May 5, 2019

3067 words 15 mins read

Paper Group ANR 549

Radiation Search Operations using Scene Understanding with Autonomous UAV and UGV. Sequential Cost-Sensitive Feature Acquisition. Mining Spatio-temporal Data on Industrialization from Historical Registries. $\ell_1$ Regularized Gradient Temporal-Difference Learning. FOMTrace: Interactive Video Segmentation By Image Graphs and Fuzzy Object Models. T …

Radiation Search Operations using Scene Understanding with Autonomous UAV and UGV


Title	Radiation Search Operations using Scene Understanding with Autonomous UAV and UGV
Authors	Gordon Christie, Adam Shoemaker, Kevin Kochersberger, Pratap Tokekar, Lance McLean, Alexander Leonessa
Abstract	Autonomously searching for hazardous radiation sources requires the ability of the aerial and ground systems to understand the scene they are scouting. In this paper, we present systems, algorithms, and experiments to perform radiation search using unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) by employing semantic scene segmentation. The aerial data is used to identify radiological points of interest, generate an orthophoto along with a digital elevation model (DEM) of the scene, and perform semantic segmentation to assign a category (e.g. road, grass) to each pixel in the orthophoto. We perform semantic segmentation by training a model on a dataset of images we collected and annotated, using the model to perform inference on images of the test area unseen to the model, and then refining the results with the DEM to better reason about category predictions at each pixel. We then use all of these outputs to plan a path for a UGV carrying a LiDAR to map the environment and avoid obstacles not present during the flight, and a radiation detector to collect more precise radiation measurements from the ground. Results of the analysis for each scenario tested favorably. We also note that our approach is general and has the potential to work for a variety of different sensing tasks.
Tasks	Scene Segmentation, Scene Understanding, Semantic Segmentation
Published	2016-08-31
URL	http://arxiv.org/abs/1609.00017v1
PDF	http://arxiv.org/pdf/1609.00017v1.pdf
PWC	https://paperswithcode.com/paper/radiation-search-operations-using-scene
Repo
Framework

Sequential Cost-Sensitive Feature Acquisition


Title	Sequential Cost-Sensitive Feature Acquisition
Authors	Gabriella Contardo, Ludovic Denoyer, Thierry Artières
Abstract	We propose a reinforcement learning based approach to tackle the cost-sensitive learning problem where each input feature has a specific cost. The acquisition process is handled through a stochastic policy which allows features to be acquired in an adaptive way. The general architecture of our approach relies on representation learning to enable performing prediction on any partially observed sample, whatever the set of its observed features are. The resulting model is an original mix of representation learning and of reinforcement learning ideas. It is learned with policy gradient techniques to minimize a budgeted inference cost. We demonstrate the effectiveness of our proposed method with several experiments on a variety of datasets for the sparse prediction problem where all features have the same cost, but also for some cost-sensitive settings.
Tasks	Representation Learning
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03691v1
PDF	http://arxiv.org/pdf/1607.03691v1.pdf
PWC	https://paperswithcode.com/paper/sequential-cost-sensitive-feature-acquisition
Repo
Framework

Mining Spatio-temporal Data on Industrialization from Historical Registries


Title	Mining Spatio-temporal Data on Industrialization from Historical Registries
Authors	David Berenbaum, Dwyer Deighan, Thomas Marlow, Ashley Lee, Scott Frickel, Mark Howison
Abstract	Despite the growing availability of big data in many fields, historical data on socioevironmental phenomena are often not available due to a lack of automated and scalable approaches for collecting, digitizing, and assembling them. We have developed a data-mining method for extracting tabulated, geocoded data from printed directories. While scanning and optical character recognition (OCR) can digitize printed text, these methods alone do not capture the structure of the underlying data. Our pipeline integrates both page layout analysis and OCR to extract tabular, geocoded data from structured text. We demonstrate the utility of this method by applying it to scanned manufacturing registries from Rhode Island that record 41 years of industrial land use. The resulting spatio-temporal data can be used for socioenvironmental analyses of industrialization at a resolution that was not previously possible. In particular, we find strong evidence for the dispersion of manufacturing from the urban core of Providence, the state’s capital, along the Interstate 95 corridor to the north and south.
Tasks	Optical Character Recognition
Published	2016-12-03
URL	http://arxiv.org/abs/1612.00992v1
PDF	http://arxiv.org/pdf/1612.00992v1.pdf
PWC	https://paperswithcode.com/paper/mining-spatio-temporal-data-on
Repo
Framework

