July 27, 2019

2759 words 13 mins read

Paper Group ANR 537

Learning Low-shot facial representations via 2D warping. Unsupervised Creation of Parameterized Avatars. A Comparison of Directional Distances for Hand Pose Estimation. Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation. A Stochastic Trust Region Algorithm Based on Careful Step Normalization. Machine-Learning …

Learning Low-shot facial representations via 2D warping


Title	Learning Low-shot facial representations via 2D warping
Authors	Shen Yan
Abstract	In this work, we mainly study the influence of the 2D warping module for one-shot face recognition.
Tasks	Face Recognition
Published	2017-12-13
URL	http://arxiv.org/abs/1712.05015v2
PDF	http://arxiv.org/pdf/1712.05015v2.pdf
PWC	https://paperswithcode.com/paper/learning-low-shot-facial-representations-via
Repo
Framework

Unsupervised Creation of Parameterized Avatars


Title	Unsupervised Creation of Parameterized Avatars
Authors	Lior Wolf, Yaniv Taigman, Adam Polyak
Abstract	We study the problem of mapping an input image to a tied pair consisting of a vector of parameters and an image that is created using a graphical engine from the vector of parameters. The mapping’s objective is to have the output image as similar as possible to the input image. During training, no supervision is given in the form of matching inputs and outputs. This learning problem extends two literature problems: unsupervised domain adaptation and cross domain transfer. We define a generalization bound that is based on discrepancy, and employ a GAN to implement a network solution that corresponds to this bound. Experimentally, our method is shown to solve the problem of automatically creating avatars.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05693v2
PDF	http://arxiv.org/pdf/1704.05693v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-creation-of-parameterized
Repo
Framework

A Comparison of Directional Distances for Hand Pose Estimation


Title	A Comparison of Directional Distances for Hand Pose Estimation
Authors	Dimitrios Tzionas, Juergen Gall
Abstract	Benchmarking methods for 3d hand tracking is still an open problem due to the difficulty of acquiring ground truth data. We introduce a new dataset and benchmarking protocol that is insensitive to the accumulative error of other protocols. To this end, we create testing frame pairs of increasing difficulty and measure the pose estimation error separately for each of them. This approach gives new insights and allows to accurately study the performance of each feature or method without employing a full tracking pipeline. Following this protocol, we evaluate various directional distances in the context of silhouette-based 3d hand tracking, expressed as special cases of a generalized Chamfer distance form. An appropriate parameter setup is proposed for each of them, and a comparative study reveals the best performing method in this context.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00492v1
PDF	http://arxiv.org/pdf/1704.00492v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-directional-distances-for
Repo
Framework

Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation


Title	Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation
Authors	Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
Abstract	State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose to model the statistical relationships of 3D hand poses and corresponding depth images using two deep generative models with a shared latent space. By design, our architecture allows for learning from unlabeled image data in a semi-supervised manner. Assuming a one-to-one mapping between a pose and a depth map, any given point in the shared latent space can be projected into both a hand pose and a corresponding depth map. Regressing the hand pose can then be done by learning a discriminator to estimate the posterior of the latent pose given some depth maps. To improve generalization and to better exploit unlabeled depth maps, we jointly train a generator and a discriminator. At each iteration, the generator is updated with the back-propagated gradient from the discriminator to synthesize realistic depth maps of the articulated hand, while the discriminator benefits from an augmented training set of synthesized and unlabeled samples. The proposed discriminator network architecture is highly efficient and runs at 90 FPS on the CPU with accuracies comparable or better than state-of-art on 3 publicly available benchmarks.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-02-11
URL	http://arxiv.org/abs/1702.03431v2
PDF	http://arxiv.org/pdf/1702.03431v2.pdf
PWC	https://paperswithcode.com/paper/crossing-nets-combining-gans-and-vaes-with-a
Repo
Framework

