October 16, 2019

2627 words 13 mins read

Paper Group ANR 1132

Predicting Gross Movie Revenue. Generative Stock Question Answering. Blameworthiness in Strategic Games. Fully Convolutional Speech Recognition. Improved EEG Event Classification Using Differential Energy. Autoencoders for Multi-Label Prostate MR Segmentation. Tubule segmentation of fluorescence microscopy images based on convolutional neural netwo …

Predicting Gross Movie Revenue


Title	Predicting Gross Movie Revenue
Authors	Sharmistha Dey
Abstract	‘There is no terror in the bang, only is the anticipation of it’ - Alfred Hitchcock. Yet there is everything in correctly anticipating the bang a movie would make in the box-office. Movies make a high profile, billion dollar industry and prediction of movie revenue can be very lucrative. Predicted revenues can be used for planning both the production and distribution stages. For example, projected gross revenue can be used to plan the remuneration of the actors and crew members as well as other parts of the budget [1]. Success or failure of a movie can depend on many factors: star-power, release date, budget, MPAA (Motion Picture Association of America) rating, plot and the highly unpredictable human reactions. The enormity of the number of exogenous variables makes manual revenue prediction process extremely difficult. However, in the era of computer and data sciences, volumes of data can be efficiently processed and modelled. Hence the tough job of predicting gross revenue of a movie can be simplified with the help of modern computing power and the historical data available as movie databases [2].
Tasks
Published	2018-04-03
URL	http://arxiv.org/abs/1804.03565v1
PDF	http://arxiv.org/pdf/1804.03565v1.pdf
PWC	https://paperswithcode.com/paper/predicting-gross-movie-revenue
Repo
Framework

Generative Stock Question Answering


Title	Generative Stock Question Answering
Authors	Zhaopeng Tu, Yong Jiang, Xiaojiang Liu, Lei Shu, Shuming Shi
Abstract	We study the problem of stock related question answering (StockQA): automatically generating answers to stock related questions, just like professional stock analysts providing action recommendations to stocks upon user’s requests. StockQA is quite different from previous QA tasks since (1) the answers in StockQA are natural language sentences (rather than entities or values) and due to the dynamic nature of StockQA, it is scarcely possible to get reasonable answers in an extractive way from the training data; and (2) StockQA requires properly analyzing the relationship between keywords in QA pair and the numerical features of a stock. We propose to address the problem with a memory-augmented encoder-decoder architecture, and integrate different mechanisms of number understanding and generation, which is a critical component of StockQA. We build a large-scale dataset containing over 180K StockQA instances, based on which various technique combinations are extensively studied and compared. Experimental results show that a hybrid word-character model with separate character components for number processing, achieves the best performance. By analyzing the results, we found that 44.8% of answers generated by our best model still suffer from the generic answer problem, which can be alleviated by a straightforward hybrid retrieval-generation model.
Tasks	Question Answering
Published	2018-04-21
URL	http://arxiv.org/abs/1804.07942v2
PDF	http://arxiv.org/pdf/1804.07942v2.pdf
PWC	https://paperswithcode.com/paper/generative-stock-question-answering
Repo
Framework

Blameworthiness in Strategic Games


Title	Blameworthiness in Strategic Games
Authors	Pavel Naumov, Jia Tao
Abstract	There are multiple notions of coalitional responsibility. The focus of this paper is on the blameworthiness defined through the principle of alternative possibilities: a coalition is blamable for a statement if the statement is true, but the coalition had a strategy to prevent it. The main technical result is a sound and complete bimodal logical system that describes properties of blameworthiness in one-shot games.
Tasks
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05485v1
PDF	http://arxiv.org/pdf/1809.05485v1.pdf
PWC	https://paperswithcode.com/paper/blameworthiness-in-strategic-games
Repo
Framework