$\ell_1$ Regularized Gradient Temporal-Difference Learning


Title	$\ell_1$ Regularized Gradient Temporal-Difference Learning
Authors	Dominik Meyer, Hao Shen, Klaus Diepold
Abstract	In this paper, we study the Temporal Difference (TD) learning with linear value function approximation. It is well known that most TD learning algorithms are unstable with linear function approximation and off-policy learning. Recent development of Gradient TD (GTD) algorithms has addressed this problem successfully. However, the success of GTD algorithms requires a set of well chosen features, which are not always available. When the number of features is huge, the GTD algorithms might face the problem of overfitting and being computationally expensive. To cope with this difficulty, regularization techniques, in particular $\ell_1$ regularization, have attracted significant attentions in developing TD learning algorithms. The present work combines the GTD algorithms with $\ell_1$ regularization. We propose a family of $\ell_1$ regularized GTD algorithms, which employ the well known soft thresholding operator. We investigate convergence properties of the proposed algorithms, and depict their performance with several numerical experiments.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01476v1
PDF	http://arxiv.org/pdf/1610.01476v1.pdf
PWC	https://paperswithcode.com/paper/ell_1-regularized-gradient-temporal
Repo
Framework

FOMTrace: Interactive Video Segmentation By Image Graphs and Fuzzy Object Models


Title	FOMTrace: Interactive Video Segmentation By Image Graphs and Fuzzy Object Models
Authors	Thiago Vallin Spina, Alexandre Xavier Falcão
Abstract	Common users have changed from mere consumers to active producers of multimedia data content. Video editing plays an important role in this scenario, calling for simple segmentation tools that can handle fast-moving and deformable video objects with possible occlusions, color similarities with the background, among other challenges. We present an interactive video segmentation method, named FOMTrace, which addresses the problem in an effective and efficient way. From a user-provided object mask in a first frame, the method performs semi-automatic video segmentation on a spatiotemporal superpixel-graph, and then estimates a Fuzzy Object Model (FOM), which refines segmentation of the second frame by constraining delineation on a pixel-graph within a region where the object’s boundary is expected to be. The user can correct/accept the refined object mask in the second frame, which is then similarly used to improve the spatiotemporal video segmentation of the remaining frames. Both steps are repeated alternately, within interactive response times, until the segmentation refinement of the final frame is accepted by the user. Extensive experiments demonstrate FOMTrace’s ability for tracing objects in comparison with state-of-the-art approaches for interactive video segmentation, supervised, and unsupervised object tracking.
Tasks	Object Tracking, Video Semantic Segmentation
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03369v1
PDF	http://arxiv.org/pdf/1606.03369v1.pdf
PWC	https://paperswithcode.com/paper/fomtrace-interactive-video-segmentation-by
Repo
Framework

The BioDynaMo Project: a platform for computer simulations of biological dynamics


Title	The BioDynaMo Project: a platform for computer simulations of biological dynamics
Authors	Leonard Johard, Lukas Breitwieser, Alberto Di Meglio, Marco Manca, Manuel Mazzara, Max Talanov
Abstract	This paper is a brief update on developments in the BioDynaMo project, a new platform for computer simulations for biological research. We will discuss the new capabilities of the simulator, important new concepts simulation methodology as well as its numerous applications to the computational biology and nanoscience communities.
Tasks
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01818v2
PDF	http://arxiv.org/pdf/1608.01818v2.pdf
PWC	https://paperswithcode.com/paper/the-biodynamo-project-a-platform-for-computer
Repo
Framework

