May 7, 2019

2944 words 14 mins read

Paper Group ANR 8

MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion. ShapeFit and ShapeKick for Robust, Scalable Structure from Motion. Panoptic Studio: A Massively Multiview System for Social Interaction Capture. Stack-propagation: Improved Representation Learning for Syntax. A Reinforcement Learning System to Encourage Physical …

MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion


Title	MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion
Authors	Mading Li, Jiaying Liu, Zhiwei Xiong, Xiaoyan Sun, Zongming Guo
Abstract	In this paper, we propose a novel multiplanar autoregressive (AR) model to exploit the correlation in cross-dimensional planes of a similar patch group collected in an image, which has long been neglected by previous AR models. On that basis, we then present a joint multiplanar AR and low-rank based approach (MARLow) for image completion from random sampling, which exploits the nonlocal self-similarity within natural images more effectively. Specifically, the multiplanar AR model constraints the local stationarity in different cross-sections of the patch group, while the low-rank minimization captures the intrinsic coherence of nonlocal patches. The proposed approach can be readily extended to multichannel images (e.g. color images), by simultaneously considering the correlation in different channels. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art methods, even if the pixel missing rate is as high as 90%.
Tasks
Published	2016-05-03
URL	http://arxiv.org/abs/1605.01115v2
PDF	http://arxiv.org/pdf/1605.01115v2.pdf
PWC	https://paperswithcode.com/paper/marlow-a-joint-multiplanar-autoregressive-and
Repo
Framework

ShapeFit and ShapeKick for Robust, Scalable Structure from Motion


Title	ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
Authors	Thomas Goldstein, Paul Hand, Choongbum Lee, Vladislav Voroninski, Stefano Soatto
Abstract	We introduce a new method for location recovery from pair-wise directions that leverages an efficient convex program that comes with exact recovery guarantees, even in the presence of adversarial outliers. When pairwise directions represent scaled relative positions between pairs of views (estimated for instance with epipolar geometry) our method can be used for location recovery, that is the determination of relative pose up to a single unknown scale. For this task, our method yields performance comparable to the state-of-the-art with an order of magnitude speed-up. Our proposed numerical framework is flexible in that it accommodates other approaches to location recovery and can be used to speed up other methods. These properties are demonstrated by extensively testing against state-of-the-art methods for location recovery on 13 large, irregular collections of images of real scenes in addition to simulated data with ground truth.
Tasks
Published	2016-08-07
URL	http://arxiv.org/abs/1608.02165v1
PDF	http://arxiv.org/pdf/1608.02165v1.pdf
PWC	https://paperswithcode.com/paper/shapefit-and-shapekick-for-robust-scalable
Repo
Framework


Title	Panoptic Studio: A Massively Multiview System for Social Interaction Capture
Authors	Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, Yaser Sheikh
Abstract	We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. Our algorithm is designed to fuse the “weak” perceptual processes in the large number of views by progressively generating skeletal proposals from low-level appearance cues, and a framework for temporal refinement is also presented by associating body parts to reconstructed dense 3D trajectory stream. Our system and method are the first in reconstructing full body motion of more than five people engaged in social interactions without using markers. We also empirically demonstrate the impact of the number of views in achieving this goal.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03153v1
PDF	http://arxiv.org/pdf/1612.03153v1.pdf
PWC	https://paperswithcode.com/paper/panoptic-studio-a-massively-multiview-system
Repo
Framework

Stack-propagation: Improved Representation Learning for Syntax


Title	Stack-propagation: Improved Representation Learning for Syntax
Authors	Yuan Zhang, David Weiss
Abstract	Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates. We demonstrate that a better approach is to utilize POS tags as a regularizer of learned representations. We propose a simple method for learning a stacked pipeline of models which we call “stack-propagation”. We apply this to dependency parsing and tagging, where we use the hidden layer of the tagger network as a representation of the input tokens for the parser. At test time, our parser does not require predicted POS tags. On 19 languages from the Universal Dependencies, our method is 1.3% (absolute) more accurate than a state-of-the-art graph-based approach and 2.7% more accurate than the most comparable greedy model.
Tasks	Dependency Parsing, Representation Learning
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06598v2
PDF	http://arxiv.org/pdf/1603.06598v2.pdf
PWC	https://paperswithcode.com/paper/stack-propagation-improved-representation
Repo
Framework

A Reinforcement Learning System to Encourage Physical Activity in Diabetes Patients