A Stochastic Trust Region Algorithm Based on Careful Step Normalization


Title	A Stochastic Trust Region Algorithm Based on Careful Step Normalization
Authors	Frank E. Curtis, Katya Scheinberg, Rui Shi
Abstract	An algorithm is proposed for solving stochastic and finite sum minimization problems. Based on a trust region methodology, the algorithm employs normalized steps, at least as long as the norms of the stochastic gradient estimates are within a specified interval. The complete algorithm—which dynamically chooses whether or not to employ normalized steps—is proved to have convergence guarantees that are similar to those possessed by a traditional stochastic gradient approach under various sets of conditions related to the accuracy of the stochastic gradient estimates and choice of stepsize sequence. The results of numerical experiments are presented when the method is employed to minimize convex and nonconvex machine learning test problems. These results illustrate that the method can outperform a traditional stochastic gradient approach.
Tasks
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10277v3
PDF	http://arxiv.org/pdf/1712.10277v3.pdf
PWC	https://paperswithcode.com/paper/a-stochastic-trust-region-algorithm-based-on
Repo
Framework

Machine-Learning Tests for Effects on Multiple Outcomes


Title	Machine-Learning Tests for Effects on Multiple Outcomes
Authors	Jens Ludwig, Sendhil Mullainathan, Jann Spiess
Abstract	In this paper we present tools for applied researchers that re-purpose off-the-shelf methods from the computer-science field of machine learning to create a “discovery engine” for data from randomized controlled trials (RCTs). The applied problem we seek to solve is that economists invest vast resources into carrying out RCTs, including the collection of a rich set of candidate outcome measures. But given concerns about inference in the presence of multiple testing, economists usually wind up exploring just a small subset of the hypotheses that the available data could be used to test. This prevents us from extracting as much information as possible from each RCT, which in turn impairs our ability to develop new theories or strengthen the design of policy interventions. Our proposed solution combines the basic intuition of reverse regression, where the dependent variable of interest now becomes treatment assignment itself, with methods from machine learning that use the data themselves to flexibly identify whether there is any function of the outcomes that predicts (or has signal about) treatment group status. This leads to correctly-sized tests with appropriate $p$-values, which also have the important virtue of being easy to implement in practice. One open challenge that remains with our work is how to meaningfully interpret the signal that these methods find.
Tasks
Published	2017-07-05
URL	https://arxiv.org/abs/1707.01473v2
PDF	https://arxiv.org/pdf/1707.01473v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-tests-for-effects-on
Repo
Framework


Title	Using Summarization to Discover Argument Facets in Online Ideological Dialog
Authors	Amita Misra, Pranav Anand, Jean E Fox Tree, Marilyn Walker
Abstract	More and more of the information available on the web is dialogic, and a significant portion of it takes place in online forum conversations about current social and political topics. We aim to develop tools to summarize what these conversations are about. What are the CENTRAL PROPOSITIONS associated with different stances on an issue, what are the abstract objects under discussion that are central to a speaker’s argument? How can we recognize that two CENTRAL PROPOSITIONS realize the same FACET of the argument? We hypothesize that the CENTRAL PROPOSITIONS are exactly those arguments that people find most salient, and use human summarization as a probe for discovering them. We describe our corpus of human summaries of opinionated dialogs, then show how we can identify similar repeated arguments, and group them into FACETS across many discussions of a topic. We define a new task, ARGUMENT FACET SIMILARITY (AFS), and show that we can predict AFS with a .54 correlation score, versus an ngram system baseline of .39 and a semantic textual similarity system baseline of .45.
Tasks	Semantic Textual Similarity
Published	2017-09-03
URL	http://arxiv.org/abs/1709.00662v1
PDF	http://arxiv.org/pdf/1709.00662v1.pdf
PWC	https://paperswithcode.com/paper/using-summarization-to-discover-argument-1
Repo
Framework

Deep Matching Autoencoders


Title	Deep Matching Autoencoders
Authors	Tanmoy Mukherjee, Makoto Yamada, Timothy M. Hospedales
Abstract	Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicability is thus limited as the paired data assumption is often violated in practice: many tasks have only a small subset of data available with pairing annotation, or even no paired data at all. In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data. Specifically we formulate this as a cross-domain representation learning and object matching problem. We simultaneously optimise parameters of representation learning auto-encoders and the pairing of unpaired multi-modal data. This framework elegantly spans the full regime from fully supervised, semi-supervised, and unsupervised (no paired data) multi-modal learning. We show promising results in image captioning, and on a new task that is uniquely enabled by our methodology: unsupervised classifier learning.
Tasks	Image Captioning, Representation Learning
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06047v1
PDF	http://arxiv.org/pdf/1711.06047v1.pdf
PWC	https://paperswithcode.com/paper/deep-matching-autoencoders
Repo
Framework

