October 18, 2019

2854 words 14 mins read

Paper Group ANR 574

Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition. High Dimensional Robust Sparse Regression. Robust pose tracking with a joint model of appearance and shape. Multilayer Network Model of Movie Script. Small Organ Segmentation in Whole-body MRI using a Two-stage FCN and Weighting Schemes. On a hypergraph probabilist …

Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition


Title	Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition
Authors	Christopher Dane Shulby, Leonardo Pombal, Vitor Jordão, Guilherme Ziolle, Bruno Martho, Antônio Postal, Thiago Prochnow
Abstract	Violence is an epidemic in Brazil and a problem on the rise world-wide. Mobile devices provide communication technologies which can be used to monitor and alert about violent situations. However, current solutions, like panic buttons or safe words, might increase the loss of life in violent situations. We propose an embedded artificial intelligence solution, using natural language and speech processing technology, to silently alert someone who can help in this situation. The corpus used contains 400 positive phrases and 800 negative phrases, totaling 1,200 sentences which are classified using two well-known extraction methods for natural language processing tasks: bag-of-words and word embeddings and classified with a support vector machine. We describe the proof-of-concept product in development with promising results, indicating a path towards a commercial product. More importantly we show that model improvements via word embeddings and data augmentation techniques provide an intrinsically robust model. The final embedded solution also has a small footprint of less than 10 MB.
Tasks	Data Augmentation, Speech Recognition, Word Embeddings
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09431v1
PDF	http://arxiv.org/pdf/1810.09431v1.pdf
PWC	https://paperswithcode.com/paper/proactive-security-embedded-ai-solution-for
Repo
Framework

High Dimensional Robust Sparse Regression


Title	High Dimensional Robust Sparse Regression
Authors	Liu Liu, Yanyao Shen, Tianyang Li, Constantine Caramanis
Abstract	We provide a novel – and to the best of our knowledge, the first – algorithm for high dimensional sparse regression with constant fraction of corruptions in explanatory and/or response variables. Our algorithm recovers the true sparse parameters with sub-linear sample complexity, in the presence of a constant fraction of arbitrary corruptions. Our main contribution is a robust variant of Iterative Hard Thresholding. Using this, we provide accurate estimators: when the covariance matrix in sparse regression is identity, our error guarantee is near information-theoretically optimal. We then deal with robust sparse regression with unknown structured covariance matrix. We propose a filtering algorithm which consists of a novel randomized outlier removal technique for robust sparse mean estimation that may be of interest in its own right: the filtering algorithm is flexible enough to deal with unknown covariance. Also, it is orderwise more efficient computationally than the ellipsoid algorithm. Using sub-linear sample complexity, our algorithm achieves the best known (and first) error guarantee. We demonstrate the effectiveness on large-scale sparse regression problems with arbitrary corruptions.
Tasks
Published	2018-05-29
URL	https://arxiv.org/abs/1805.11643v3
PDF	https://arxiv.org/pdf/1805.11643v3.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-robust-sparse-regression
Repo
Framework

Robust pose tracking with a joint model of appearance and shape


Title	Robust pose tracking with a joint model of appearance and shape
Authors	Yuliang Guo, Lakshmi Narasimhan Govindarajan, Benjamin Kimia, Thomas Serre
Abstract	We present a novel approach for estimating the 2D pose of an articulated object with an application to automated video analysis of small laboratory animals. We have found that deformable part models developed for humans, exemplified by the flexible mixture of parts (FMP) model, typically fail on challenging animal poses. We argue that beyond encoding appearance and spatial relations, shape is needed to overcome the lack of distinctive landmarks on laboratory animal bodies. In our approach, a shape consistent FMP (scFMP) model computes promising pose candidates after a standard FMP model is used to rapidly discard false part detections. This “cascaded” approach combines the relative strengths of spatial-relations, appearance and shape representations and is shown to yield significant improvements over the original FMP model as well as a representative deep neural network baseline.
Tasks	Pose Tracking
Published	2018-06-28
URL	http://arxiv.org/abs/1806.11011v1
PDF	http://arxiv.org/pdf/1806.11011v1.pdf
PWC	https://paperswithcode.com/paper/robust-pose-tracking-with-a-joint-model-of
Repo
Framework

