May 6, 2019

3318 words 16 mins read

Paper Group ANR 215

Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions. Recursive nearest agglomeration (ReNA): fast clustering for approximation of structured signals. Tuning-Free Heterogeneity Pursuit in Massive Networks. Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification. The Edit Dista …

Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions


Title	Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions
Authors	Keunwoo Choi, George Fazekas, Mark Sandler
Abstract	We introduce a novel playlist generation algorithm that focuses on the quality of transitions using a recurrent neural network (RNN). The proposed model assumes that optimal transitions between tracks can be modelled and predicted by internal transitions within music tracks. We introduce modelling sequences of high-level music descriptors using RNNs and discuss an experiment involving different similarity functions, where the sequences are provided by a musical structural analysis algorithm. Qualitative observations show that the proposed approach can effectively model transitions of music tracks in playlists.
Tasks
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02096v1
PDF	http://arxiv.org/pdf/1606.02096v1.pdf
PWC	https://paperswithcode.com/paper/towards-playlist-generation-algorithms-using
Repo
Framework

Recursive nearest agglomeration (ReNA): fast clustering for approximation of structured signals


Title	Recursive nearest agglomeration (ReNA): fast clustering for approximation of structured signals
Authors	Andrés Hoyos-Idrobo, Gaël Varoquaux, Jonas Kahn, Bertrand Thirion
Abstract	In this work, we revisit fast dimension reduction approaches, as with random projections and random sampling. Our goal is to summarize the data to decrease computational costs and memory footprint of subsequent analysis. Such dimension reduction can be very efficient when the signals of interest have a strong structure, such as with images. We focus on this setting and investigate feature clustering schemes for data reductions that capture this structure. An impediment to fast dimension reduction is that good clustering comes with large algorithmic costs. We address it by contributing a linear-time agglomerative clustering scheme, Recursive Nearest Agglomeration (ReNA). Unlike existing fast agglomerative schemes, it avoids the creation of giant clusters. We empirically validate that it approximates the data as well as traditional variance-minimizing clustering schemes that have a quadratic complexity. In addition, we analyze signal approximation with feature clustering and show that it can remove noise, improving subsequent analysis steps. As a consequence, data reduction by clustering features with ReNA yields very fast and accurate models, enabling to process large datasets on budget. Our theoretical analysis is backed by extensive experiments on publicly-available data that illustrate the computation efficiency and the denoising properties of the resulting dimension reduction scheme.
Tasks	Denoising, Dimensionality Reduction
Published	2016-09-15
URL	http://arxiv.org/abs/1609.04608v2
PDF	http://arxiv.org/pdf/1609.04608v2.pdf
PWC	https://paperswithcode.com/paper/recursive-nearest-agglomeration-rena-fast
Repo
Framework

Tuning-Free Heterogeneity Pursuit in Massive Networks


Title	Tuning-Free Heterogeneity Pursuit in Massive Networks
Authors	Zhao Ren, Yongjian Kang, Yingying Fan, Jinchi Lv
Abstract	Heterogeneity is often natural in many contemporary applications involving massive data. While posing new challenges to effective learning, it can play a crucial role in powering meaningful scientific discoveries through the understanding of important differences among subpopulations of interest. In this paper, we exploit multiple networks with Gaussian graphs to encode the connectivity patterns of a large number of features on the subpopulations. To uncover the heterogeneity of these structures across subpopulations, we suggest a new framework of tuning-free heterogeneity pursuit (THP) via large-scale inference, where the number of networks is allowed to diverge. In particular, two new tests, the chi-based test and the linear functional-based test, are introduced and their asymptotic null distributions are established. Under mild regularity conditions, we establish that both tests are optimal in achieving the testable region boundary and the sample size requirement for the latter test is minimal. Both theoretical guarantees and the tuning-free feature stem from efficient multiple-network estimation by our newly suggested approach of heterogeneous group square-root Lasso (HGSL) for high-dimensional multi-response regression with heterogeneous noises. To solve this convex program, we further introduce a tuning-free algorithm that is scalable and enjoys provable convergence to the global optimum. Both computational and theoretical advantages of our procedure are elucidated through simulation and real data examples.
Tasks
Published	2016-06-13
URL	http://arxiv.org/abs/1606.03803v1
PDF	http://arxiv.org/pdf/1606.03803v1.pdf
PWC	https://paperswithcode.com/paper/tuning-free-heterogeneity-pursuit-in-massive
Repo
Framework

Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification


Title	Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
Authors	Keiller Nogueira, Otávio A. B. Penatti, Jefersson A. dos Santos
Abstract	We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature extractors. In many applications, especially including remote sensing, it is not feasible to fully design and train a new ConvNet, as this usually requires a considerable amount of labeled data and demands high computational costs. Therefore, it is important to understand how to obtain the best profit from existing ConvNets. We perform experiments with six popular ConvNets using three remote sensing datasets. We also compare ConvNets in each strategy with existing descriptors and with state-of-the-art baselines. Results point that fine tuning tends to be the best performing strategy. In fact, using the features from the fine-tuned ConvNet with linear SVM obtains the best results. We also achieved state-of-the-art results for the three datasets used.
Tasks	Scene Classification
Published	2016-02-04
URL	http://arxiv.org/abs/1602.01517v1
PDF	http://arxiv.org/pdf/1602.01517v1.pdf
PWC	https://paperswithcode.com/paper/towards-better-exploiting-convolutional
Repo
Framework

The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16


Title	The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
Authors	Felix Stahlberg, Eva Hasler, Bill Byrne
Abstract	This paper presents the University of Cambridge submission to WMT16. Motivated by the complementary nature of syntactical machine translation and neural machine translation (NMT), we exploit the synergies of Hiero and NMT in different combination schemes. Starting out with a simple neural lattice rescoring approach, we show that the Hiero lattices are often too narrow for NMT ensembles. Therefore, instead of a hard restriction of the NMT search space to the lattice, we propose to loosely couple NMT and Hiero by composition with a modified version of the edit distance transducer. The loose combination outperforms lattice rescoring, especially when using multiple NMT systems in an ensemble.
Tasks	Machine Translation
Published	2016-06-15
URL	http://arxiv.org/abs/1606.04963v1
PDF	http://arxiv.org/pdf/1606.04963v1.pdf
PWC	https://paperswithcode.com/paper/the-edit-distance-transducer-in-action-the
Repo
Framework

Visualization of Jacques Lacan’s Registers of the Psychoanalytic Field, and Discovery of Metaphor and of Metonymy. Analytical Case Study of Edgar Allan Poe’s “The Purloined Letter”


Title	Visualization of Jacques Lacan’s Registers of the Psychoanalytic Field, and Discovery of Metaphor and of Metonymy. Analytical Case Study of Edgar Allan Poe’s “The Purloined Letter”
Authors	Fionn Murtagh, Giuseppe Iurato
Abstract	We start with a description of Lacan’s work that we then take into our analytics methodology. In a first investigation, a Lacan-motivated template of the Poe story is fitted to the data. A segmentation of the storyline is used in order to map out the diachrony. Based on this, it will be shown how synchronous aspects, potentially related to Lacanian registers, can be sought. This demonstrates the effectiveness of an approach based on a model template of the storyline narrative. In a second and more comprehensive investigation, we develop an approach for revealing, that is, uncovering, Lacanian register relationships. Objectives of this work include the wide and general application of our methodology. This methodology is strongly based on the “letting the data speak” Correspondence Analysis analytics platform of Jean-Paul Benz'ecri, that is also the geometric data analysis, both qualitative and quantitative analytics, developed by Pierre Bourdieu.
Tasks
Published	2016-04-23
URL	http://arxiv.org/abs/1604.06952v3
PDF	http://arxiv.org/pdf/1604.06952v3.pdf
PWC	https://paperswithcode.com/paper/visualization-of-jacques-lacans-registers-of
Repo
Framework