A Machine Learning Approach for Evaluating Creative Artifacts


Title	A Machine Learning Approach for Evaluating Creative Artifacts
Authors	Disha Shrivastava, Saneem Ahmed CG, Anirban Laha, Karthik Sankaranarayanan
Abstract	Much work has been done in understanding human creativity and defining measures to evaluate creativity. This is necessary mainly for the reason of having an objective and automatic way of quantifying creative artifacts. In this work, we propose a regression-based learning framework which takes into account quantitatively the essential criteria for creativity like novelty, influence, value and unexpectedness. As it is often the case with most creative domains, there is no clear ground truth available for creativity. Our proposed learning framework is applicable to all creative domains; yet we evaluate it on a dataset of movies created from IMDb and Rotten Tomatoes due to availability of audience and critic scores, which can be used as proxy ground truth labels for creativity. We report promising results and observations from our experiments in the following ways : 1) Correlation of creative criteria with critic scores, 2) Improvement in movie rating prediction with inclusion of various creative criteria, and 3) Identification of creative movies.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05499v1
PDF	http://arxiv.org/pdf/1707.05499v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-approach-for-evaluating
Repo
Framework

Disentangling ASR and MT Errors in Speech Translation


Title	Disentangling ASR and MT Errors in Speech Translation
Authors	Ngoc-Tien Le, Benjamin Lecouteux, Laurent Besacier
Abstract	The main aim of this paper is to investigate automatic quality assessment for spoken language translation (SLT). More precisely, we investigate SLT errors that can be due to transcription (ASR) or to translation (MT) modules. This paper investigates automatic detection of SLT errors using a single classifier based on joint ASR and MT features. We evaluate both 2-class (good/bad) and 3-class (good/badASR/badMT ) labeling tasks. The 3-class problem necessitates to disentangle ASR and MT errors in the speech translation output and we propose two label extraction methods for this non trivial step. This enables - as a by-product - qualitative analysis on the SLT errors and their origin (are they due to transcription or to translation step?) on our large in-house corpus for French-to-English speech translation.
Tasks
Published	2017-09-03
URL	http://arxiv.org/abs/1709.00678v1
PDF	http://arxiv.org/pdf/1709.00678v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-asr-and-mt-errors-in-speech
Repo
Framework

Cluster-based Kriging Approximation Algorithms for Complexity Reduction


Title	Cluster-based Kriging Approximation Algorithms for Complexity Reduction
Authors	Bas van Stein, Hao Wang, Wojtek Kowalczyk, Michael Emmerich, Thomas Bäck
Abstract	Kriging or Gaussian Process Regression is applied in many fields as a non-linear regression model as well as a surrogate model in the field of evolutionary computation. However, the computational and space complexity of Kriging, that is cubic and quadratic in the number of data points respectively, becomes a major bottleneck with more and more data available nowadays. In this paper, we propose a general methodology for the complexity reduction, called cluster Kriging, where the whole data set is partitioned into smaller clusters and multiple Kriging models are built on top of them. In addition, four Kriging approximation algorithms are proposed as candidate algorithms within the new framework. Each of these algorithms can be applied to much larger data sets while maintaining the advantages and power of Kriging. The proposed algorithms are explained in detail and compared empirically against a broad set of existing state-of-the-art Kriging approximation methods on a well-defined testing framework. According to the empirical study, the proposed algorithms consistently outperform the existing algorithms. Moreover, some practical suggestions are provided for using the proposed algorithms.
Tasks
Published	2017-02-04
URL	http://arxiv.org/abs/1702.01313v1
PDF	http://arxiv.org/pdf/1702.01313v1.pdf
PWC	https://paperswithcode.com/paper/cluster-based-kriging-approximation
Repo
Framework