Multilayer Network Model of Movie Script


Title	Multilayer Network Model of Movie Script
Authors	Youssef Mourchid, Benjamin Renoust, Hocine Cherifi, Mohammed El Hassouni
Abstract	Network models have been increasingly used in the past years to support summarization and analysis of narratives, such as famous TV series, books and news. Inspired by social network analysis, most of these models focus on the characters at play. The network model well captures all characters interactions, giving a broad picture of the narration’s content. A few works went beyond by introducing additional semantic elements, always captured in a single layer network. In contrast, we introduce in this work a multilayer network model to capture more elements of the narration of a movie from its script: people, locations, and other semantic elements. This model enables new measures and insights on movies. We demonstrate this model on two very popular movies.
Tasks
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05718v1
PDF	http://arxiv.org/pdf/1812.05718v1.pdf
PWC	https://paperswithcode.com/paper/multilayer-network-model-of-movie-script
Repo
Framework

Small Organ Segmentation in Whole-body MRI using a Two-stage FCN and Weighting Schemes


Title	Small Organ Segmentation in Whole-body MRI using a Two-stage FCN and Weighting Schemes
Authors	Vanya V. Valindria, Ioannis Lavdas, Juan Cerrolaza, Eric O. Aboagye, Andrea G. Rockall, Daniel Rueckert, Ben Glocker
Abstract	Accurate and robust segmentation of small organs in whole-body MRI is difficult due to anatomical variation and class imbalance. Recent deep network based approaches have demonstrated promising performance on abdominal multi-organ segmentations. However, the performance on small organs is still suboptimal as these occupy only small regions of the whole-body volumes with unclear boundaries and variable shapes. A coarse-to-fine, hierarchical strategy is a common approach to alleviate this problem, however, this might miss useful contextual information. We propose a two-stage approach with weighting schemes based on auto-context and spatial atlas priors. Our experiments show that the proposed approach can boost the segmentation accuracy of multiple small organs in whole-body MRI scans.
Tasks
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11368v1
PDF	http://arxiv.org/pdf/1807.11368v1.pdf
PWC	https://paperswithcode.com/paper/small-organ-segmentation-in-whole-body-mri
Repo
Framework

On a hypergraph probabilistic graphical model


Title	On a hypergraph probabilistic graphical model
Authors	Mohammad Ali Javidian, Linyuan Lu, Marco Valtorta, Zhiyu Wang
Abstract	We propose a directed acyclic hypergraph framework for a probabilistic graphical model that we call Bayesian hypergraphs. The space of directed acyclic hypergraphs is much larger than the space of chain graphs. Hence Bayesian hypergraphs can model much finer factorizations than Bayesian networks or LWF chain graphs and provide simpler and more computationally efficient procedures for factorizations and interventions. Bayesian hypergraphs also allow a modeler to represent causal patterns of interaction such as Noisy-OR graphically (without additional annotations). We introduce global, local and pairwise Markov properties of Bayesian hypergraphs and prove under which conditions they are equivalent. We define a projection operator, called shadow, that maps Bayesian hypergraphs to chain graphs, and show that the Markov properties of a Bayesian hypergraph are equivalent to those of its corresponding chain graph. We extend the causal interpretation of LWF chain graphs to Bayesian hypergraphs and provide corresponding formulas and a graphical criterion for intervention.
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08372v1
PDF	http://arxiv.org/pdf/1811.08372v1.pdf
PWC	https://paperswithcode.com/paper/on-a-hypergraph-probabilistic-graphical-model
Repo
Framework

A First Analysis of Kernels for Kriging-based Optimization in Hierarchical Search Spaces


Title	A First Analysis of Kernels for Kriging-based Optimization in Hierarchical Search Spaces
Authors	Martin Zaefferer, Daniel Horn
Abstract	Many real-world optimization problems require significant resources for objective function evaluations. This is a challenge to evolutionary algorithms, as it limits the number of available evaluations. One solution are surrogate models, which replace the expensive objective. A particular issue in this context are hierarchical variables. Hierarchical variables only influence the objective function if other variables satisfy some condition. We study how this kind of hierarchical structure can be integrated into the model based optimization framework. We discuss an existing kernel and propose alternatives. An artificial test function is used to investigate how different kernels and assumptions affect model quality and search performance.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01011v1
PDF	http://arxiv.org/pdf/1807.01011v1.pdf
PWC	https://paperswithcode.com/paper/a-first-analysis-of-kernels-for-kriging-based
Repo
Framework

