January 30, 2020

3288 words 16 mins read

Paper Group ANR 331

Towards automatic estimation of conversation floors within F-formations. Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder. Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS. Modal-aware Features for Multimodal Hashing. Procedure Planning in Instructional Videos. Feature-Model-Gu …

Towards automatic estimation of conversation floors within F-formations


Title	Towards automatic estimation of conversation floors within F-formations
Authors	Chirag Raman, Hayley Hung
Abstract	The detection of free-standing conversing groups has received significant attention in recent years. In the absence of a formal definition, most studies operationalize the notion of a conversation group either through a spatial or a temporal lens. Spatially, the most commonly used representation is the F-formation, defined by social scientists as the configuration in which people arrange themselves to sustain an interaction. However, the use of this representation is often accompanied with the simplifying assumption that a single conversation occurs within an F-formation. Temporally, various categories have been used to organize conversational units; these include, among others, turn, topic, and floor. Some of these concepts are hard to define objectively by themselves. The present work constitutes an initial exploration into unifying these perspectives by primarily posing the question: can we use the observation of simultaneous speaker turns to infer whether multiple conversation floors exist within an F-formation? We motivate a metric for the existence of distinct conversation floors based on simultaneous speaker turns, and provide an analysis using this metric to characterize conversations across F-formations of varying cardinality. We contribute two key findings: firstly, at the average speaking turn duration of about two seconds for humans, there is evidence for the existence of multiple floors within an F-formation; and secondly, an increase in the cardinality of an F-formation correlates with a decrease in duration of simultaneous speaking turns.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.10384v2
PDF	https://arxiv.org/pdf/1907.10384v2.pdf
PWC	https://paperswithcode.com/paper/towards-automatic-estimation-of-conversation
Repo
Framework

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder


Title	Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder
Authors	Kara Lamb, Garima Malhotra, Athanasios Vlontzos, Edward Wagstaff, Atılım Günes Baydin, Anahita Bhiwandiwalla, Yarin Gal, Alfredo Kalaitzis, Anthony Reina, Asti Bhatt
Abstract	High energy particles originating from solar activity travel along the the Earth’s magnetic field and interact with the atmosphere around the higher latitudes. These interactions often manifest as aurora in the form of visible light in the Earth’s ionosphere. These interactions also result in irregularities in the electron density, which cause disruptions in the amplitude and phase of the radio signals from the Global Navigation Satellite Systems (GNSS), known as ‘scintillation’. In this paper we use a multi-scale residual autoencoder (Res-AE) to show the correlation between specific dynamic structures of the aurora and the magnitude of the GNSS phase scintillations ($\sigma_{\phi}$). Auroral images are encoded in a lower dimensional feature space using the Res-AE, which in turn are clustered with t-SNE and UMAP. Both methods produce similar clusters, and specific clusters demonstrate greater correlations with observed phase scintillations. Our results suggest that specific dynamic structures of auroras are highly correlated with GNSS phase scintillations.
Tasks
Published	2019-10-04
URL	https://arxiv.org/abs/1910.03085v1
PDF	https://arxiv.org/pdf/1910.03085v1.pdf
PWC	https://paperswithcode.com/paper/correlation-of-auroral-dynamics-and-gnss
Repo
Framework

Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS


Title	Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS
Authors	Nicolas Scheiner, Nils Appenrodt, Jürgen Dickmann, Bernhard Sick
Abstract	Annotating automotive radar data is a difficult task. This article presents an automated way of acquiring data labels which uses a highly accurate and portable global navigation satellite system (GNSS). The proposed system is discussed besides a revision of other label acquisitions techniques and a problem description of manual data annotation. The article concludes with a systematic comparison of conventional hand labeling and automatic data acquisition. The results show clear advantages of the proposed method without a relevant loss in labeling accuracy. Minor changes can be observed in the measured radar data, but the so introduced bias of the GNSS reference is clearly outweighed by the indisputable time savings. Beside data annotation, the proposed system can also provide a ground truth for validating object tracking or other automated driving system applications.
Tasks	Object Tracking
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11219v1
PDF	https://arxiv.org/pdf/1905.11219v1.pdf
PWC	https://paperswithcode.com/paper/automated-ground-truth-estimation-of
Repo
Framework