Detecting Sockpuppets in Deceptive Opinion Spam


Title	Detecting Sockpuppets in Deceptive Opinion Spam
Authors	Marjan Hosseinia, Arjun Mukherjee
Abstract	This paper explores the problem of sockpuppet detection in deceptive opinion spam using authorship attribution and verification approaches. Two methods are explored. The first is a feature subsampling scheme that uses the KL-Divergence on stylistic language models of an author to find discriminative features. The second is a transduction scheme, spy induction that leverages the diversity of authors in the unlabeled test set by sending a set of spies (positive samples) from the training set to retrieve hidden samples in the unlabeled test set using nearest and farthest neighbors. Experiments using ground truth sockpuppet data show the effectiveness of the proposed schemes.
Tasks
Published	2017-03-09
URL	http://arxiv.org/abs/1703.03149v1
PDF	http://arxiv.org/pdf/1703.03149v1.pdf
PWC	https://paperswithcode.com/paper/detecting-sockpuppets-in-deceptive-opinion
Repo
Framework

Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning


Title	Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning
Authors	Joao Vieira, Erik Leitinger, Muris Sarajlic, Xuhong Li, Fredrik Tufvesson
Abstract	This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning purposes. We evaluate the positioning accuracy of state-of-the-art CNNs with channel fingerprints generated from a channel model with a rich clustered structure: the COST 2100 channel model. We find that moderately deep CNNs can achieve fractional-wavelength positioning accuracies, provided that an enough representative data set is available for training.
Tasks
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06235v1
PDF	http://arxiv.org/pdf/1708.06235v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-8
Repo
Framework

A convergence analysis of the perturbed compositional gradient flow: averaging principle and normal deviations


Title	A convergence analysis of the perturbed compositional gradient flow: averaging principle and normal deviations
Authors	Wenqing Hu, Chris Junchi Li
Abstract	We consider in this work a system of two stochastic differential equations named the perturbed compositional gradient flow. By introducing a separation of fast and slow scales of the two equations, we show that the limit of the slow motion is given by an averaged ordinary differential equation. We then demonstrate that the deviation of the slow motion from the averaged equation, after proper rescaling, converges to a stochastic process with Gaussian inputs. This indicates that the slow motion can be approximated in the weak sense by a standard perturbed gradient flow or the continuous-time stochastic gradient descent algorithm that solves the optimization problem for a composition of two functions. As an application, the perturbed compositional gradient flow corresponds to the diffusion limit of the Stochastic Composite Gradient Descent (SCGD) algorithm for minimizing a composition of two expected-value functions in the optimization literatures. For the strongly convex case, such an analysis implies that the SCGD algorithm has the same convergence time asymptotic as the classical stochastic gradient descent algorithm. Thus it validates, at the level of continuous approximation, the effectiveness of using the SCGD algorithm in the strongly convex case.
Tasks
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00515v3
PDF	http://arxiv.org/pdf/1709.00515v3.pdf
PWC	https://paperswithcode.com/paper/a-convergence-analysis-of-the-perturbed
Repo
Framework

Deep Learning Paradigm with Transformed Monolingual Word Embeddings for Multilingual Sentiment Analysis


Title	Deep Learning Paradigm with Transformed Monolingual Word Embeddings for Multilingual Sentiment Analysis
Authors	Yujie Lu, Tatsunori Mori
Abstract	The surge of social media use brings huge demand of multilingual sentiment analysis (MSA) for unveiling cultural difference. So far, traditional methods resorted to machine translation—translating texts in other languages to English, and then adopt the methods once worked in English. However, this paradigm is conditioned by the quality of machine translation. In this paper, we propose a new deep learning paradigm to assimilate the differences between languages for MSA. We first pre-train monolingual word embeddings separately, then map word embeddings in different spaces into a shared embedding space, and then finally train a parameter-sharing deep neural network for MSA. The experimental results show that our paradigm is effective. Especially, our CNN model outperforms a state-of-the-art baseline by around 2.1% in terms of classification accuracy.
Tasks	Machine Translation, Sentiment Analysis, Word Embeddings
Published	2017-10-09
URL	http://arxiv.org/abs/1710.03203v2
PDF	http://arxiv.org/pdf/1710.03203v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-paradigm-with-transformed
Repo
Framework