Canonical and Compact Point Cloud Representation for Shape Classification


Title	Canonical and Compact Point Cloud Representation for Shape Classification
Authors	Kent Fujiwara, Ikuro Sato, Mitsuru Ambai, Yuichi Yoshida, Yoshiaki Sakakura
Abstract	We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation. The key idea is to parametrize a distance field around an individual shape into a unique, canonical, and compact vector in an unsupervised manner. We firstly project a distance field to a $4$D canonical space using singular value decomposition. We then train a neural network for each instance to non-linearly embed its distance field into network parameters. We employ a bias-free Extreme Learning Machine (ELM) with ReLU activation units, which has scale-factor commutative property between layers. We demonstrate the descriptiveness of the instance-wise, shape-embedded network parameters by using them to classify shapes in $3$D datasets. Our learning-based representation requires minimal augmentation and simple neural networks, where previous approaches demand numerous representations to handle coordinate change and point permutation.
Tasks
Published	2018-09-13
URL	http://arxiv.org/abs/1809.04820v1
PDF	http://arxiv.org/pdf/1809.04820v1.pdf
PWC	https://paperswithcode.com/paper/canonical-and-compact-point-cloud
Repo
Framework

Contextual Language Model Adaptation for Conversational Agents


Title	Contextual Language Model Adaptation for Conversational Agents
Authors	Anirudh Raju, Behnam Hedayatnia, Linda Liu, Ankur Gandhe, Chandra Khatri, Angeliki Metallinou, Anu Venkatesh, Ariya Rastrow
Abstract	Statistical language models (LM) play a key role in Automatic Speech Recognition (ASR) systems used by conversational agents. These ASR systems should provide a high accuracy under a variety of speaking styles, domains, vocabulary and argots. In this paper, we present a DNN-based method to adapt the LM to each user-agent interaction based on generalized contextual information, by predicting an optimal, context-dependent set of LM interpolation weights. We show that this framework for contextual adaptation provides accuracy improvements under different possible mixture LM partitions that are relevant for both (1) Goal-oriented conversational agents where it’s natural to partition the data by the requested application and for (2) Non-goal oriented conversational agents where the data can be partitioned using topic labels that come from predictions of a topic classifier. We obtain a relative WER improvement of 3% with a 1-pass decoding strategy and 6% in a 2-pass decoding framework, over an unadapted model. We also show up to a 15% relative improvement in recognizing named entities which is of significant value for conversational ASR systems.
Tasks	Language Modelling, Speech Recognition
Published	2018-06-26
URL	http://arxiv.org/abs/1806.10215v4
PDF	http://arxiv.org/pdf/1806.10215v4.pdf
PWC	https://paperswithcode.com/paper/contextual-language-model-adaptation-for
Repo
Framework

A Bit Too Much? High Speed Imaging from Sparse Photon Counts


Title	A Bit Too Much? High Speed Imaging from Sparse Photon Counts
Authors	Paramanand Chandramouli, Samuel Burri, Claudio Bruschini, Edoardo Charbon, Andreas Kolb
Abstract	Recent advances in photographic sensing technologies have made it possible to achieve light detection in terms of a single photon. Photon counting sensors are being increasingly used in many diverse applications. We address the problem of jointly recovering spatial and temporal scene radiance from very few photon counts. Our ConvNet-based scheme effectively combines spatial and temporal information present in measurements to reduce noise. We demonstrate that using our method one can acquire videos at a high frame rate and still achieve good quality signal-to-noise ratio. Experiments show that the proposed scheme performs quite well in different challenging scenarios while the existing approaches are unable to handle them.
Tasks
Published	2018-11-06
URL	https://arxiv.org/abs/1811.02396v3
PDF	https://arxiv.org/pdf/1811.02396v3.pdf
PWC	https://paperswithcode.com/paper/a-little-bit-too-much-high-speed-imaging-from
Repo
Framework

Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld


Title	Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
Authors	Sicheng Zhao, Bichen Wu, Joseph Gonzalez, Sanjit A. Seshia, Kurt Keutzer
Abstract	Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled target domain. Unfortunately, direct transfer across domains often performs poorly due to domain shift and dataset bias. Domain adaptation is the machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this paper, we summarize and compare the latest unsupervised domain adaptation methods in computer vision applications. We classify the non-deep approaches into sample re-weighting and intermediate subspace transformation categories, while the deep strategy includes discrepancy-based methods, adversarial generative models, adversarial discriminative models and reconstruction-based methods. We also discuss some potential directions.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2018-03-24
URL	http://arxiv.org/abs/1803.09180v1
PDF	http://arxiv.org/pdf/1803.09180v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-from
Repo
Framework