Shape Animation with Combined Captured and Simulated Dynamics


Title	Shape Animation with Combined Captured and Simulated Dynamics
Authors	Benjamin Allain, Li Wang, Jean-Sebastien Franco, Franck Hetroy, Edmond Boyer
Abstract	We present a novel volumetric animation generation framework to create new types of animations from raw 3D surface or point cloud sequence of captured real performances. The framework considers as input time incoherent 3D observations of a moving shape, and is thus particularly suitable for the output of performance capture platforms. In our system, a suitable virtual representation of the actor is built from real captures that allows seamless combination and simulation with virtual external forces and objects, in which the original captured actor can be reshaped, disassembled or reassembled from user-specified virtual physics. Instead of using the dominant surface-based geometric representation of the capture, which is less suitable for volumetric effects, our pipeline exploits Centroidal Voronoi tessellation decompositions as unified volumetric representation of the real captured actor, which we show can be used seamlessly as a building block for all processing stages, from capture and tracking to virtual physic simulation. The representation makes no human specific assumption and can be used to capture and re-simulate the actor with props or other moving scenery elements. We demonstrate the potential of this pipeline for virtual reanimation of a real captured event with various unprecedented volumetric visual effects, such as volumetric distortion, erosion, morphing, gravity pull, or collisions.
Tasks
Published	2016-01-06
URL	http://arxiv.org/abs/1601.01232v1
PDF	http://arxiv.org/pdf/1601.01232v1.pdf
PWC	https://paperswithcode.com/paper/shape-animation-with-combined-captured-and
Repo
Framework

Appraisal of data-driven and mechanistic emulators of nonlinear hydrodynamic urban drainage simulators


Title	Appraisal of data-driven and mechanistic emulators of nonlinear hydrodynamic urban drainage simulators
Authors	Juan Pablo Carbajal, João Paulo Leitão, Carlo Albert, Jörg Rieckermann
Abstract	Many model based scientific and engineering methodologies, such as system identification, sensitivity analysis, optimization and control, require a large number of model evaluations. In particular, model based real-time control of urban water infrastructures and online flood alarm systems require fast prediction of the network response at different actuation and/or parameter values. General purpose urban drainage simulators are too slow for this application. Fast surrogate models, so-called emulators, provide a solution to this efficiency demand. Emulators are attractive, because they sacrifice unneeded accuracy in favor of speed. However, they have to be fine-tuned to predict the system behavior satisfactorily. Also, some emulators fail to extrapolate the system behavior beyond the training set. Although, there are many strategies for developing emulators, up until now the selection of the emulation strategy remains subjective. In this paper, we therefore compare the performance of two families of emulators for open channel flows in the context of urban drainage simulators. We compare emulators that explicitly use knowledge of the simulator’s equations, i.e. mechanistic emulators based on Gaussian Processes, with purely data-driven emulators using matrix factorization. Our results suggest that in many urban applications, naive data-driven emulation outperforms mechanistic emulation. Nevertheless, we discuss scenarios in which we think that mechanistic emulation might be favorable for i) extrapolation in time and ii) dealing with sparse and unevenly sampled data. We also provide many references to advances in the field of Machine Learning that have not yet permeated into the Bayesian environmental science community.
Tasks	Gaussian Processes
Published	2016-09-25
URL	http://arxiv.org/abs/1609.08395v2
PDF	http://arxiv.org/pdf/1609.08395v2.pdf
PWC	https://paperswithcode.com/paper/appraisal-of-data-driven-and-mechanistic
Repo
Framework

Learning Identity Mappings with Residual Gates


Title	Learning Identity Mappings with Residual Gates
Authors	Pedro H. P. Savarese, Leonardo O. Mazza, Daniel R. Figueiredo
Abstract	We propose a new layer design by adding a linear gating mechanism to shortcut connections. By using a scalar parameter to control each gate, we provide a way to learn identity mappings by optimizing only one parameter. We build upon the motivation behind Residual Networks, where a layer is reformulated in order to make learning identity mappings less problematic to the optimizer. The augmentation introduces only one extra parameter per layer, and provides easier optimization by making degeneration into identity mappings simpler. We propose a new model, the Gated Residual Network, which is the result when augmenting Residual Networks. Experimental results show that augmenting layers provides better optimization, increased performance, and more layer independence. We evaluate our method on MNIST using fully-connected networks, showing empirical indications that our augmentation facilitates the optimization of deep models, and that it provides high tolerance to full layer removal: the model retains over 90% of its performance even after half of its layers have been randomly removed. We also evaluate our model on CIFAR-10 and CIFAR-100 using Wide Gated ResNets, achieving 3.65% and 18.27% error, respectively.
Tasks	Image Classification
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01260v2
PDF	http://arxiv.org/pdf/1611.01260v2.pdf
PWC	https://paperswithcode.com/paper/learning-identity-mappings-with-residual
Repo
Framework