Title	A Reinforcement Learning System to Encourage Physical Activity in Diabetes Patients
Authors	Irit Hochberg, Guy Feraru, Mark Kozdoba, Shie Mannor, Moshe Tennenholtz, Elad Yom-Tov
Abstract	Regular physical activity is known to be beneficial to people suffering from diabetes type 2. Nevertheless, most such people are sedentary. Smartphones create new possibilities for helping people to adhere to their physical activity goals, through continuous monitoring and communication, coupled with personalized feedback. We provided 27 sedentary diabetes type 2 patients with a smartphone-based pedometer and a personal plan for physical activity. Patients were sent SMS messages to encourage physical activity between once a day and once per week. Messages were personalized through a Reinforcement Learning (RL) algorithm which optimized messages to improve each participant’s compliance with the activity regimen. The RL algorithm was compared to a static policy for sending messages and to weekly reminders. Our results show that participants who received messages generated by the RL algorithm increased the amount of activity and pace of walking, while the control group patients did not. Patients assigned to the RL algorithm group experienced a superior reduction in blood glucose levels (HbA1c) compared to control policies, and longer participation caused greater reductions in blood glucose levels. The learning algorithm improved gradually in predicting which messages would lead participants to exercise. Our results suggest that a mobile phone application coupled with a learning algorithm can improve adherence to exercise in diabetic patients. As a learning algorithm is automated, and delivers personalized messages, it could be used in large populations of diabetic patients to improve health and glycemic control. Our results can be expanded to other areas where computer-led health coaching of humans may have a positive impact.
Tasks
Published	2016-05-13
URL	http://arxiv.org/abs/1605.04070v1
PDF	http://arxiv.org/pdf/1605.04070v1.pdf
PWC	https://paperswithcode.com/paper/a-reinforcement-learning-system-to-encourage
Repo
Framework

Semiring Programming: A Declarative Framework for Generalized Sum Product Problems


Title	Semiring Programming: A Declarative Framework for Generalized Sum Product Problems
Authors	Vaishak Belle, Luc De Raedt
Abstract	To solve hard problems, AI relies on a variety of disciplines such as logic, probabilistic reasoning, machine learning and mathematical programming. Although it is widely accepted that solving real-world problems requires an integration amongst these, contemporary representation methodologies offer little support for this. In an attempt to alleviate this situation, we introduce a new declarative programming framework that provides abstractions of well-known problems such as SAT, Bayesian inference, generative models, and convex optimization. The semantics of programs is defined in terms of first-order structures with semiring labels, which allows us to freely combine and integrate problems from different AI disciplines.
Tasks	Bayesian Inference
Published	2016-09-21
URL	https://arxiv.org/abs/1609.06954v2
PDF	https://arxiv.org/pdf/1609.06954v2.pdf
PWC	https://paperswithcode.com/paper/semiring-programming-a-framework-for-search
Repo
Framework

Modelling Stock-market Investors as Reinforcement Learning Agents [Correction]


Title	Modelling Stock-market Investors as Reinforcement Learning Agents [Correction]
Authors	Alvin Pastore, Umberto Esposito, Eleni Vasilaki
Abstract	Decision making in uncertain and risky environments is a prominent area of research. Standard economic theories fail to fully explain human behaviour, while a potentially promising alternative may lie in the direction of Reinforcement Learning (RL) theory. We analyse data for 46 players extracted from a financial market online game and test whether Reinforcement Learning (Q-Learning) could capture these players behaviour using a risk measure based on financial modeling. Moreover we test an earlier hypothesis that players are “na"ive” (short-sighted). Our results indicate that a simple Reinforcement Learning model which considers only the selling component of the task captures the decision-making process for a subset of players but this is not sufficient to draw any conclusion on the population. We also find that there is not a significant improvement of fitting of the players when using a full RL model against a myopic version, where only immediate reward is valued by the players. This indicates that players, if using a Reinforcement Learning approach, do so na"ively
Tasks	Decision Making, Q-Learning
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06086v1
PDF	http://arxiv.org/pdf/1609.06086v1.pdf
PWC	https://paperswithcode.com/paper/modelling-stock-market-investors-as
Repo
Framework

