July 26, 2019

2896 words 14 mins read

Paper Group ANR 773

Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet. Decoding Epileptogenesis in a Reduced State Space. A natural approach to studying schema processing. Split and Rephrase. Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection. Adversarial Attacks Beyon …

Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet


Title	Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet
Authors	Vahid Moosavi
Abstract	Study of urban form is an important area of research in urban planning/design that contributes to our understanding of how cities function and evolve. However, classical approaches are based on very limited observations and inconsistent methods. As an alternative, availability of massive urban data collections such as Open Street Map from the one hand and the recent advancements in machine learning methods such as deep learning techniques on the other have opened up new possibilities to automatically investigate urban forms at the global scale. In this work for the first time, by collecting a large data set of street networks in more than one million cities, towns and villages all over the world, we trained a deep convolutional auto-encoder, that automatically learns the hierarchical structures of urban forms and represents them via dense and comparable vectors. We showed how the learned urban vectors could be used for different investigations. Using the learned urban vectors, one is able to easily find and compare similar urban forms all over the world, considering their overall spatial structure and other factors such as orientation, graphical structure, and density and partial deformations. Further cluster analysis reveals the distribution of the main patterns of urban forms all over the planet.
Tasks
Published	2017-09-09
URL	http://arxiv.org/abs/1709.02939v2
PDF	http://arxiv.org/pdf/1709.02939v2.pdf
PWC	https://paperswithcode.com/paper/urban-morphology-meets-deep-learning
Repo
Framework

Decoding Epileptogenesis in a Reduced State Space


Title	Decoding Epileptogenesis in a Reduced State Space
Authors	François G. Meyer, Alexander M. Benison, Zachariah Smith, Daniel S. Barth
Abstract	We describe here the recent results of a multidisciplinary effort to design a biomarker that can actively and continuously decode the progressive changes in neuronal organization leading to epilepsy, a process known as epileptogenesis. Using an animal model of acquired epilepsy, wechronically record hippocampal evoked potentials elicited by an auditory stimulus. Using a set of reduced coordinates, our algorithm can identify universal smooth low-dimensional configurations of the auditory evoked potentials that correspond to distinct stages of epileptogenesis. We use a hidden Markov model to learn the dynamics of the evoked potential, as it evolves along these smooth low-dimensional subsets. We provide experimental evidence that the biomarker is able to exploit subtle changes in the evoked potential to reliably decode the stage of epileptogenesis and predict whether an animal will eventually recover from the injury, or develop spontaneous seizures.
Tasks
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07243v1
PDF	http://arxiv.org/pdf/1701.07243v1.pdf
PWC	https://paperswithcode.com/paper/decoding-epileptogenesis-in-a-reduced-state
Repo
Framework

A natural approach to studying schema processing


Title	A natural approach to studying schema processing
Authors	Jack McKay Fletcher, Thomas Wennekers
Abstract	The Building Block Hypothesis (BBH) states that adaptive systems combine good partial solutions (so-called building blocks) to find increasingly better solutions. It is thought that Genetic Algorithms (GAs) implement the BBH. However, for GAs building blocks are semi-theoretical objects in that they are thought only to be implicitly exploited via the selection and crossover operations of a GA. In the current work, we discover a mathematical method to identify the complete set of schemata present in a given population of a GA; as such a natural way to study schema processing (and thus the BBH) is revealed. We demonstrate how this approach can be used both theoretically and experimentally. Theoretically, we show that the search space for good schemata is a complete lattice and that each generation samples a complete sub-lattice of this search space. In addition, we show that combining schemata can only explore a subset of the search space. Experimentally, we compare how well different crossover methods combine building blocks. We find that for most crossover methods approximately 25-35% of building blocks in a generation result from the combination of the previous generation’s building blocks. We also find that an increase in the combination of building blocks does not lead to an increase in the efficiency of a GA. To complement this article, we introduce an open source Python package called schematax, which allows one to calculate the schemata present in a population using the methods described in this article.
Tasks
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04536v1
PDF	http://arxiv.org/pdf/1705.04536v1.pdf
PWC	https://paperswithcode.com/paper/a-natural-approach-to-studying-schema
Repo
Framework