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems


Title	Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
Authors	Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
Abstract	We study the projected gradient descent method on low-rank matrix problems with a strongly convex objective. We use the Burer-Monteiro factorization approach to implicitly enforce low-rankness; such factorization introduces non-convexity in the objective. We focus on constraint sets that include both positive semi-definite (PSD) constraints and specific matrix norm-constraints. Such criteria appear in quantum state tomography and phase retrieval applications. We show that non-convex projected gradient descent favors local linear convergence in the factored space. We build our theory on a novel descent lemma, that non-trivially extends recent results on the unconstrained problem. The resulting algorithm is Projected Factored Gradient Descent, abbreviated as ProjFGD, and shows superior performance compared to state of the art on quantum state tomography and sparse phase retrieval applications.
Tasks	Quantum State Tomography
Published	2016-06-04
URL	http://arxiv.org/abs/1606.01316v3
PDF	http://arxiv.org/pdf/1606.01316v3.pdf
PWC	https://paperswithcode.com/paper/provable-burer-monteiro-factorization-for-a
Repo
Framework


Title	Automatic Detection and Categorization of Election-Related Tweets
Authors	Prashanth Vijayaraghavan, Soroush Vosoughi, Deb Roy
Abstract	With the rise in popularity of public social media and micro-blogging services, most notably Twitter, the people have found a venue to hear and be heard by their peers without an intermediary. As a consequence, and aided by the public nature of Twitter, political scientists now potentially have the means to analyse and understand the narratives that organically form, spread and decline among the public in a political campaign. However, the volume and diversity of the conversation on Twitter, combined with its noisy and idiosyncratic nature, make this a hard task. Thus, advanced data mining and language processing techniques are required to process and analyse the data. In this paper, we present and evaluate a technical framework, based on recent advances in deep neural networks, for identifying and analysing election-related conversation on Twitter on a continuous, longitudinal basis. Our models can detect election-related tweets with an F-score of 0.92 and can categorize these tweets into 22 topics with an F-score of 0.90.
Tasks
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05150v1
PDF	http://arxiv.org/pdf/1605.05150v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-and-categorization-of
Repo
Framework

Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes


Title	Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes
Authors	Ahmed M. Alaa, Jinsung Yoon, Scott Hu, Mihaela van der Schaar
Abstract	Objective: In this paper, we develop a personalized real-time risk scoring algorithm that provides timely and granular assessments for the clinical acuity of ward patients based on their (temporal) lab tests and vital signs; the proposed risk scoring system ensures timely intensive care unit (ICU) admissions for clinically deteriorating patients. Methods: The risk scoring system learns a set of latent patient subtypes from the offline electronic health record data, and trains a mixture of Gaussian Process (GP) experts, where each expert models the physiological data streams associated with a specific patient subtype. Transfer learning techniques are used to learn the relationship between a patient’s latent subtype and her static admission information (e.g. age, gender, transfer status, ICD-9 codes, etc). Results: Experiments conducted on data from a heterogeneous cohort of 6,321 patients admitted to Ronald Reagan UCLA medical center show that our risk score significantly and consistently outperforms the currently deployed risk scores, such as the Rothman index, MEWS, APACHE and SOFA scores, in terms of timeliness, true positive rate (TPR), and positive predictive value (PPV). Conclusion: Our results reflect the importance of adopting the concepts of personalized medicine in critical care settings; significant accuracy and timeliness gains can be achieved by accounting for the patients’ heterogeneity. Significance: The proposed risk scoring methodology can confer huge clinical and social benefits on more than 200,000 critically ill inpatient who exhibit cardiac arrests in the US every year.
Tasks	Gaussian Processes, Transfer Learning
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08853v1
PDF	http://arxiv.org/pdf/1610.08853v1.pdf
PWC	https://paperswithcode.com/paper/personalized-risk-scoring-for-critical-care-1
Repo
Framework

Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection


Title	Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection
Authors	Sheng-syun Shen, Hung-yi Lee
Abstract	Recurrent neural network architectures combining with attention mechanism, or neural attention model, have shown promising performance recently for the tasks including speech recognition, image caption generation, visual question answering and machine translation. In this paper, neural attention model is applied on two sequence classification tasks, dialogue act detection and key term extraction. In the sequence labeling tasks, the model input is a sequence, and the output is the label of the input sequence. The major difficulty of sequence labeling is that when the input sequence is long, it can include many noisy or irrelevant part. If the information in the whole sequence is treated equally, the noisy or irrelevant part may degrade the classification performance. The attention mechanism is helpful for sequence classification task because it is capable of highlighting important part among the entire sequence for the classification task. The experimental results show that with the attention mechanism, discernible improvements were achieved in the sequence labeling task considered here. The roles of the attention mechanism in the tasks are further analyzed and visualized in this paper.
Tasks	Machine Translation, Question Answering, Speech Recognition, Visual Question Answering
Published	2016-03-31
URL	http://arxiv.org/abs/1604.00077v1
PDF	http://arxiv.org/pdf/1604.00077v1.pdf
PWC	https://paperswithcode.com/paper/neural-attention-models-for-sequence
Repo
Framework

Parallel Wavelet Schemes for Images


Title	Parallel Wavelet Schemes for Images
Authors	David Barina, Michal Kula, Pavel Zemcik
Abstract	In this paper, we introduce several new schemes for calculation of discrete wavelet transforms of images. These schemes reduce the number of steps and, as a consequence, allow to reduce the number of synchronizations on parallel architectures. As an additional useful property, the proposed schemes can reduce also the number of arithmetic operations. The schemes are primarily demonstrated on CDF 5/3 and CDF 9/7 wavelets employed in JPEG 2000 image compression standard. However, the presented method is general, and it can be applied on any wavelet transform. As a result, our scheme requires only two memory barriers for 2-D CDF 5/3 transform compared to four barriers in the original separable form or three barriers in the non-separable scheme recently published. Our reasoning is supported by exhaustive experiments on high-end graphics cards.
Tasks	Image Compression
Published	2016-05-02
URL	https://arxiv.org/abs/1605.00561v4
PDF	https://arxiv.org/pdf/1605.00561v4.pdf
PWC	https://paperswithcode.com/paper/parallel-wavelet-schemes-for-images
Repo
Framework

Spontaneous Facial Micro-Expression Recognition using Discriminative Spatiotemporal Local Binary Pattern with an Improved Integral Projection


Title	Spontaneous Facial Micro-Expression Recognition using Discriminative Spatiotemporal Local Binary Pattern with an Improved Integral Projection
Authors	Xiaohua Huang, Sujing Wang, Xin Liu, Guoying Zhao, Xiaoyi Feng, Matti Pietikainen
Abstract	Recently, there are increasing interests in inferring mirco-expression from facial image sequences. Due to subtle facial movement of micro-expressions, feature extraction has become an important and critical issue for spontaneous facial micro-expression recognition. Recent works usually used spatiotemporal local binary pattern for micro-expression analysis. However, the commonly used spatiotemporal local binary pattern considers dynamic texture information to represent face images while misses the shape attribute of face images. On the other hand, their works extracted the spatiotemporal features from the global face regions, which ignore the discriminative information between two micro-expression classes. The above-mentioned problems seriously limit the application of spatiotemporal local binary pattern on micro-expression recognition. In this paper, we propose a discriminative spatiotemporal local binary pattern based on an improved integral projection to resolve the problems of spatiotemporal local binary pattern for micro-expression recognition. Firstly, we develop an improved integral projection for preserving the shape attribute of micro-expressions. Furthermore, an improved integral projection is incorporated with local binary pattern operators across spatial and temporal domains. Specifically, we extract the novel spatiotemporal features incorporating shape attributes into spatiotemporal texture features. For increasing the discrimination of micro-expressions, we propose a new feature selection based on Laplacian method to extract the discriminative information for facial micro-expression recognition. Intensive experiments are conducted on three availably published micro-expression databases. We compare our method with the state-of-the-art algorithms. Experimental results demonstrate that our proposed method achieves promising performance for micro-expression recognition.
Tasks	Feature Selection
Published	2016-08-07
URL	http://arxiv.org/abs/1608.02255v1
PDF	http://arxiv.org/pdf/1608.02255v1.pdf
PWC	https://paperswithcode.com/paper/spontaneous-facial-micro-expression
Repo
Framework