Stochastic Gradient MCMC with Stale Gradients


Title	Stochastic Gradient MCMC with Stale Gradients
Authors	Changyou Chen, Nan Ding, Chunyuan Li, Yizhe Zhang, Lawrence Carin
Abstract	Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popular to employ distributed systems, where stochastic gradients are computed based on some outdated parameters, yielding what are termed stale gradients. While stale gradients could be directly used in SG-MCMC, their impact on convergence properties has not been well studied. In this paper we develop theory to show that while the bias and MSE of an SG-MCMC algorithm depend on the staleness of stochastic gradients, its estimation variance (relative to the expected estimate, based on a prescribed number of samples) is independent of it. In a simple Bayesian distributed system with SG-MCMC, where stale gradients are computed asynchronously by a set of workers, our theory indicates a linear speedup on the decrease of estimation variance w.r.t. the number of workers. Experiments on synthetic data and deep neural networks validate our theory, demonstrating the effectiveness and scalability of SG-MCMC with stale gradients.
Tasks
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06664v1
PDF	http://arxiv.org/pdf/1610.06664v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-gradient-mcmc-with-stale-gradients
Repo
Framework

Robust Variational Inference


Title	Robust Variational Inference
Authors	Michael Figurnov, Kirill Struminsky, Dmitry Vetrov
Abstract	Variational inference is a powerful tool for approximate inference. However, it mainly focuses on the evidence lower bound as variational objective and the development of other measures for variational inference is a promising area of research. This paper proposes a robust modification of evidence and a lower bound for the evidence, which is applicable when the majority of the training set samples are random noise objects. We provide experiments for variational autoencoders to show advantage of the objective over the evidence lower bound on synthetic datasets obtained by adding uninformative noise objects to MNIST and OMNIGLOT. Additionally, for the original MNIST and OMNIGLOT datasets we observe a small improvement over the non-robust evidence lower bound.
Tasks	Omniglot
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09226v1
PDF	http://arxiv.org/pdf/1611.09226v1.pdf
PWC	https://paperswithcode.com/paper/robust-variational-inference
Repo
Framework


Title	Applications of Online Deep Learning for Crisis Response Using Social Media Information
Authors	Dat Tien Nguyen, Shafiq Joty, Muhammad Imran, Hassan Sajjad, Prasenjit Mitra
Abstract	During natural or man-made disasters, humanitarian response organizations look for useful information to support their decision-making processes. Social media platforms such as Twitter have been considered as a vital source of useful information for disaster response and management. Despite advances in natural language processing techniques, processing short and informal Twitter messages is a challenging task. In this paper, we propose to use Deep Neural Network (DNN) to address two types of information needs of response organizations: 1) identifying informative tweets and 2) classifying them into topical classes. DNNs use distributed representation of words and learn the representation as well as higher level features automatically for the classification task. We propose a new online algorithm based on stochastic gradient descent to train DNNs in an online fashion during disaster situations. We test our models using a crisis-related real-world Twitter dataset.
Tasks	Decision Making
Published	2016-10-04
URL	http://arxiv.org/abs/1610.01030v2
PDF	http://arxiv.org/pdf/1610.01030v2.pdf
PWC	https://paperswithcode.com/paper/applications-of-online-deep-learning-for
Repo
Framework

Dynamic Filter Networks


Title	Dynamic Filter Networks
Authors	Bert De Brabandere, Xu Jia, Tinne Tuytelaars, Luc Van Gool
Abstract	In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operations can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple such layers can be combined, e.g. in a recurrent architecture. We demonstrate the effectiveness of the dynamic filter network on the tasks of video and stereo prediction, and reach state-of-the-art performance on the moving MNIST dataset with a much smaller model. By visualizing the learned filters, we illustrate that the network has picked up flow information by only looking at unlabelled training data. This suggests that the network can be used to pretrain networks for various supervised tasks in an unsupervised way, like optical flow and depth estimation.
Tasks	Depth Estimation, Optical Flow Estimation
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09673v2
PDF	http://arxiv.org/pdf/1605.09673v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-filter-networks
Repo
Framework

Intra-Team Strategies for Teams Negotiating Against Competitor, Matchers, and Conceders