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs


Title	Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs
Authors	Hui Li, Chunhua Shen
Abstract	In this work, we tackle the problem of car license plate detection and recognition in natural scene images. Inspired by the success of deep neural networks (DNNs) in various vision applications, here we leverage DNNs to learn high-level features in a cascade framework, which lead to improved performance on both detection and recognition. Firstly, we train a $37$-class convolutional neural network (CNN) to detect all characters in an image, which results in a high recall, compared with conventional approaches such as training a binary text/non-text classifier. False positives are then eliminated by the second plate/non-plate CNN classifier. Bounding box refinement is then carried out based on the edge information of the license plates, in order to improve the intersection-over-union (IoU) ratio. The proposed cascade framework extracts license plates effectively with both high recall and precision. Last, we propose to recognize the license characters as a {sequence labelling} problem. A recurrent neural network (RNN) with long short-term memory (LSTM) is trained to recognize the sequential features extracted from the whole license plate via CNNs. The main advantage of this approach is that it is segmentation free. By exploring context information and avoiding errors caused by segmentation, the RNN method performs better than a baseline method of combining segmentation and deep CNN classification; and achieves state-of-the-art recognition accuracy.
Tasks
Published	2016-01-21
URL	http://arxiv.org/abs/1601.05610v1
PDF	http://arxiv.org/pdf/1601.05610v1.pdf
PWC	https://paperswithcode.com/paper/reading-car-license-plates-using-deep
Repo
Framework

A multilevel framework for sparse optimization with application to inverse covariance estimation and logistic regression


Title	A multilevel framework for sparse optimization with application to inverse covariance estimation and logistic regression
Authors	Eran Treister, Javier S. Turek, Irad Yavneh
Abstract	Solving l1 regularized optimization problems is common in the fields of computational biology, signal processing and machine learning. Such l1 regularization is utilized to find sparse minimizers of convex functions. A well-known example is the LASSO problem, where the l1 norm regularizes a quadratic function. A multilevel framework is presented for solving such l1 regularized sparse optimization problems efficiently. We take advantage of the expected sparseness of the solution, and create a hierarchy of problems of similar type, which is traversed in order to accelerate the optimization process. This framework is applied for solving two problems: (1) the sparse inverse covariance estimation problem, and (2) l1-regularized logistic regression. In the first problem, the inverse of an unknown covariance matrix of a multivariate normal distribution is estimated, under the assumption that it is sparse. To this end, an l1 regularized log-determinant optimization problem needs to be solved. This task is challenging especially for large-scale datasets, due to time and memory limitations. In the second problem, the l1-regularization is added to the logistic regression classification objective to reduce overfitting to the data and obtain a sparse model. Numerical experiments demonstrate the efficiency of the multilevel framework in accelerating existing iterative solvers for both of these problems.
Tasks
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00315v1
PDF	http://arxiv.org/pdf/1607.00315v1.pdf
PWC	https://paperswithcode.com/paper/a-multilevel-framework-for-sparse
Repo
Framework

Automatic and Quantitative evaluation of attribute discovery methods


Title	Automatic and Quantitative evaluation of attribute discovery methods
Authors	Liangchen Liu, Arnold Wiliem, Shaokang Chen, Brian C. Lovell
Abstract	Many automatic attribute discovery methods have been developed to extract a set of visual attributes from images for various tasks. However, despite good performance in some image classification tasks, it is difficult to evaluate whether these methods discover meaningful attributes and which one is the best to find the attributes for image descriptions. An intuitive way to evaluate this is to manually verify whether consistent identifiable visual concepts exist to distinguish between positive and negative images of an attribute. This manual checking is tedious, labor intensive and expensive and it is very hard to get quantitative comparisons between different methods. In this work, we tackle this problem by proposing an attribute meaningfulness metric, that can perform automatic evaluation on the meaningfulness of attribute sets as well as achieving quantitative comparisons. We apply our proposed metric to recent automatic attribute discovery methods and popular hashing methods on three attribute datasets. A user study is also conducted to validate the effectiveness of the metric. In our evaluation, we gleaned some insights that could be beneficial in developing automatic attribute discovery methods to generate meaningful attributes. To the best of our knowledge, this is the first work to quantitatively measure the semantic content of automatically discovered attributes.
Tasks	Image Classification
Published	2016-02-05
URL	http://arxiv.org/abs/1602.01940v1
PDF	http://arxiv.org/pdf/1602.01940v1.pdf
PWC	https://paperswithcode.com/paper/automatic-and-quantitative-evaluation-of
Repo
Framework