Title	Modal-aware Features for Multimodal Hashing
Authors	Haien Zeng, Hanjiang Lai, Hanlu Chu, Yong Tang, Jian Yin
Abstract	Many retrieval applications can benefit from multiple modalities, e.g., text that contains images on Wikipedia, for which how to represent multimodal data is the critical component. Most deep multimodal learning methods typically involve two steps to construct the joint representations: 1) learning of multiple intermediate features, with each intermediate feature corresponding to a modality, using separate and independent deep models; 2) merging the intermediate features into a joint representation using a fusion strategy. However, in the first step, these intermediate features do not have previous knowledge of each other and cannot fully exploit the information contained in the other modalities. In this paper, we present a modal-aware operation as a generic building block to capture the non-linear dependences among the heterogeneous intermediate features that can learn the underlying correlation structures in other multimodal data as soon as possible. The modal-aware operation consists of a kernel network and an attention network. The kernel network is utilized to learn the non-linear relationships with other modalities. Then, to learn better representations for binary hash codes, we present an attention network that finds the informative regions of these modal-aware features that are favorable for retrieval. Experiments conducted on three public benchmark datasets demonstrate significant improvements in the performance of our method relative to state-of-the-art methods.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08479v1
PDF	https://arxiv.org/pdf/1911.08479v1.pdf
PWC	https://paperswithcode.com/paper/modal-aware-features-for-multimodal-hashing
Repo
Framework

Procedure Planning in Instructional Videos


Title	Procedure Planning in Instructional Videos
Authors	Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles
Abstract	In this paper, we study the problem of procedure planning in instructional videos, which can be seen as the first step towards enabling autonomous agents to plan for real-life tasks in everyday settings. The key technical challenge of planning in instructional videos is that the state and action spaces are underconstrained. We address this challenge by proposing Dual Dynamics Networks (DDN), a framework that explicitly leverages the constraints imposed by the conjugate relationships between states and actions in a learned plannable latent space. We evaluate our method on large-scale real-world instructional videos. Our experiments show that DDN learns plannable representations without explicit supervision and leads to stronger generalization compared to existing planning approaches and neural network policies.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01172v2
PDF	https://arxiv.org/pdf/1907.01172v2.pdf
PWC	https://paperswithcode.com/paper/procedure-planning-in-instructional-videos
Repo
Framework

Feature-Model-Guided Online Learning for Self-Adaptive Systems


Title	Feature-Model-Guided Online Learning for Self-Adaptive Systems
Authors	Andreas Metzger, Clément Quinton, Zoltán Ádám Mann, Luciano Baresi, Klaus Pohl
Abstract	A self-adaptive system can modify its own structure and behavior at runtime based on its perception of the environment, of itself and of its requirements. To develop a self-adaptive system, software developers codify knowledge about the system and its environment, as well as how adaptation actions impact on the system. However, the codified knowledge may be insufficient due to design time uncertainty, and thus a self-adaptive system may execute adaptation actions that do not have the desired effect. Online learning is an emerging approach to address design time uncertainty by employing machine learning at runtime. Online learning accumulates knowledge at runtime by, for instance, exploring not-yet executed adaptation actions. We address two specific problems with respect to online learning for self-adaptive systems. First, the number of possible adaptation actions can be very large. Existing online learning techniques randomly explore the possible adaptation actions, but this can lead to slow convergence of the learning process. Second, the possible adaptation actions can change as a result of system evolution. Existing online learning techniques are unaware of these changes and thus do not explore new adaptation actions, but explore adaptation actions that are no longer valid. We propose using feature models to give structure to the set of adaptation actions and thereby guide the exploration process during online learning. Experimental results involving four real-world systems suggest that considering the hierarchical structure of feature models may speed up convergence by 7.2% on average. Considering the differences between feature models before and after an evolution step may speed up convergence by 64.6% on average. […]
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09158v1
PDF	https://arxiv.org/pdf/1907.09158v1.pdf
PWC	https://paperswithcode.com/paper/feature-model-guided-online-learning-for-self
Repo
Framework

A Human-AI Loop Approach for Joint Keyword Discovery and Expectation Estimation in Micropost Event Detection


Title	A Human-AI Loop Approach for Joint Keyword Discovery and Expectation Estimation in Micropost Event Detection
Authors	Akansha Bhardwaj, Jie Yang, Philippe Cudré-Mauroux
Abstract	Microblogging platforms such as Twitter are increasingly being used in event detection. Existing approaches mainly use machine learning models and rely on event-related keywords to collect the data for model training. These approaches make strong assumptions on the distribution of the relevant micro-posts containing the keyword – referred to as the expectation of the distribution – and use it as a posterior regularization parameter during model training. Such approaches are, however, limited as they fail to reliably estimate the informativeness of a keyword and its expectation for model training. This paper introduces a Human-AI loop approach to jointly discover informative keywords for model training while estimating their expectation. Our approach iteratively leverages the crowd to estimate both keyword specific expectation and the disagreement between the crowd and the model in order to discover new keywords that are most beneficial for model training. These keywords and their expectation not only improve the resulting performance but also make the model training process more transparent. We empirically demonstrate the merits of our approach, both in terms of accuracy and interpretability, on multiple real-world datasets and show that our approach improves the state of the art by 24.3%.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00667v1
PDF	https://arxiv.org/pdf/1912.00667v1.pdf
PWC	https://paperswithcode.com/paper/a-human-ai-loop-approach-for-joint-keyword
Repo
Framework