Split and Rephrase


Title	Split and Rephrase
Authors	Shashi Narayan, Claire Gardent, Shay B. Cohen, Anastasia Shimorina
Abstract	We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences. Like sentence simplification, splitting-and-rephrasing has the potential of benefiting both natural language processing and societal applications. Because shorter sentences are generally better processed by NLP systems, it could be used as a preprocessing step which facilitates and improves the performance of parsers, semantic role labellers and machine translation systems. It should also be of use for people with reading disabilities because it allows the conversion of longer sentences into shorter ones. This paper makes two contributions towards this new task. First, we create and make available a benchmark consisting of 1,066,115 tuples mapping a single complex sentence to a sequence of sentences expressing the same meaning. Second, we propose five models (vanilla sequence-to-sequence to semantically-motivated models) to understand the difficulty of the proposed task.
Tasks	Machine Translation
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06971v1
PDF	http://arxiv.org/pdf/1707.06971v1.pdf
PWC	https://paperswithcode.com/paper/split-and-rephrase
Repo
Framework

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection


Title	Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
Authors	Mohammadamin Barekatain, Miquel Martí, Hsueh-Fu Shih, Samuel Murray, Kotaro Nakayama, Yutaka Matsuo, Helmut Prendinger
Abstract	Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.
Tasks	Action Detection
Published	2017-06-09
URL	http://arxiv.org/abs/1706.03038v2
PDF	http://arxiv.org/pdf/1706.03038v2.pdf
PWC	https://paperswithcode.com/paper/okutama-action-an-aerial-view-video-dataset
Repo
Framework

Adversarial Attacks Beyond the Image Space


Title	Adversarial Attacks Beyond the Image Space
Authors	Xiaohui Zeng, Chenxi Liu, Yu-Siang Wang, Weichao Qiu, Lingxi Xie, Yu-Wing Tai, Chi Keung Tang, Alan L. Yuille
Abstract	Generating adversarial examples is an intriguing problem and an important way of understanding the working mechanism of deep neural networks. Most existing approaches generated perturbations in the image space, i.e., each pixel can be modified independently. However, in this paper we pay special attention to the subset of adversarial examples that correspond to meaningful changes in 3D physical properties (like rotation and translation, illumination condition, etc.). These adversaries arguably pose a more serious concern, as they demonstrate the possibility of causing neural network failure by easy perturbations of real-world 3D objects and scenes. In the contexts of object classification and visual question answering, we augment state-of-the-art deep neural networks that receive 2D input images with a rendering module (either differentiable or not) in front, so that a 3D scene (in the physical space) is rendered into a 2D image (in the image space), and then mapped to a prediction (in the output space). The adversarial perturbations can now go beyond the image space, and have clear meanings in the 3D physical world. Though image-space adversaries can be interpreted as per-pixel albedo change, we verify that they cannot be well explained along these physically meaningful dimensions, which often have a non-local effect. But it is still possible to successfully attack beyond the image space on the physical space, though this is more difficult than image-space attacks, reflected in lower success rates and heavier perturbations required.
Tasks	Object Classification, Question Answering, Visual Question Answering
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07183v6
PDF	http://arxiv.org/pdf/1711.07183v6.pdf
PWC	https://paperswithcode.com/paper/adversarial-attacks-beyond-the-image-space
Repo
Framework

Towards Decoding as Continuous Optimization in Neural Machine Translation


Title	Towards Decoding as Continuous Optimization in Neural Machine Translation
Authors	Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn
Abstract	We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained continuous optimisation problem is then tackled using gradient-based methods. Our powerful decoding framework enables decoding intractable models such as the intersection of left-to-right and right-to-left (bidirectional) as well as source-to-target and target-to-source (bilingual) NMT models. Our empirical results show that our decoding framework is effective, and leads to substantial improvements in translations generated from the intersected models where the typical greedy or beam search is not feasible. We also compare our framework against reranking, and analyse its advantages and disadvantages.
Tasks	Machine Translation
Published	2017-01-11
URL	http://arxiv.org/abs/1701.02854v4
PDF	http://arxiv.org/pdf/1701.02854v4.pdf
PWC	https://paperswithcode.com/paper/towards-decoding-as-continuous-optimization
Repo
Framework

What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?


