May 6, 2019

2705 words 13 mins read

Paper Group ANR 270

The infochemical core. ALLSAT compressed with wildcards: From CNF’s to orthogonal DNF’s by imposing the clauses one by one. Observational-Interventional Priors for Dose-Response Learning. Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks. The Virtual Electromagnetic Interaction between Digital Images for …

The infochemical core


Title	The infochemical core
Authors	Antoni Hernández-Fernández, Ramon Ferrer-i-Cancho
Abstract	Vocalizations and less often gestures have been the object of linguistic research over decades. However, the development of a general theory of communication with human language as a particular case requires a clear understanding of the organization of communication through other means. Infochemicals are chemical compounds that carry information and are employed by small organisms that cannot emit acoustic signals of optimal frequency to achieve successful communication. Here the distribution of infochemicals across species is investigated when they are ranked by their degree or the number of species with which it is associated (because they produce or they are sensitive to it). The quality of the fit of different functions to the dependency between degree and rank is evaluated with a penalty for the number of parameters of the function. Surprisingly, a double Zipf (a Zipf distribution with two regimes with a different exponent each) is the model yielding the best fit although it is the function with the largest number of parameters. This suggests that the world wide repertoire of infochemicals contains a chemical nucleus shared by many species and reminiscent of the core vocabularies found for human language in dictionaries or large corpora.
Tasks
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05654v2
PDF	http://arxiv.org/pdf/1610.05654v2.pdf
PWC	https://paperswithcode.com/paper/the-infochemical-core
Repo
Framework

ALLSAT compressed with wildcards: From CNF’s to orthogonal DNF’s by imposing the clauses one by one


Title	ALLSAT compressed with wildcards: From CNF’s to orthogonal DNF’s by imposing the clauses one by one
Authors	Marcel Wild
Abstract	We present a novel technique for converting a Boolean CNF into an orthogonal DNF, aka exclusive sum of products. Our method (which will be pitted against a hardwired command from Mathematica) zooms in on the models of the CNF by imposing the clauses one after another. Wildcards beyond the common don’t-care symbol compress the output. Furthermore, clausal imposition adapts well (challenging BDD’s) to enumerate all models of bounded weight.
Tasks
Published	2016-08-30
URL	https://arxiv.org/abs/1608.08472v3
PDF	https://arxiv.org/pdf/1608.08472v3.pdf
PWC	https://paperswithcode.com/paper/allsat-compressed-with-wildcards-part-1
Repo
Framework

Observational-Interventional Priors for Dose-Response Learning


Title	Observational-Interventional Priors for Dose-Response Learning
Authors	Ricardo Silva
Abstract	Controlled interventions provide the most direct source of information for learning causal effects. In particular, a dose-response curve can be learned by varying the treatment level and observing the corresponding outcomes. However, interventions can be expensive and time-consuming. Observational data, where the treatment is not controlled by a known mechanism, is sometimes available. Under some strong assumptions, observational data allows for the estimation of dose-response curves. Estimating such curves nonparametrically is hard: sample sizes for controlled interventions may be small, while in the observational case a large number of measured confounders may need to be marginalized. In this paper, we introduce a hierarchical Gaussian process prior that constructs a distribution over the dose-response curve by learning from observational data, and reshapes the distribution with a nonparametric affine transform learned from controlled interventions. This function composition from different sources is shown to speed-up learning, which we demonstrate with a thorough sensitivity analysis and an application to modeling the effect of therapy on cognitive skills of premature infants.
Tasks
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01573v1
PDF	http://arxiv.org/pdf/1605.01573v1.pdf
PWC	https://paperswithcode.com/paper/observational-interventional-priors-for-dose
Repo
Framework

Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks


Title	Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
Authors	Yinda Zhang, Shuran Song, Ersin Yumer, Manolis Savva, Joon-Young Lee, Hailin Jin, Thomas Funkhouser
Abstract	Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their representation learning capabilities. One of the bottlenecks in training for better representations is the amount of available per-pixel ground truth data that is required for core scene understanding tasks such as semantic segmentation, normal prediction, and object edge detection. To address this problem, a number of works proposed using synthetic data. However, a systematic study of how such synthetic data is generated is missing. In this work, we introduce a large-scale synthetic dataset with 400K physically-based rendered images from 45K realistic 3D indoor scenes. We study the effects of rendering methods and scene lighting on training for three computer vision tasks: surface normal prediction, semantic segmentation, and object boundary detection. This study provides insights into the best practices for training with synthetic data (more realistic rendering is worth it) and shows that pretraining with our new synthetic dataset can improve results beyond the current state of the art on all three tasks.
Tasks	Boundary Detection, Edge Detection, Representation Learning, Robot Navigation, Scene Understanding, Semantic Segmentation
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07429v3
PDF	http://arxiv.org/pdf/1612.07429v3.pdf
PWC	https://paperswithcode.com/paper/physically-based-rendering-for-indoor-scene
Repo
Framework