Fully Convolutional Speech Recognition


Title	Fully Convolutional Speech Recognition
Authors	Neil Zeghidour, Qiantong Xu, Vitaliy Liptchinsky, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert
Abstract	Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we present an alternative approach based solely on convolutional neural networks, leveraging recent advances in acoustic models from the raw waveform and language modeling. This fully convolutional approach is trained end-to-end to predict characters from the raw waveform, removing the feature extraction step altogether. An external convolutional language model is used to decode words. On Wall Street Journal, our model matches the current state-of-the-art. On Librispeech, we report state-of-the-art performance among end-to-end models, including Deep Speech 2 trained with 12 times more acoustic data and significantly more linguistic data.
Tasks	End-To-End Speech Recognition, Language Modelling, Speech Recognition
Published	2018-12-17
URL	http://arxiv.org/abs/1812.06864v2
PDF	http://arxiv.org/pdf/1812.06864v2.pdf
PWC	https://paperswithcode.com/paper/fully-convolutional-speech-recognition
Repo
Framework

Improved EEG Event Classification Using Differential Energy


Title	Improved EEG Event Classification Using Differential Energy
Authors	Amir Harati, Meysam Golmohammadi, Silvia Lopez, Iyad Obeid, Joseph Picone
Abstract	Feature extraction for automatic classification of EEG signals typically relies on time frequency representations of the signal. Techniques such as cepstral-based filter banks or wavelets are popular analysis techniques in many signal processing applications including EEG classification. In this paper, we present a comparison of a variety of approaches to estimating and postprocessing features. To further aid in discrimination of periodic signals from aperiodic signals, we add a differential energy term. We evaluate our approaches on the TUH EEG Corpus, which is the largest publicly available EEG corpus and an exceedingly challenging task due to the clinical nature of the data. We demonstrate that a variant of a standard filter bank-based approach, coupled with first and second derivatives, provides a substantial reduction in the overall error rate. The combination of differential energy and derivatives produces a 24% absolute reduction in the error rate and improves our ability to discriminate between signal events and background noise. This relatively simple approach proves to be comparable to other popular feature extraction approaches such as wavelets, but is much more computationally efficient.
Tasks	EEG
Published	2018-01-03
URL	http://arxiv.org/abs/1801.02477v1
PDF	http://arxiv.org/pdf/1801.02477v1.pdf
PWC	https://paperswithcode.com/paper/improved-eeg-event-classification-using
Repo
Framework

Autoencoders for Multi-Label Prostate MR Segmentation


Title	Autoencoders for Multi-Label Prostate MR Segmentation
Authors	Ard de Gelder, Henkjan Huisman
Abstract	Organ image segmentation can be improved by implementing prior knowledge about the anatomy. One way of doing this is by training an autoencoder to learn a lowdimensional representation of the segmentation. In this paper, this is applied in multi-label prostate MR segmentation, with some positive results.
Tasks	Semantic Segmentation
Published	2018-06-09
URL	http://arxiv.org/abs/1806.08216v2
PDF	http://arxiv.org/pdf/1806.08216v2.pdf
PWC	https://paperswithcode.com/paper/autoencoders-for-multi-label-prostate-mr
Repo
Framework

Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction


Title	Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction
Authors	Soonam Lee, Chichen Fu, Paul Salama, Kenneth W. Dunn, Edward J. Delp
Abstract	Fluorescence microscopy has become a widely used tool for studying various biological structures of in vivo tissue or cells. However, quantitative analysis of these biological structures remains a challenge due to their complexity which is exacerbated by distortions caused by lens aberrations and light scattering. Moreover, manual quantification of such image volumes is an intractable and error-prone process, making the need for automated image analysis methods crucial. This paper describes a segmentation method for tubular structures in fluorescence microscopy images using convolutional neural networks with data augmentation and inhomogeneity correction. The segmentation results of the proposed method are visually and numerically compared with other microscopy segmentation methods. Experimental results indicate that the proposed method has better performance with correctly segmenting and identifying multiple tubular structures compared to other methods.
Tasks	Data Augmentation
Published	2018-02-10
URL	http://arxiv.org/abs/1802.03542v1
PDF	http://arxiv.org/pdf/1802.03542v1.pdf
PWC	https://paperswithcode.com/paper/tubule-segmentation-of-fluorescence
Repo
Framework