Title	What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?
Authors	Hung Le, Ali Borji
Abstract	In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated. While our focus here is on CNNs, the same operations, but in the reverse order, can be used to calculate these quantities for deconvolutional neural networks. These are important concepts, not only for better understanding and analyzing convolutional and deconvolutional networks, but also for optimizing their performance in real-world applications.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07049v2
PDF	http://arxiv.org/pdf/1705.07049v2.pdf
PWC	https://paperswithcode.com/paper/what-are-the-receptive-effective-receptive
Repo
Framework

Efficient fetal-maternal ECG signal separation from two channel maternal abdominal ECG via diffusion-based channel selection


Title	Efficient fetal-maternal ECG signal separation from two channel maternal abdominal ECG via diffusion-based channel selection
Authors	Ruilin Li, Martin G. Frasch, Hau-tieng Wu
Abstract	There is a need for affordable, widely deployable maternal-fetal ECG monitors to improve maternal and fetal health during pregnancy and delivery. Based on the diffusion-based channel selection, here we present the mathematical formalism and clinical validation of an algorithm capable of accurate separation of maternal and fetal ECG from a two channel signal acquired over maternal abdomen.
Tasks
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02025v1
PDF	http://arxiv.org/pdf/1702.02025v1.pdf
PWC	https://paperswithcode.com/paper/efficient-fetal-maternal-ecg-signal
Repo
Framework

Towards CNN map representation and compression for camera relocalisation


Title	Towards CNN map representation and compression for camera relocalisation
Authors	Luis Contreras, Walterio Mayol-Cuevas
Abstract	This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression. We follow state of the art visual relocalisation results and evaluate the response to different data inputs. We use a CNN map representation and introduce the notion of map compression under this paradigm by using smaller CNN architectures without sacrificing relocalisation performance. We evaluate this approach in a series of publicly available datasets over a number of CNN architectures with different sizes, both in complexity and number of layers. This formulation allows us to improve relocalisation accuracy by increasing the number of training trajectories while maintaining a constant-size CNN.
Tasks	Camera Relocalization
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05972v2
PDF	http://arxiv.org/pdf/1709.05972v2.pdf
PWC	https://paperswithcode.com/paper/towards-cnn-map-representation-and
Repo
Framework

A Conditional Variational Framework for Dialog Generation


Title	A Conditional Variational Framework for Dialog Generation
Authors	Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
Abstract	Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to uncontrollable generated responses. In this paper, we propose a framework allowing conditional response generation based on specific attributes. These attributes can be either manually assigned or automatically detected. Moreover, the dialog states for both speakers are modeled separately in order to reflect personal features. We validate this framework on two different scenarios, where the attribute refers to genericness and sentiment states respectively. The experiment result testified the potential of our model, where meaningful responses can be generated in accordance with the specified attributes.
Tasks	Latent Variable Models
Published	2017-04-30
URL	http://arxiv.org/abs/1705.00316v4
PDF	http://arxiv.org/pdf/1705.00316v4.pdf
PWC	https://paperswithcode.com/paper/a-conditional-variational-framework-for
Repo
Framework

3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images


Title	3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
Authors	Benjamin Hou, Bishesh Khanal, Amir Alansary, Steven McDonagh, Alice Davidson, Mary Rutherford, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
Abstract	Limited capture range, and the requirement to provide high quality initialization for optimization-based 2D/3D image registration methods, can significantly degrade the performance of 3D image reconstruction and motion compensation pipelines. Challenging clinical imaging scenarios, which contain significant subject motion such as fetal in-utero imaging, complicate the 3D image and volume reconstruction process. In this paper we present a learning based image registration method capable of predicting 3D rigid transformations of arbitrarily oriented 2D image slices, with respect to a learned canonical atlas co-ordinate system. Only image slice intensity information is used to perform registration and canonical alignment, no spatial transform initialization is required. To find image transformations we utilize a Convolutional Neural Network (CNN) architecture to learn the regression function capable of mapping 2D image slices to a 3D canonical atlas space. We extensively evaluate the effectiveness of our approach quantitatively on simulated Magnetic Resonance Imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline. Our learning based registration achieves an average spatial prediction error of 7 mm on simulated data and produces qualitatively improved reconstructions for heavily moving fetuses with gestational ages of approximately 20 weeks. Our model provides a general and computationally efficient solution to the 2D/3D registration initialization problem and is suitable for real-time scenarios.
Tasks	3D Reconstruction, Image Reconstruction, Image Registration, Motion Compensation
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06341v4
PDF	http://arxiv.org/pdf/1709.06341v4.pdf
PWC	https://paperswithcode.com/paper/3d-reconstruction-in-canonical-co-ordinate
Repo
Framework

