July 27, 2019

2987 words 15 mins read

Paper Group ANR 601

Fast Top-k Area Topics Extraction with Knowledge Base. Integrating semi-supervised label propagation and random forests for multi-atlas based hippocampus segmentation. One for All: Towards Language Independent Named Entity Linking. Speckle Reduction with Trained Nonlinear Diffusion Filtering. Camera-trap images segmentation using multi-layer robust …

Fast Top-k Area Topics Extraction with Knowledge Base


Title	Fast Top-k Area Topics Extraction with Knowledge Base
Authors	Fang Zhang, Xiaochen Wang, Jingfei Han, Jie Tang, Shiyin Wang, Marie-Francine Moens
Abstract	What are the most popular research topics in Artificial Intelligence (AI)? We formulate the problem as extracting top-$k$ topics that can best represent a given area with the help of knowledge base. We theoretically prove that the problem is NP-hard and propose an optimization model, FastKATE, to address this problem by combining both explicit and latent representations for each topic. We leverage a large-scale knowledge base (Wikipedia) to generate topic embeddings using neural networks and use this kind of representations to help capture the representativeness of topics for given areas. We develop a fast heuristic algorithm to efficiently solve the problem with a provable error bound. We evaluate the proposed model on three real-world datasets. Experimental results demonstrate our model’s effectiveness, robustness, real-timeness (return results in $<1$s), and its superiority over several alternative methods.
Tasks
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04822v2
PDF	http://arxiv.org/pdf/1710.04822v2.pdf
PWC	https://paperswithcode.com/paper/fast-top-k-area-topics-extraction-with
Repo
Framework

Integrating semi-supervised label propagation and random forests for multi-atlas based hippocampus segmentation


Title	Integrating semi-supervised label propagation and random forests for multi-atlas based hippocampus segmentation
Authors	Qiang Zheng, Yong Fan
Abstract	A novel multi-atlas based image segmentation method is proposed by integrating a semi-supervised label propagation method and a supervised random forests method in a pattern recognition based label fusion framework. The semi-supervised label propagation method takes into consideration local and global image appearance of images to be segmented and segments the images by propagating reliable segmentation results obtained by the supervised random forests method. Particularly, the random forests method is used to train a regression model based on image patches of atlas images for each voxel of the images to be segmented. The regression model is used to obtain reliable segmentation results to guide the label propagation for the segmentation. The proposed method has been compared with state-of-the-art multi-atlas based image segmentation methods for segmenting the hippocampus in MR images. The experiment results have demonstrated that our method obtained superior segmentation performance.
Tasks	Semantic Segmentation
Published	2017-12-31
URL	http://arxiv.org/abs/1801.00223v1
PDF	http://arxiv.org/pdf/1801.00223v1.pdf
PWC	https://paperswithcode.com/paper/integrating-semi-supervised-label-propagation
Repo
Framework

One for All: Towards Language Independent Named Entity Linking


Title	One for All: Towards Language Independent Named Entity Linking
Authors	Avirup Sil, Radu Florian
Abstract	Entity linking (EL) is the task of disambiguating mentions in text by associating them with entries in a predefined database of mentions (persons, organizations, etc). Most previous EL research has focused mainly on one language, English, with less attention being paid to other languages, such as Spanish or Chinese. In this paper, we introduce LIEL, a Language Independent Entity Linking system, which provides an EL framework which, once trained on one language, works remarkably well on a number of different languages without change. LIEL makes a joint global prediction over the entire document, employing a discriminative reranking framework with many domain and language-independent feature functions. Experiments on numerous benchmark datasets, show that the proposed system, once trained on one language, English, outperforms several state-of-the-art systems in English (by 4 points) and the trained model also works very well on Spanish (14 points better than a competitor system), demonstrating the viability of the approach.
Tasks	Entity Linking
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01797v1
PDF	http://arxiv.org/pdf/1712.01797v1.pdf
PWC	https://paperswithcode.com/paper/one-for-all-towards-language-independent
Repo
Framework