Machine Learning Optimization Algorithms & Portfolio Allocation


Title	Machine Learning Optimization Algorithms & Portfolio Allocation
Authors	Sarah Perrin, Thierry Roncalli
Abstract	Portfolio optimization emerged with the seminal paper of Markowitz (1952). The original mean-variance framework is appealing because it is very efficient from a computational point of view. However, it also has one well-established failing since it can lead to portfolios that are not optimal from a financial point of view. Nevertheless, very few models have succeeded in providing a real alternative solution to the Markowitz model. The main reason lies in the fact that most academic portfolio optimization models are intractable in real life although they present solid theoretical properties. By intractable we mean that they can be implemented for an investment universe with a small number of assets using a lot of computational resources and skills, but they are unable to manage a universe with dozens or hundreds of assets. However, the emergence and the rapid development of robo-advisors means that we need to rethink portfolio optimization and go beyond the traditional mean-variance optimization approach. Another industry has faced similar issues concerning large-scale optimization problems. Machine learning has long been associated with linear and logistic regression models. Again, the reason was the inability of optimization algorithms to solve high-dimensional industrial problems. Nevertheless, the end of the 1990s marked an important turning point with the development and the rediscovery of several methods that have since produced impressive results. The goal of this paper is to show how portfolio allocation can benefit from the development of these large-scale optimization algorithms. Not all of these algorithms are useful in our case, but four of them are essential when solving complex portfolio optimization problems. These four algorithms are the coordinate descent, the alternating direction method of multipliers, the proximal gradient method and the Dykstra’s algorithm.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10233v1
PDF	https://arxiv.org/pdf/1909.10233v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-optimization-algorithms
Repo
Framework

A Note on Optimal Sampling Strategy for Structural Variant Detection Using Optical Mapping


Title	A Note on Optimal Sampling Strategy for Structural Variant Detection Using Optical Mapping
Authors	Weiwei Li, Jan Hannig, Corbin Jones
Abstract	Structural variants compose the majority of human genetic variation, but are difficult to assess using current genomic sequencing technologies. Optical mapping technologies, which measure the size of chromosomal fragments between labeled markers, offer an alternative approach. As these technologies mature towards becoming clinical tools, there is a need to develop an approach for determining the optimal strategy for sampling biological material in order to detect a variant at some threshold. Here we develop an optimization approach using a simple, yet realistic, model of the genomic mapping process using a hyper-geometric distribution and {probabilistic} concentration inequalities. Our approach is both computationally and analytically tractable and includes a novel approach to getting tail bounds of hyper-geometric distribution. We show that if a genomic mapping technology can sample most of the chromosomal fragments within a sample, comparatively little biological material is needed to detect a variant at high confidence.
Tasks
Published	2019-10-04
URL	https://arxiv.org/abs/1910.04067v1
PDF	https://arxiv.org/pdf/1910.04067v1.pdf
PWC	https://paperswithcode.com/paper/a-note-on-optimal-sampling-strategy-for
Repo
Framework

Exhaustive Exact String Matching: The Analysis of the Full Human Genome


Title	Exhaustive Exact String Matching: The Analysis of the Full Human Genome
Authors	Konstantinos F. Xylogiannopoulos
Abstract	Exact string matching has been a fundamental problem in computer science for decades because of many practical applications. Some are related to common procedures, such as searching in files and text editors, or, more recently, to more advanced problems such as pattern detection in Artificial Intelligence and Bioinformatics. Tens of algorithms and methodologies have been developed for pattern matching and several programming languages, packages, applications and online systems exist that can perform exact string matching in biological sequences. These techniques, however, are limited to searching for specific and predefined strings in a sequence. In this paper a novel methodology (called Ex2SM) is presented, which is a pipeline of execution of advanced data structures and algorithms, explicitly designed for text mining, that can detect every possible repeated string in multivariate biological sequences. In contrast to known algorithms in literature, the methodology presented here is string agnostic, i.e., it does not require an input string to search for it, rather it can detect every string that exists at least twice, regardless of its attributes such as length, frequency, alphabet, overlapping etc. The complexity of the problem solved and the potential of the proposed methodology is demonstrated with the experimental analysis performed on the entire human genome. More specifically, all repeated strings with a length of up to 50 characters have been detected, an achievement which is practically impossible using other algorithms due to the exponential number of possible permutations of such long strings.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.11232v1
PDF	https://arxiv.org/pdf/1907.11232v1.pdf
PWC	https://paperswithcode.com/paper/exhaustive-exact-string-matching-the-analysis
Repo
Framework