GP CaKe: Effective brain connectivity with causal kernels


Title	GP CaKe: Effective brain connectivity with causal kernels
Authors	Luca Ambrogioni, Max Hinne, Marcel van Gerven, Eric Maris
Abstract	A fundamental goal in network neuroscience is to understand how activity in one region drives activity elsewhere, a process referred to as effective connectivity. Here we propose to model this causal interaction using integro-differential equations and causal kernels that allow for a rich analysis of effective connectivity. The approach combines the tractability and flexibility of autoregressive modeling with the biophysical interpretability of dynamic causal modeling. The causal kernels are learned nonparametrically using Gaussian process regression, yielding an efficient framework for causal inference. We construct a novel class of causal covariance functions that enforce the desired properties of the causal kernels, an approach which we call GP CaKe. By construction, the model and its hyperparameters have biophysical meaning and are therefore easily interpretable. We demonstrate the efficacy of GP CaKe on a number of simulations and give an example of a realistic application on magnetoencephalography (MEG) data.
Tasks	Causal Inference
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05603v1
PDF	http://arxiv.org/pdf/1705.05603v1.pdf
PWC	https://paperswithcode.com/paper/gp-cake-effective-brain-connectivity-with
Repo
Framework

Synergy of all-purpose static solver and temporal reasoning tools in dynamic integrated expert systems


Title	Synergy of all-purpose static solver and temporal reasoning tools in dynamic integrated expert systems
Authors	Galina Rybina, Alexey Mozgachev, Dmitry Demidov
Abstract	The paper discusses scientific and technological problems of dynamic integrated expert systems development. Extensions of problem-oriented methodology for dynamic integrated expert systems development are considered. Attention is paid to the temporal knowledge representation and processing.
Tasks
Published	2017-04-16
URL	http://arxiv.org/abs/1704.05392v1
PDF	http://arxiv.org/pdf/1704.05392v1.pdf
PWC	https://paperswithcode.com/paper/synergy-of-all-purpose-static-solver-and
Repo
Framework

Learning Quadratic Variance Function (QVF) DAG models via OverDispersion Scoring (ODS)


Title	Learning Quadratic Variance Function (QVF) DAG models via OverDispersion Scoring (ODS)
Authors	Gunwoong Park, Garvesh Raskutti
Abstract	Learning DAG or Bayesian network models is an important problem in multi-variate causal inference. However, a number of challenges arises in learning large-scale DAG models including model identifiability and computational complexity since the space of directed graphs is huge. In this paper, we address these issues in a number of steps for a broad class of DAG models where the noise or variance is signal-dependent. Firstly we introduce a new class of identifiable DAG models, where each node has a distribution where the variance is a quadratic function of the mean (QVF DAG models). Our QVF DAG models include many interesting classes of distributions such as Poisson, Binomial, Geometric, Exponential, Gamma and many other distributions in which the noise variance depends on the mean. We prove that this class of QVF DAG models is identifiable, and introduce a new algorithm, the OverDispersion Scoring (ODS) algorithm, for learning large-scale QVF DAG models. Our algorithm is based on firstly learning the moralized or undirected graphical model representation of the DAG to reduce the DAG search-space, and then exploiting the quadratic variance property to learn the causal ordering. We show through theoretical results and simulations that our algorithm is statistically consistent in the high-dimensional p>n setting provided that the degree of the moralized graph is bounded and performs well compared to state-of-the-art DAG-learning algorithms.
Tasks	Causal Inference
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08783v1
PDF	http://arxiv.org/pdf/1704.08783v1.pdf
PWC	https://paperswithcode.com/paper/learning-quadratic-variance-function-qvf-dag
Repo
Framework