedorov, Purang Abolmaesumi, Bram Platel, William M. Wells III
Abstract	Magnetic Resonance Imaging (MRI) is widely used in routine clinical diagnosis and treatment. However, variations in MRI acquisition protocols result in different appearances of normal and diseased tissue in the images. Convolutional neural networks (CNNs), which have shown to be successful in many medical image analysis tasks, are typically sensitive to the variations in imaging protocols. Therefore, in many cases, networks trained on data acquired with one MRI protocol, do not perform satisfactorily on data acquired with different protocols. This limits the use of models trained with large annotated legacy datasets on a new dataset with a different domain which is often a recurring situation in clinical settings. In this study, we aim to answer the following central questions regarding domain adaptation in medical image analysis: Given a fitted legacy model, 1) How much data from the new domain is required for a decent adaptation of the original network?; and, 2) What portion of the pre-trained model parameters should be retrained given a certain number of the new domain training samples? To address these questions, we conducted extensive experiments in white matter hyperintensity segmentation task. We trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain. We then compared the performance of the model to the surrogate scenarios where either the same trained network is used or a new network is trained from scratch on the new dataset.The domain-adapted network tuned only by two training examples achieved a Dice score of 0.63 substantially outperforming a similar network trained on the same set of examples from scratch.
Tasks	Domain Adaptation, Lesion Segmentation, Transfer Learning
Published	2017-02-25
URL	http://arxiv.org/abs/1702.07841v1
PDF	http://arxiv.org/pdf/1702.07841v1.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-for-domain-adaptation-in
Repo
Framework