Induction of Non-monotonic Logic Programs To Explain Statistical Learning Models


Title	Induction of Non-monotonic Logic Programs To Explain Statistical Learning Models
Authors	Farhad Shakerin
Abstract	We present a fast and scalable algorithm to induce non-monotonic logic programs from statistical learning models. We reduce the problem of search for best clauses to instances of the High-Utility Itemset Mining (HUIM) problem. In the HUIM problem, feature values and their importance are treated as transactions and utilities respectively. We make use of TreeExplainer, a fast and scalable implementation of the Explainable AI tool SHAP, to extract locally important features and their weights from ensemble tree models. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics and running time of the training algorithm compared to ALEPH, a state-of-the-art Inductive Logic Programming (ILP) system.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.09017v1
PDF	https://arxiv.org/pdf/1909.09017v1.pdf
PWC	https://paperswithcode.com/paper/induction-of-non-monotonic-logic-programs-to-1
Repo
Framework

On Target Shift in Adversarial Domain Adaptation


Title	On Target Shift in Adversarial Domain Adaptation
Authors	Yitong Li, Michael Murias, Samantha Major, Geraldine Dawson, David E. Carlson
Abstract	Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each class is different between domains, has received less attention. Label shift naturally arises in many contexts, especially in behavioral studies where the behaviors are freely chosen. In this work, we propose a method called Domain Adversarial nets for Target Shift (DATS) to address label shift while learning a domain invariant representation. This is accomplished by using distribution matching to estimate label proportions in a blind test set. We extend this framework to handle multiple domains by developing a scheme to upweight source domains most similar to the target domain. Empirical results show that this framework performs well under large label shift in synthetic and real experiments, demonstrating the practical importance.
Tasks	Domain Adaptation
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06336v1
PDF	http://arxiv.org/pdf/1903.06336v1.pdf
PWC	https://paperswithcode.com/paper/on-target-shift-in-adversarial-domain
Repo
Framework

Live Face De-Identification in Video


Title	Live Face De-Identification in Video
Authors	Oran Gafni, Lior Wolf, Yaniv Taigman
Abstract	We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having the perception (pose, illumination and expression) fixed. We achieve this by a novel feed-forward encoder-decoder network architecture that is conditioned on the high-level representation of a person’s facial image. The network is global, in the sense that it does not need to be retrained for a given video or for a given identity, and it creates natural looking image sequences with little distortion in time.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08348v1
PDF	https://arxiv.org/pdf/1911.08348v1.pdf
PWC	https://paperswithcode.com/paper/live-face-de-identification-in-video-1
Repo
Framework

Learning Humanoid Robot Motions Through Deep Neural Networks


Title	Learning Humanoid Robot Motions Through Deep Neural Networks
Authors	Luckeciano Carvalho Melo, Marcos Ricardo Omena Albuquerque Maximo, Adilson Marques da Cunha
Abstract	Controlling a high degrees of freedom humanoid robot is acknowledged as one of the hardest problems in Robotics. Due to the lack of mathematical models, an approach frequently employed is to rely on human intuition to design keyframe movements by hand, usually aided by graphical tools. In this paper, we propose a learning framework based on neural networks in order to mimic humanoid robot movements. The developed technique does not make any assumption about the underlying implementation of the movement, therefore both keyframe and model-based motions may be learned. The framework was applied in the RoboCup 3D Soccer Simulation domain and promising results were obtained using the same network architecture for several motions, even when copying motions from another teams.
Tasks
Published	2019-01-02
URL	http://arxiv.org/abs/1901.00270v1
PDF	http://arxiv.org/pdf/1901.00270v1.pdf
PWC	https://paperswithcode.com/paper/learning-humanoid-robot-motions-through-deep
Repo
Framework

Revisiting Metric Learning for Few-Shot Image Classification


Title	Revisiting Metric Learning for Few-Shot Image Classification
Authors	Xiaomeng Li, Lequan Yu, Chi-Wing Fu, Meng Fang, Pheng-Ann Heng
Abstract	The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric learning, and extend it into a deep K-tuplet network for few-shot learning, utilizing the relationship among the input samples to learn a general representation learning via episode-training. Once trained, our network is able to extract discriminative features for unseen novel categories and can be seamlessly incorporated with a non-linear distance metric function to facilitate the few-shot classification. Our result on the miniImageNet benchmark outperforms other metric-based few-shot classification methods. More importantly, when evaluated on completely different datasets (Caltech-101, CUB-200, Stanford Dogs and Cars) using the model trained with miniImageNet, our method significantly outperforms prior methods, demonstrating its superior capability to generalize to unseen classes.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Image Classification, Metric Learning, Representation Learning
Published	2019-07-06
URL	https://arxiv.org/abs/1907.03123v1
PDF	https://arxiv.org/pdf/1907.03123v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-metric-learning-for-few-shot-image
Repo
Framework