Speckle Reduction with Trained Nonlinear Diffusion Filtering


Title	Speckle Reduction with Trained Nonlinear Diffusion Filtering
Authors	Wensen Feng, Yunjin Chen
Abstract	Speckle reduction is a prerequisite for many image processing tasks in synthetic aperture radar (SAR) images, as well as all coherent images. In recent years, predominant state-of-the-art approaches for despeckling are usually based on nonlocal methods which mainly concentrate on achieving utmost image restoration quality, with relatively low computational efficiency. Therefore, in this study we aim to propose an efficient despeckling model with both high computational efficiency and high recovery quality. To this end, we exploit a newly-developed trainable nonlinear reaction diffusion(TNRD) framework which has proven a simple and effective model for various image restoration problems. {In the original TNRD applications, the diffusion network is usually derived based on the direct gradient descent scheme. However, this approach will encounter some problem for the task of multiplicative noise reduction exploited in this study. To solve this problem, we employed a new architecture derived from the proximal gradient descent method.} {Taking into account the speckle noise statistics, the diffusion process for the despeckling task is derived. We then retrain all the model parameters in the presence of speckle noise. Finally, optimized nonlinear diffusion filtering models are obtained, which are specialized for despeckling with various noise levels. Experimental results substantiate that the trained filtering models provide comparable or even better results than state-of-the-art nonlocal approaches. Meanwhile, our proposed model merely contains convolution of linear filters with an image, which offers high level parallelism on GPUs. As a consequence, for images of size $512 \times 512$, our GPU implementation takes less than 0.1 seconds to produce state-of-the-art despeckling performance.}
Tasks	Image Restoration
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07482v1
PDF	http://arxiv.org/pdf/1702.07482v1.pdf
PWC	https://paperswithcode.com/paper/speckle-reduction-with-trained-nonlinear
Repo
Framework

Camera-trap images segmentation using multi-layer robust principal component analysis


Title	Camera-trap images segmentation using multi-layer robust principal component analysis
Authors	Jhony-Heriberto Giraldo-Zuluaga, Alexander Gomez, Augusto Salazar, Angélica Diaz-Pulido
Abstract	The segmentation of animals from camera-trap images is a difficult task. To illustrate, there are various challenges due to environmental conditions and hardware limitation in these images. We proposed a multi-layer robust principal component analysis (multi-layer RPCA) approach for background subtraction. Our method computes sparse and low-rank images from a weighted sum of descriptors, using color and texture features as case of study for camera-trap images segmentation. The segmentation algorithm is composed of histogram equalization or Gaussian filtering as pre-processing, and morphological filters with active contour as post-processing. The parameters of our multi-layer RPCA were optimized with an exhaustive search. The database consists of camera-trap images from the Colombian forest taken by the Instituto de Investigaci'on de Recursos Biol'ogicos Alexander von Humboldt. We analyzed the performance of our method in inherent and therefore challenging situations of camera-trap images. Furthermore, we compared our method with some state-of-the-art algorithms of background subtraction, where our multi-layer RPCA outperformed these other methods. Our multi-layer RPCA reached 76.17 and 69.97% of average fine-grained F-measure for color and infrared sequences, respectively. To our best knowledge, this paper is the first work proposing multi-layer RPCA and using it for camera-trap images segmentation.
Tasks
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08180v2
PDF	http://arxiv.org/pdf/1701.08180v2.pdf
PWC	https://paperswithcode.com/paper/camera-trap-images-segmentation-using-multi
Repo
Framework

Multi-task learning of time series and its application to the travel demand


Title	Multi-task learning of time series and its application to the travel demand
Authors	Boris Chidlovskii
Abstract	We address the problem of modeling and prediction of a set of temporal events in the context of intelligent transportation systems. To leverage the information shared by different events, we propose a multi-task learning framework. We develop a support vector regression model for joint learning of mutually dependent time series. It is the regularization-based multi-task learning previously developed for the classification case and extended to time series. We discuss the relatedness of observed time series and first deploy the dynamic time warping distance measure to identify groups of similar series. Then we take into account both time and scale warping and propose to align multiple time series by inferring their common latent representation. We test the proposed models on the problem of travel demand prediction in Nancy (France) public transport system and analyze the benefits of multi-task learning.
Tasks	Multi-Task Learning, Time Series
Published	2017-12-21
URL	http://arxiv.org/abs/1712.08164v1
PDF	http://arxiv.org/pdf/1712.08164v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-of-time-series-and-its
Repo
Framework

On the exact relationship between the denoising function and the data distribution


Title	On the exact relationship between the denoising function and the data distribution
Authors	Heikki Arponen, Matti Herranen, Harri Valpola
Abstract	We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the structure of data allowing it to be exploited in the unsupervised learning of representations. This result generalizes a known relationship [2], which is valid only in the limit of small corruption noise.
Tasks	Denoising
Published	2017-09-06
URL	http://arxiv.org/abs/1709.02797v1
PDF	http://arxiv.org/pdf/1709.02797v1.pdf
PWC	https://paperswithcode.com/paper/on-the-exact-relationship-between-the
Repo
Framework

TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation


Title	TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation
Authors	Stefano Alletto, Davide Abati, Simone Calderara, Rita Cucchiara, Luca Rigazio
Abstract	We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in two stages. First, a dense pixel-level flow is computed with a geometric prior imposing strong spatial constraints. Such prior is typical of driving scenes, where the point of view is coherent with the vehicle motion. We show how such global transformation can be approximated with an homography and how spatial transformer layers can be employed to compute the flow field implied by such transformation. The second stage then refines the prediction feeding a second deeper network. A final reconstruction loss compares the warping of frame X(t) with the subsequent frame X(t+1) and guides both estimates. The model, which we named TransFlow, performs favorably compared to other unsupervised algorithms, and shows better generalization compared to supervised methods with a 3x reduction in error on unseen data.
Tasks	Optical Flow Estimation
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00322v3
PDF	http://arxiv.org/pdf/1706.00322v3.pdf
PWC	https://paperswithcode.com/paper/transflow-unsupervised-motion-flow-by-joint
Repo
Framework

A Comparative Study for Predicting Heart Diseases Using Data Mining Classification Methods


Title	A Comparative Study for Predicting Heart Diseases Using Data Mining Classification Methods
Authors	Israa Ahmed Zriqat, Ahmad Mousa Altamimi, Mohammad Azzeh
Abstract	Improving the precision of heart diseases detection has been investigated by many researchers in the literature. Such improvement induced by the overwhelming health care expenditures and erroneous diagnosis. As a result, various methodologies have been proposed to analyze the disease factors aiming to decrease the physicians practice variation and reduce medical costs and errors. In this paper, our main motivation is to develop an effective intelligent medical decision support system based on data mining techniques. In this context, five data mining classifying algorithms, with large datasets, have been utilized to assess and analyze the risk factors statistically related to heart diseases in order to compare the performance of the implemented classifiers (e.g., Na"ive Bayes, Decision Tree, Discriminant, Random Forest, and Support Vector Machine). To underscore the practical viability of our approach, the selected classifiers have been implemented using MATLAB tool with two datasets. Results of the conducted experiments showed that all classification algorithms are predictive and can give relatively correct answer. However, the decision tree outperforms other classifiers with an accuracy rate of 99.0% followed by Random forest. That is the case because both of them have relatively same mechanism but the Random forest can build ensemble of decision tree. Although ensemble learning has been proved to produce superior results, but in our case the decision tree has outperformed its ensemble version.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02799v1
PDF	http://arxiv.org/pdf/1704.02799v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-for-predicting-heart
Repo
Framework

Lung Nodule Classification by the Combination of Fusion Classifier and Cascaded Convolutional Neural Networks


Title	Lung Nodule Classification by the Combination of Fusion Classifier and Cascaded Convolutional Neural Networks
Authors	Masaharu Sakamoto, Hiroki Nakano, Kun Zhao, Taro Sekiyama
Abstract	Lung nodule classification is a class imbalanced problem, as nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We showed that cascaded convolutional neural networks can classify the nodule candidates precisely for a class imbalanced nodule candidate data set in our previous study. In this paper, we propose Fusion classifier in conjunction with the cascaded convolutional neural network models. To fuse the models, nodule probabilities are calculated by using the convolutional neural network models at first. Then, Fusion classifier is trained and tested by the nodule probabilities. The proposed method achieved the sensitivity of 94.4% and 95.9% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, respectively.
Tasks	Lung Nodule Classification
Published	2017-11-19
URL	http://arxiv.org/abs/1712.02198v2
PDF	http://arxiv.org/pdf/1712.02198v2.pdf
PWC	https://paperswithcode.com/paper/lung-nodule-classification-by-the-combination
Repo
Framework

Cross-genre Document Retrieval: Matching between Conversational and Formal Writings


Title	Cross-genre Document Retrieval: Matching between Conversational and Formal Writings
Authors	Tomasz Jurczyk, Jinho D. Choi
Abstract	This paper challenges a cross-genre document retrieval task, where the queries are in formal writing and the target documents are in conversational writing. In this task, a query, is a sentence extracted from either a summary or a plot of an episode in a TV show, and the target document consists of transcripts from the corresponding episode. To establish a strong baseline, we employ the current state-of-the-art search engine to perform document retrieval on the dataset collected for this work. We then introduce a structure reranking approach to improve the initial ranking by utilizing syntactic and semantic structures generated by NLP tools. Our evaluation shows an improvement of more than 4% when the structure reranking is applied, which is very promising.
Tasks
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04538v1
PDF	http://arxiv.org/pdf/1707.04538v1.pdf
PWC	https://paperswithcode.com/paper/cross-genre-document-retrieval-matching
Repo
Framework