Towards Large-Scale Exploratory Search over Heterogeneous Sources


Title	Towards Large-Scale Exploratory Search over Heterogeneous Sources
Authors	Mariia Seleznova, Anton Belyy, Aleksei Sholokhov
Abstract	Since time immemorial, people have been looking for ways to organize scientific knowledge into some systems to facilitate search and discovery of new ideas. The problem was partially solved in the pre-Internet era using library classifications, but nowadays it is nearly impossible to classify all scientific and popular scientific knowledge manually. There is a clear gap between the diversity and the amount of data available on the Internet and the algorithms for automatic structuring of such data. In our preliminary study, we approach the problem of knowledge discovery on web-scale data with diverse text sources and propose an algorithm to aggregate multiple collections into a single hierarchical topic model. We implement a web service named Rysearch to demonstrate the concept of topical exploratory search and make it available online.
Tasks
Published	2018-11-15
URL	http://arxiv.org/abs/1811.07042v2
PDF	http://arxiv.org/pdf/1811.07042v2.pdf
PWC	https://paperswithcode.com/paper/towards-large-scale-exploratory-search-over
Repo
Framework

Weakly Supervised Scene Parsing with Point-based Distance Metric Learning


Title	Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Authors	Rui Qian, Yunchao Wei, Honghui Shi, Jiachen Li, Jiaying Liu, Thomas Huang
Abstract	Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and inter-category points to keep consistent, i.e. points within the same category should have more similar feature representations compared to those from different categories. We formulate such a characteristic into a simple distance metric loss, which collaborates with the point-wise cross-entropy loss to optimize the deep neural networks. Furthermore, to fully exploit the limited annotations, distance metric learning is conducted across different training images instead of simply adopting an image-dependent manner. We conduct extensive experiments on two challenging scene parsing benchmarks of PASCAL-Context and ADE 20K to validate the effectiveness of our PDML, and competitive mIoU scores are achieved.
Tasks	Metric Learning, Scene Parsing
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02233v1
PDF	http://arxiv.org/pdf/1811.02233v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-scene-parsing-with-point
Repo
Framework

Accelerated Training for Massive Classification via Dynamic Class Selection


Title	Accelerated Training for Massive Classification via Dynamic Class Selection
Authors	Xingcheng Zhang, Lei Yang, Junjie Yan, Dahua Lin
Abstract	Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e.g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately identify a small number of “active classes” for each mini-batch, based on a set of dynamic class hierarchies constructed on the fly. We also develop an adaptive allocation scheme thereon, which leads to a better tradeoff between performance and cost. On several large-scale benchmarks, our method significantly reduces the training cost and memory demand, while maintaining competitive performance.
Tasks	Face Recognition
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01687v1
PDF	http://arxiv.org/pdf/1801.01687v1.pdf
PWC	https://paperswithcode.com/paper/accelerated-training-for-massive
Repo
Framework

Dermoscopic Image Analysis for ISIC Challenge 2018


Title	Dermoscopic Image Analysis for ISIC Challenge 2018
Authors	Jinyi Zou, Xiao Ma, Cheng Zhong, Yao Zhang
Abstract	This short paper reports the algorithms we used and the evaluation performances for ISIC Challenge 2018. Our team participates in all the tasks in this challenge. In lesion segmentation task, the pyramid scene parsing network (PSPNet) is modified to segment the lesions. In lesion attribute detection task, the modified PSPNet is also adopted in a multi-label way. In disease classification task, the DenseNet-169 is adopted for multi-class classification.
Tasks	Lesion Segmentation, Scene Parsing
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08948v1
PDF	http://arxiv.org/pdf/1807.08948v1.pdf
PWC	https://paperswithcode.com/paper/dermoscopic-image-analysis-for-isic-challenge
Repo
Framework