A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine


Title	A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine
Authors	Xiaohang Ren, Kai Chen, Jun Sun
Abstract	Scene text recognition plays an important role in many computer vision applications. The small size of available public available scene text datasets is the main challenge when training a text recognition CNN model. In this paper, we propose a CNN based Chinese text recognition algorithm. To enlarge the dataset for training the CNN model, we design a synthetic data engine for Chinese scene character generation, which generates representative character images according to the fonts use frequency of Chinese texts. As the Chinese text is more complex, the English text recognition CNN architecture is modified for Chinese text. To ensure the small size nature character dataset and the large size artificial character dataset are comparable in training, the CNN model are trained progressively. The proposed Chinese text recognition algorithm is evaluated with two Chinese text datasets. The algorithm achieves better recognize accuracy compared to the baseline methods.
Tasks	Scene Text Recognition
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01891v1
PDF	http://arxiv.org/pdf/1604.01891v1.pdf
PWC	https://paperswithcode.com/paper/a-cnn-based-scene-chinese-text-recognition
Repo
Framework

On Randomized Distributed Coordinate Descent with Quantized Updates


Title	On Randomized Distributed Coordinate Descent with Quantized Updates
Authors	Mostafa El Gamal, Lifeng Lai
Abstract	In this paper, we study the randomized distributed coordinate descent algorithm with quantized updates. In the literature, the iteration complexity of the randomized distributed coordinate descent algorithm has been characterized under the assumption that machines can exchange updates with an infinite precision. We consider a practical scenario in which the messages exchange occurs over channels with finite capacity, and hence the updates have to be quantized. We derive sufficient conditions on the quantization error such that the algorithm with quantized update still converge. We further verify our theoretical results by running an experiment, where we apply the algorithm with quantized updates to solve a linear regression problem.
Tasks	Quantization
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05539v2
PDF	http://arxiv.org/pdf/1609.05539v2.pdf
PWC	https://paperswithcode.com/paper/on-randomized-distributed-coordinate-descent
Repo
Framework

User Dependent Features in Online Signature Verification


Title	User Dependent Features in Online Signature Verification
Authors	D. S. Guru, K. S. Manjunatha, S. Manjunath
Abstract	In this paper, we propose a novel approach for verification of on-line signatures based on user dependent feature selection and symbolic representation. Unlike other signature verification methods, which work with same features for all users, the proposed approach introduces the concept of user dependent features. It exploits the typicality of each and every user to select different features for different users. Initially all possible features are extracted for all users and a method of feature selection is employed for selecting user dependent features. The selected features are clustered using Fuzzy C means algorithm. In order to preserve the intra-class variation within each user, we recommend to represent each cluster in the form of an interval valued symbolic feature vector. A method of signature verification based on the proposed cluster based symbolic representation is also presented. Extensive experimentations are conducted on MCYT-100 User (DB1) and MCYT-330 User (DB2) online signature data sets to demonstrate the effectiveness of the proposed novel approach.
Tasks	Feature Selection
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10104v1
PDF	http://arxiv.org/pdf/1611.10104v1.pdf
PWC	https://paperswithcode.com/paper/user-dependent-features-in-online-signature
Repo
Framework