The Virtual Electromagnetic Interaction between Digital Images for Image Matching with Shifting Transformation


Title	The Virtual Electromagnetic Interaction between Digital Images for Image Matching with Shifting Transformation
Authors	Xiaodong Zhuang, N. E. Mastorakis
Abstract	A novel way of matching two images with shifting transformation is studied. The approach is based on the presentation of the virtual edge current in images, and also the study of virtual electromagnetic interaction between two related images inspired by electromagnetism. The edge current in images is proposed as a discrete simulation of the physical current, which is based on the significant edge line extracted by Canny-like edge detection. Then the virtual interaction of the edge currents between related images is studied by imitating the electro-magnetic interaction between current-carrying wires. Based on the virtual interaction force between two related images, a novel method is presented and applied in image matching for shifting transformation. The preliminary experimental results indicate the effectiveness of the proposed method.
Tasks	Edge Detection
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03615v1
PDF	http://arxiv.org/pdf/1610.03615v1.pdf
PWC	https://paperswithcode.com/paper/the-virtual-electromagnetic-interaction
Repo
Framework

Robust Spectral Detection of Global Structures in the Data by Learning a Regularization


Title	Robust Spectral Detection of Global Structures in the Data by Learning a Regularization
Authors	Pan Zhang
Abstract	Spectral methods are popular in detecting global structures in the given data that can be represented as a matrix. However when the data matrix is sparse or noisy, classic spectral methods usually fail to work, due to localization of eigenvectors (or singular vectors) induced by the sparsity or noise. In this work, we propose a general method to solve the localization problem by learning a regularization matrix from the localized eigenvectors. Using matrix perturbation analysis, we demonstrate that the learned regularizations suppress down the eigenvalues associated with localized eigenvectors and enable us to recover the informative eigenvectors representing the global structure. We show applications of our method in several inference problems: community detection in networks, clustering from pairwise similarities, rank estimation and matrix completion problems. Using extensive experiments, we illustrate that our method solves the localization problem and works down to the theoretical detectability limits in different kinds of synthetic data. This is in contrast with existing spectral algorithms based on data matrix, non-backtracking matrix, Laplacians and those with rank-one regularizations, which perform poorly in the sparse case with noise.
Tasks	Community Detection, Matrix Completion
Published	2016-09-09
URL	http://arxiv.org/abs/1609.02906v1
PDF	http://arxiv.org/pdf/1609.02906v1.pdf
PWC	https://paperswithcode.com/paper/robust-spectral-detection-of-global
Repo
Framework

Semantic Parsing of Mathematics by Context-based Learning from Aligned Corpora and Theorem Proving


Title	Semantic Parsing of Mathematics by Context-based Learning from Aligned Corpora and Theorem Proving
Authors	Cezary Kaliszyk, Josef Urban, Jiří Vyskočil
Abstract	We study methods for automated parsing of informal mathematical expressions into formal ones, a main prerequisite for deep computer understanding of informal mathematical texts. We propose a context-based parsing approach that combines efficient statistical learning of deep parse trees with their semantic pruning by type checking and large-theory automated theorem proving. We show that the methods very significantly improve on previous results in parsing theorems from the Flyspeck corpus.
Tasks	Automated Theorem Proving, Semantic Parsing
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09703v1
PDF	http://arxiv.org/pdf/1611.09703v1.pdf
PWC	https://paperswithcode.com/paper/semantic-parsing-of-mathematics-by-context
Repo
Framework

A Light-powered, Always-On, Smart Camera with Compressed Domain Gesture Detection