Pressure Predictions of Turbine Blades with Deep Learning


Title	Pressure Predictions of Turbine Blades with Deep Learning
Authors	Cheng’an Bai, Chao Zhou
Abstract	Deep learning has been used in many areas, such as feature detections in images and the game of go. This paper presents a study that attempts to use the deep learning method to predict turbomachinery performance. Three different deep neural networks are built and trained to predict the pressure distributions of turbine airfoils. The performance of a library of turbine airfoils were firstly predicted using methods based on Euler equations, which were then used to train and validate the deep learning neural networks. The results show that network with four layers of convolutional neural network and two layers of fully connected neural network provides the best predictions. For the best neural network architecture, the pressure prediction on more than 99% locations are better than 3% and 90% locations are better than 1%.
Tasks	Game of Go
Published	2018-06-12
URL	http://arxiv.org/abs/1806.06940v1
PDF	http://arxiv.org/pdf/1806.06940v1.pdf
PWC	https://paperswithcode.com/paper/pressure-predictions-of-turbine-blades-with
Repo
Framework

MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge


Title	MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
Authors	Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater, Manfred Pinkal
Abstract	We introduce a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge. Our dataset complements similar datasets in that we focus on stories about everyday activities, such as going to the movies or working in the garden, and that the questions require commonsense knowledge, or more specifically, script knowledge, to be answered. We show that our mode of data collection via crowdsourcing results in a substantial amount of such inference questions. The dataset forms the basis of a shared task on commonsense and script knowledge organized at SemEval 2018 and provides challenging test cases for the broader natural language understanding community.
Tasks	Reading Comprehension
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05223v1
PDF	http://arxiv.org/pdf/1803.05223v1.pdf
PWC	https://paperswithcode.com/paper/mcscript-a-novel-dataset-for-assessing
Repo
Framework

City-Scale Road Audit System using Deep Learning


Title	City-Scale Road Audit System using Deep Learning
Authors	Sudhir Yarram, Girish Varma, C. V. Jawahar
Abstract	Road networks in cities are massive and is a critical component of mobility. Fast response to defects, that can occur not only due to regular wear and tear but also because of extreme events like storms, is essential. Hence there is a need for an automated system that is quick, scalable and cost-effective for gathering information about defects. We propose a system for city-scale road audit, using some of the most recent developments in deep learning and semantic segmentation. For building and benchmarking the system, we curated a dataset which has annotations required for road defects. However, many of the labels required for road audit have high ambiguity which we overcome by proposing a label hierarchy. We also propose a multi-step deep learning model that segments the road, subdivide the road further into defects, tags the frame for each defect and finally localizes the defects on a map gathered using GPS. We analyze and evaluate the models on image tagging as well as segmentation at different levels of the label hierarchy.
Tasks	Semantic Segmentation
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10210v1
PDF	http://arxiv.org/pdf/1811.10210v1.pdf
PWC	https://paperswithcode.com/paper/city-scale-road-audit-system-using-deep
Repo
Framework

A Modern Take on the Bias-Variance Tradeoff in Neural Networks


Title	A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Authors	Brady Neal, Sarthak Mittal, Aristide Baratin, Vinayak Tantia, Matthew Scicluna, Simon Lacoste-Julien, Ioannis Mitliagkas
Abstract	The bias-variance tradeoff tells us that as model complexity increases, bias falls and variances increases, leading to a U-shaped test error curve. However, recent empirical results with over-parameterized neural networks are marked by a striking absence of the classic U-shaped test error curve: test error keeps decreasing in wider networks. This suggests that there might not be a bias-variance tradeoff in neural networks with respect to network width, unlike was originally claimed by, e.g., Geman et al. (1992). Motivated by the shaky evidence used to support this claim in neural networks, we measure bias and variance in the modern setting. We find that both bias and variance can decrease as the number of parameters grows. To better understand this, we introduce a new decomposition of the variance to disentangle the effects of optimization and data sampling. We also provide theoretical analysis in a simplified setting that is consistent with our empirical findings.
Tasks
Published	2018-10-19
URL	https://arxiv.org/abs/1810.08591v4
PDF	https://arxiv.org/pdf/1810.08591v4.pdf
PWC	https://paperswithcode.com/paper/a-modern-take-on-the-bias-variance-tradeoff
Repo
Framework