Learning to Focus when Ranking Answers


Title	Learning to Focus when Ranking Answers
Authors	Dana Sagi, Tzoof Avny, Kira Radinsky, Eugene Agichtein
Abstract	One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm. To achieve this representation, the conventional state of the art approaches perform extensive feature engineering that encode the similarity of the query-answer pair. Recently, deep-learning solutions have shown that it is possible to achieve comparable performance, in some settings, by learning the similarity representation directly from data. Unfortunately, previous models perform poorly on longer texts, or on texts with significant portion of irrelevant information, or which are grammatically incorrect. To overcome these limitations, we propose a novel ranking algorithm for question answering, QARAT, which uses an attention mechanism to learn on which words and phrases to focus when building the mutual representation. We demonstrate superior ranking performance on several real-world question-answer ranking datasets, and provide visualization of the attention mechanism to otter more insights into how our models of attention could benefit ranking for difficult question answering challenges.
Tasks	Feature Engineering, Learning-To-Rank, Question Answering
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02724v1
PDF	http://arxiv.org/pdf/1808.02724v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-focus-when-ranking-answers
Repo
Framework

Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning


Title	Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning
Authors	Melvin Wong, Bilal Farooq
Abstract	In this paper, we implement an information-theoretic approach to travel behaviour analysis by introducing a generative modelling framework to identify informative latent characteristics in travel decision making. It involves developing a joint tri-partite Bayesian graphical network model using a Restricted Boltzmann Machine (RBM) generative modelling framework. We apply this framework on a mode choice survey data to identify abstract latent variables and compare the performance with a traditional latent variable model with specific latent preferences – safety, comfort, and environmental. Data collected from a joint stated and revealed preference mode choice survey in Quebec, Canada were used to calibrate the RBM model. Results show that a signficant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.
Tasks	Decision Making
Published	2018-09-15
URL	http://arxiv.org/abs/1809.05781v1
PDF	http://arxiv.org/pdf/1809.05781v1.pdf
PWC	https://paperswithcode.com/paper/modelling-latent-travel-behaviour
Repo
Framework

Counterfactual Fairness in Text Classification through Robustness


Title	Counterfactual Fairness in Text Classification through Robustness
Authors	Sahaj Garg, Vincent Perot, Nicole Limtiaco, Ankur Taly, Ed H. Chi, Alex Beutel
Abstract	In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the example were different? Toxicity classifiers demonstrate a counterfactual fairness issue by predicting that “Some people are gay” is toxic while “Some people are straight” is nontoxic. We offer a metric, counterfactual token fairness (CTF), for measuring this particular form of fairness in text classifiers, and describe its relationship with group fairness. Further, we offer three approaches, blindness, counterfactual augmentation, and counterfactual logit pairing (CLP), for optimizing counterfactual token fairness during training, bridging the robustness and fairness literature. Empirically, we find that blindness and CLP address counterfactual token fairness. The methods do not harm classifier performance, and have varying tradeoffs with group fairness. These approaches, both for measurement and optimization, provide a new path forward for addressing fairness concerns in text classification.
Tasks	Text Classification
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10610v2
PDF	http://arxiv.org/pdf/1809.10610v2.pdf
PWC	https://paperswithcode.com/paper/counterfactual-fairness-in-text
Repo
Framework

Rare Feature Selection in High Dimensions


Title	Rare Feature Selection in High Dimensions
Authors	Xiaohan Yan, Jacob Bien
Abstract	It is common in modern prediction problems for many predictor variables to be counts of rarely occurring events. This leads to design matrices in which many columns are highly sparse. The challenge posed by such “rare features” has received little attention despite its prevalence in diverse areas, ranging from natural language processing (e.g., rare words) to biology (e.g., rare species). We show, both theoretically and empirically, that not explicitly accounting for the rareness of features can greatly reduce the effectiveness of an analysis. We next propose a framework for aggregating rare features into denser features in a flexible manner that creates better predictors of the response. Our strategy leverages side information in the form of a tree that encodes feature similarity. We apply our method to data from TripAdvisor, in which we predict the numerical rating of a hotel based on the text of the associated review. Our method achieves high accuracy by making effective use of rare words; by contrast, the lasso is unable to identify highly predictive words if they are too rare. A companion R package, called rare, implements our new estimator, using the alternating direction method of multipliers.
Tasks	Feature Selection
Published	2018-03-18
URL	http://arxiv.org/abs/1803.06675v1
PDF	http://arxiv.org/pdf/1803.06675v1.pdf
PWC	https://paperswithcode.com/paper/rare-feature-selection-in-high-dimensions
Repo
Framework