Title	A Light-powered, Always-On, Smart Camera with Compressed Domain Gesture Detection
Authors	Anvesha A, Shaojie Xu, Ningyuan Cao, Justin Romberg, Arijit Raychowdhury
Abstract	In this paper we propose an energy-efficient camera-based gesture recognition system powered by light energy for “always on” applications. Low energy consumption is achieved by directly extracting gesture features from the compressed measurements, which are the block averages and the linear combinations of the image sensor’s pixel values. The gestures are recognized using a nearest-neighbour (NN) classifier followed by Dynamic Time Warping (DTW). The system has been implemented on an Analog Devices Black Fin ULP vision processor and powered by PV cells whose output is regulated by TI’s DC-DC buck converter with Maximum Power Point Tracking (MPPT). Measured data reveals that with only 400 compressed measurements (768x compression ratio) per frame, the system is able to recognize key wake-up gestures with greater than 80% accuracy and only 95mJ of energy per frame. Owing to its fully self-powered operation, the proposed system can find wide applications in “always-on” vision systems such as in surveillance, robotics and consumer electronics with touch-less operation.
Tasks	Gesture Recognition
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08313v2
PDF	http://arxiv.org/pdf/1605.08313v2.pdf
PWC	https://paperswithcode.com/paper/a-light-powered-always-on-smart-camera-with
Repo
Framework

Neural Morphological Tagging from Characters for Morphologically Rich Languages


Title	Neural Morphological Tagging from Characters for Morphologically Rich Languages
Authors	Georg Heigold, Guenter Neumann, Josef van Genabith
Abstract	This paper investigates neural character-based morphological tagging for languages with complex morphology and large tag sets. We systematically explore a variety of neural architectures (DNN, CNN, CNNHighway, LSTM, BLSTM) to obtain character-based word vectors combined with bidirectional LSTMs to model across-word context in an end-to-end setting. We explore supplementary use of word-based vectors trained on large amounts of unlabeled data. Our experiments for morphological tagging suggest that for “simple” model configurations, the choice of the network architecture (CNN vs. CNNHighway vs. LSTM vs. BLSTM) or the augmentation with pre-trained word embeddings can be important and clearly impact the accuracy. Increasing the model capacity by adding depth, for example, and carefully optimizing the neural networks can lead to substantial improvements, and the differences in accuracy (but not training time) become much smaller or even negligible. Overall, our best morphological taggers for German and Czech outperform the best results reported in the literature by a large margin.
Tasks	Morphological Tagging, Word Embeddings
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06640v1
PDF	http://arxiv.org/pdf/1606.06640v1.pdf
PWC	https://paperswithcode.com/paper/neural-morphological-tagging-from-characters
Repo
Framework

System-Generated Requests for Rewriting Proposals


Title	System-Generated Requests for Rewriting Proposals
Authors	Pietro Speroni di Fenizio, Cyril Velikanov
Abstract	We present an online deliberation system using mutual evaluation in order to collaboratively develop solutions. Participants submit their proposals and evaluate each other’s proposals; some of them may then be invited by the system to rewrite ‘problematic’ proposals. Two cases are discussed: a proposal supported by many, but not by a given person, who is then invited to rewrite it for making yet more acceptable; and a poorly presented but presumably interesting proposal. The first of these cases has been successfully implemented. Proposals are evaluated along two axes-understandability (or clarity, or, more generally, quality), and agreement. The latter is used by the system to cluster proposals according to their ideas, while the former is used both to present the best proposals on top of their clusters, and to find poorly written proposals candidates for rewriting. These functionalities may be considered as important components of a large scale online deliberation system.
Tasks
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10095v1
PDF	http://arxiv.org/pdf/1611.10095v1.pdf
PWC	https://paperswithcode.com/paper/system-generated-requests-for-rewriting
Repo
Framework

Multi-velocity neural networks for gesture recognition in videos


Title	Multi-velocity neural networks for gesture recognition in videos
Authors	Otkrist Gupta, Dan Raviv, Ramesh Raskar
Abstract	We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification. While deep neural networks have reached maturity for image understanding tasks, we are still exploring network topologies and features to handle the richer environment of video clips. Here, we tackle the problem of multiple velocities in action recognition, and provide state-of-the-art results for gesture recognition, on known and new collected datasets. We further provide the training steps for our semi-supervised network, suited to learn from huge unlabeled datasets with only a fraction of labeled examples.
Tasks	Gesture Recognition, Temporal Action Localization
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06829v1
PDF	http://arxiv.org/pdf/1603.06829v1.pdf
PWC	https://paperswithcode.com/paper/multi-velocity-neural-networks-for-gesture
Repo
Framework

Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition


Title	Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
Authors	Changxing Ding, Dacheng Tao
Abstract	Human faces in surveillance videos often suffer from severe image blur, dramatic pose variations, and occlusion. In this paper, we propose a comprehensive framework based on Convolutional Neural Networks (CNN) to overcome challenges in video-based face recognition (VFR). First, to learn blur-robust face representations, we artificially blur training data composed of clear still images to account for a shortfall in real-world video training data. Using training data composed of both still images and artificially blurred data, CNN is encouraged to learn blur-insensitive features automatically. Second, to enhance robustness of CNN features to pose variations and occlusion, we propose a Trunk-Branch Ensemble CNN model (TBE-CNN), which extracts complementary information from holistic face images and patches cropped around facial components. TBE-CNN is an end-to-end model that extracts features efficiently by sharing the low- and middle-level convolutional layers between the trunk and branch networks. Third, to further promote the discriminative power of the representations learnt by TBE-CNN, we propose an improved triplet loss function. Systematic experiments justify the effectiveness of the proposed techniques. Most impressively, TBE-CNN achieves state-of-the-art performance on three popular video face databases: PaSC, COX Face, and YouTube Faces. With the proposed techniques, we also obtain the first place in the BTAS 2016 Video Person Recognition Evaluation.
Tasks	Face Recognition, Person Recognition
Published	2016-07-19
URL	http://arxiv.org/abs/1607.05427v2
PDF	http://arxiv.org/pdf/1607.05427v2.pdf
PWC	https://paperswithcode.com/paper/trunk-branch-ensemble-convolutional-neural
Repo
Framework

BET on Independence


Title	BET on Independence
Authors	Kai Zhang
Abstract	We study the problem of nonparametric dependence detection. Many existing methods may suffer severe power loss due to non-uniform consistency, which we illustrate with a paradox. To avoid such power loss, we approach the nonparametric test of independence through the new framework of binary expansion statistics (BEStat) and binary expansion testing (BET), which examine dependence through a novel binary expansion filtration approximation of the copula. Through a Hadamard transform, we find that the symmetry statistics in the filtration are complete sufficient statistics for dependence. These statistics are also uncorrelated under the null. By utilizing symmetry statistics, the BET avoids the problem of non-uniform consistency and improves upon a wide class of commonly used methods (a) by achieving the minimax rate in sample size requirement for reliable power and (b) by providing clear interpretations of global relationships upon rejection of independence. The binary expansion approach also connects the symmetry statistics with the current computing system to facilitate efficient bitwise implementation. We illustrate the BET with a study of the distribution of stars in the night sky and with an exploratory data analysis of the TCGA breast cancer data.
Tasks
Published	2016-10-17
URL	http://arxiv.org/abs/1610.05246v7
PDF	http://arxiv.org/pdf/1610.05246v7.pdf
PWC	https://paperswithcode.com/paper/bet-on-independence
Repo
Framework

Psychologically Motivated Text Mining


Title	Psychologically Motivated Text Mining
Authors	Ekaterina Shutova, Patricia Lichtenstein
Abstract	Natural language processing techniques are increasingly applied to identify social trends and predict behavior based on large text collections. Existing methods typically rely on surface lexical and syntactic information. Yet, research in psychology shows that patterns of human conceptualisation, such as metaphorical framing, are reliable predictors of human expectations and decisions. In this paper, we present a method to learn patterns of metaphorical framing from large text collections, using statistical techniques. We apply the method to data in three different languages and evaluate the identified patterns, demonstrating their psychological validity.
Tasks
Published	2016-09-28
URL	http://arxiv.org/abs/1609.09019v1
PDF	http://arxiv.org/pdf/1609.09019v1.pdf
PWC	https://paperswithcode.com/paper/psychologically-motivated-text-mining
Repo
Framework

Fast calculation of correlations in recognition systems


Title	Fast calculation of correlations in recognition systems
Authors	Pavel Dourbal, Mikhail Pekker
Abstract	Computationally efficient classification system architecture is proposed. It utilizes fast tensor-vector multiplication algorithm to apply linear operators upon input signals . The approach is applicable to wide variety of recognition system architectures ranging from single stage matched filter bank classifiers to complex neural networks with unlimited number of hidden layers.
Tasks
Published	2016-03-06
URL	http://arxiv.org/abs/1603.01772v1
PDF	http://arxiv.org/pdf/1603.01772v1.pdf
PWC	https://paperswithcode.com/paper/fast-calculation-of-correlations-in
Repo
Framework