A Planning Approach to Monitoring Behavior of Computer Programs


Title	A Planning Approach to Monitoring Behavior of Computer Programs
Authors	Alexandre Cukier, Ronen I. Brafman, Yotam Perkal, David Tolpin
Abstract	We describe a novel approach to monitoring high level behaviors using concepts from AI planning. Our goal is to understand what a program is doing based on its system call trace. This ability is particularly important for detecting malware. We approach this problem by building an abstract model of the operating system using the STRIPS planning language, casting system calls as planning operators. Given a system call trace, we simulate the corresponding operators on our model and by observing the properties of the state reached, we learn about the nature of the original program and its behavior. Thus, unlike most statistical detection methods that focus on syntactic features, our approach is semantic in nature. Therefore, it is more robust against obfuscation techniques used by malware that change the outward appearance of the trace but not its effect. We demonstrate the efficacy of our approach by evaluating it on actual system call traces.
Tasks
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03363v1
PDF	http://arxiv.org/pdf/1709.03363v1.pdf
PWC	https://paperswithcode.com/paper/a-planning-approach-to-monitoring-behavior-of
Repo
Framework

Linear regression without correspondence


Title	Linear regression without correspondence
Authors	Daniel Hsu, Kevin Shi, Xiaorui Sun
Abstract	This article considers algorithmic and statistical aspects of linear regression when the correspondence between the covariates and the responses is unknown. First, a fully polynomial-time approximation scheme is given for the natural least squares optimization problem in any constant dimension. Next, in an average-case and noise-free setting where the responses exactly correspond to a linear function of i.i.d. draws from a standard multivariate normal distribution, an efficient algorithm based on lattice basis reduction is shown to exactly recover the unknown linear function in arbitrary dimension. Finally, lower bounds on the signal-to-noise ratio are established for approximate recovery of the unknown linear function by any estimator.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07048v2
PDF	http://arxiv.org/pdf/1705.07048v2.pdf
PWC	https://paperswithcode.com/paper/linear-regression-without-correspondence
Repo
Framework

Large-scale Multiview 3D Hand Pose Dataset


Title	Large-scale Multiview 3D Hand Pose Dataset
Authors	Francisco Gomez-Donoso, Sergio Orts-Escolano, Miguel Cazorla
Abstract	Accurate hand pose estimation at joint level has several uses on human-robot interaction, user interfacing and virtual reality applications. Yet, it currently is not a solved problem. The novel deep learning techniques could make a great improvement on this matter but they need a huge amount of annotated data. The hand pose datasets released so far present some issues that make them impossible to use on deep learning methods such as the few number of samples, high-level abstraction annotations or samples consisting in depth maps. In this work, we introduce a multiview hand pose dataset in which we provide color images of hands and different kind of annotations for each, i.e the bounding box and the 2D and 3D location on the joints in the hand. Besides, we introduce a simple yet accurate deep learning architecture for real-time robust 2D hand pose estimation.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03742v3
PDF	http://arxiv.org/pdf/1707.03742v3.pdf
PWC	https://paperswithcode.com/paper/large-scale-multiview-3d-hand-pose-dataset
Repo
Framework

Son of Zorn’s Lemma: Targeted Style Transfer Using Instance-aware Semantic Segmentation


Title	Son of Zorn’s Lemma: Targeted Style Transfer Using Instance-aware Semantic Segmentation
Authors	Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, Tom Goldstein
Abstract	Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only one particular object in a target image without altering the object’s general morphology or surroundings. This is useful, for example, in augmented reality applications (such as the recently released Pokemon GO), where one wants to alter the appearance of a single real-world object in an image frame to make it appear as a cartoon. Most notably, the rendering of real-world objects into cartoon characters has been used in a number of films and television show, such as the upcoming series Son of Zorn. We present a method for targeted style transfer that simultaneously segments and stylizes single objects selected by the user. The method uses a Markov random field model to smooth and anti-alias outlier pixels near object boundaries, so that stylized objects naturally blend into their surroundings.
Tasks	Semantic Segmentation, Style Transfer
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02357v1
PDF	http://arxiv.org/pdf/1701.02357v1.pdf
PWC	https://paperswithcode.com/paper/son-of-zorns-lemma-targeted-style-transfer
Repo
Framework