Title	Intra-Team Strategies for Teams Negotiating Against Competitor, Matchers, and Conceders
Authors	Victor Sanchez-Anguix, Reyhan Aydogan, Vicente Julian, Catholijn Jonker
Abstract	Under some circumstances, a group of individuals may need to negotiate together as a negotiation team against another party. Unlike bilateral negotiation between two individuals, this type of negotiations entails to adopt an intra-team strategy for negotiation teams in order to make team decisions and accordingly negotiate with the opponent. It is crucial to be able to negotiate successfully with heterogeneous opponents since opponents’ negotiation strategy and behavior may vary in an open environment. While one opponent might collaborate and concede over time, another may not be inclined to concede. This paper analyzes the performance of recently proposed intra-team strategies for negotiation teams against different categories of opponents: competitors, matchers, and conceders. Furthermore, it provides an extension of the negotiation tool Genius for negotiation teams in bilateral settings. Consequently, this work facilitates research in negotiation teams.
Tasks
Published	2016-04-16
URL	http://arxiv.org/abs/1604.04736v1
PDF	http://arxiv.org/pdf/1604.04736v1.pdf
PWC	https://paperswithcode.com/paper/intra-team-strategies-for-teams-negotiating
Repo
Framework

Multiwinner Approval Rules as Apportionment Methods


Title	Multiwinner Approval Rules as Apportionment Methods
Authors	Markus Brill, Jean-François Laslier, Piotr Skowron
Abstract	We establish a link between multiwinner elections and apportionment problems by showing how approval-based multiwinner election rules can be interpreted as methods of apportionment. We consider several multiwinner rules and observe that they induce apportionment methods that are well-established in the literature on proportional representation. For instance, we show that Proportional Approval Voting induces the D’Hondt method and that Monroe’s rule induces the largest reminder method. We also consider properties of apportionment methods and exhibit multiwinner rules that induce apportionment methods satisfying these properties.
Tasks
Published	2016-11-26
URL	http://arxiv.org/abs/1611.08691v1
PDF	http://arxiv.org/pdf/1611.08691v1.pdf
PWC	https://paperswithcode.com/paper/multiwinner-approval-rules-as-apportionment
Repo
Framework

Inferring Coupling of Distributed Dynamical Systems via Transfer Entropy


Title	Inferring Coupling of Distributed Dynamical Systems via Transfer Entropy
Authors	Oliver M. Cliff, Mikhail Prokopenko, Robert Fitch
Abstract	In this work, we are interested in structure learning for a set of spatially distributed dynamical systems, where individual subsystems are coupled via latent variables and observed through a filter. We represent this model as a directed acyclic graph (DAG) that characterises the unidirectional coupling between subsystems. Standard approaches to structure learning are not applicable in this framework due to the hidden variables, however we can exploit the properties of certain dynamical systems to formulate exact methods based on state space reconstruction. We approach the problem by using reconstruction theorems to analytically derive a tractable expression for the KL-divergence of a candidate DAG from the observed dataset. We show this measure can be decomposed as a function of two information-theoretic measures, transfer entropy and stochastic interaction. We then present two mathematically robust scoring functions based on transfer entropy and statistical independence tests. These results support the previously held conjecture that transfer entropy can be used to infer effective connectivity in complex networks.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00549v1
PDF	http://arxiv.org/pdf/1611.00549v1.pdf
PWC	https://paperswithcode.com/paper/inferring-coupling-of-distributed-dynamical
Repo
Framework

Real-time 3D Tracking of Articulated Tools for Robotic Surgery


Title	Real-time 3D Tracking of Articulated Tools for Robotic Surgery
Authors	Menglong Ye, Lin Zhang, Stamatia Giannarou, Guang-Zhong Yang
Abstract	In robotic surgery, tool tracking is important for providing safe tool-tissue interaction and facilitating surgical skills assessment. Despite recent advances in tool tracking, existing approaches are faced with major difficulties in real-time tracking of articulated tools. Most algorithms are tailored for offline processing with pre-recorded videos. In this paper, we propose a real-time 3D tracking method for articulated tools in robotic surgery. The proposed method is based on the CAD model of the tools as well as robot kinematics to generate online part-based templates for efficient 2D matching and 3D pose estimation. A robust verification approach is incorporated to reject outliers in 2D detections, which is then followed by fusing inliers with robot kinematic readings for 3D pose estimation of the tool. The proposed method has been validated with phantom data, as well as ex vivo and in vivo experiments. The results derived clearly demonstrate the performance advantage of the proposed method when compared to the state-of-the-art.
Tasks	3D Pose Estimation, Pose Estimation
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03483v3
PDF	http://arxiv.org/pdf/1605.03483v3.pdf
PWC	https://paperswithcode.com/paper/real-time-3d-tracking-of-articulated-tools
Repo
Framework