Robust Cardiac Motion Estimation using Ultrafast Ultrasound Data: A Low-Rank-Topology-Preserving Approach


Title	Robust Cardiac Motion Estimation using Ultrafast Ultrasound Data: A Low-Rank-Topology-Preserving Approach
Authors	Angelica I. Aviles, Thomas Widlak, Alicia Casals, Maartje M. Nillesen, Habib Ammari
Abstract	Cardiac motion estimation is an important diagnostic tool to detect heart diseases and it has been explored with modalities such as MRI and conventional ultrasound (US) sequences. US cardiac motion estimation still presents challenges because of the complex motion patterns and the presence of noise. In this work, we propose a novel approach to estimate the cardiac motion using ultrafast ultrasound data. – Our solution is based on a variational formulation characterized by the L2-regularized class. The displacement is represented by a lattice of b-splines and we ensure robustness by applying a maximum likelihood type estimator. While this is an important part of our solution, the main highlight of this paper is to combine a low-rank data representation with topology preservation. Low-rank data representation (achieved by finding the k-dominant singular values of a Casorati Matrix arranged from the data sequence) speeds up the global solution and achieves noise reduction. On the other hand, topology preservation (achieved by monitoring the Jacobian determinant) allows to radically rule out distortions while carefully controlling the size of allowed expansions and contractions. Our variational approach is carried out on a realistic dataset as well as on a simulated one. We demonstrate how our proposed variational solution deals with complex deformations through careful numerical experiments. While maintaining the accuracy of the solution, the low-rank preprocessing is shown to speed up the convergence of the variational problem. Beyond cardiac motion estimation, our approach is promising for the analysis of other organs that experience motion.
Tasks	Motion Estimation
Published	2016-10-26
URL	http://arxiv.org/abs/1611.02730v2
PDF	http://arxiv.org/pdf/1611.02730v2.pdf
PWC	https://paperswithcode.com/paper/robust-cardiac-motion-estimation-using
Repo
Framework

A Computational Model for Situated Task Learning with Interactive Instruction


Title	A Computational Model for Situated Task Learning with Interactive Instruction
Authors	Shiwali Mohan, James Kirk, John Laird
Abstract	Learning novel tasks is a complex cognitive activity requiring the learner to acquire diverse declarative and procedural knowledge. Prior ACT-R models of acquiring task knowledge from instruction focused on learning procedural knowledge from declarative instructions encoded in semantic memory. In this paper, we identify the requirements for designing compu- tational models that learn task knowledge from situated task- oriented interactions with an expert and then describe and evaluate a model of learning from situated interactive instruc- tion that is implemented in the Soar cognitive architecture.
Tasks
Published	2016-04-23
URL	http://arxiv.org/abs/1604.06849v1
PDF	http://arxiv.org/pdf/1604.06849v1.pdf
PWC	https://paperswithcode.com/paper/a-computational-model-for-situated-task
Repo
Framework

Uncertain programming model for multi-item solid transportation problem


Title	Uncertain programming model for multi-item solid transportation problem
Authors	Hasan Dalman
Abstract	In this paper, an uncertain Multi-objective Multi-item Solid Transportation Problem (MMSTP) based on uncertainty theory is presented. In the model, transportation costs, supplies, demands and conveyances parameters are taken to be uncertain parameters. There are restrictions on some items and conveyances of the model. Therefore, some particular items cannot be transported by some exceptional conveyances. Using the advantage of uncertainty theory, the MMSTP is first converted into an equivalent deterministic MMSTP. By applying convex combination method and minimizing distance function method, the deterministic MMSTP is reduced into single objective programming problems. Thus, both single objective programming problems are solved using Maple 18.02 optimization toolbox. Finally, a numerical example is given to illustrate the performance of the models.
Tasks
Published	2016-05-31
URL	http://arxiv.org/abs/1606.00002v1
PDF	http://arxiv.org/pdf/1606.00002v1.pdf
PWC	https://paperswithcode.com/paper/uncertain-programming-model-for-multi-item
Repo
Framework