July 28, 2019

3005 words 15 mins read

Paper Group ANR 187

Vehicle Tracking in Wide Area Motion Imagery via Stochastic Progressive Association Across Multiple Frames (SPAAM). Attribution Modeling Increases Efficiency of Bidding in Display Advertising. On the Development of Intelligent Agents for MOBA Games. Predicting Cognitive Decline with Deep Learning of Brain Metabolism and Amyloid Imaging. Generative …

Vehicle Tracking in Wide Area Motion Imagery via Stochastic Progressive Association Across Multiple Frames (SPAAM)


Title	Vehicle Tracking in Wide Area Motion Imagery via Stochastic Progressive Association Across Multiple Frames (SPAAM)
Authors	Ahmed Elliethy, Gaurav Sharma
Abstract	Vehicle tracking in Wide Area Motion Imagery (WAMI) relies on associating vehicle detections across multiple WAMI frames to form tracks corresponding to individual vehicles. The temporal window length, i.e., the number $M$ of sequential frames, over which associations are collectively estimated poses a trade-off between accuracy and computational complexity. A larger $M$ improves performance because the increased temporal context enables the use of motion models and allows occlusions and spurious detections to be handled better. The number of total hypotheses tracks, on the other hand, grows exponentially with increasing $M$, making larger values of $M$ computationally challenging to tackle. In this paper, we introduce SPAAM an iterative approach that progressively grows $M$ with each iteration to improve estimated tracks by exploiting the enlarged temporal context while keeping computation manageable through two novel approaches for pruning association hypotheses. First, guided by a road network, accurately co-registered to the WAMI frames, we disregard unlikely associations that do not agree with the road network. Second, as $M$ is progressively enlarged at each iteration, the related increase in association hypotheses is limited by revisiting only the subset of association possibilities rendered open by stochastically determined dis-associations for the previous iteration. The stochastic dis-association at each iteration maintains each estimated association according to an estimated probability for confidence, obtained via a probabilistic model. Associations at each iteration are then estimated globally over the $M$ frames by (approximately) solving a binary integer programming problem for selecting a set of compatible tracks. Vehicle tracking results obtained over test WAMI datasets indicate that our proposed approach provides significant performance improvements over 3 alternatives.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06035v1
PDF	http://arxiv.org/pdf/1709.06035v1.pdf
PWC	https://paperswithcode.com/paper/vehicle-tracking-in-wide-area-motion-imagery
Repo
Framework

Attribution Modeling Increases Efficiency of Bidding in Display Advertising


Title	Attribution Modeling Increases Efficiency of Bidding in Display Advertising
Authors	Eustache Diemert, Julien Meynet, Pierre Galland, Damien Lefortier
Abstract	Predicting click and conversion probabilities when bidding on ad exchanges is at the core of the programmatic advertising industry. Two separated lines of previous works respectively address i) the prediction of user conversion probability and ii) the attribution of these conversions to advertising events (such as clicks) after the fact. We argue that attribution modeling improves the efficiency of the bidding policy in the context of performance advertising. Firstly we explain the inefficiency of the standard bidding policy with respect to attribution. Secondly we learn and utilize an attribution model in the bidder itself and show how it modifies the average bid after a click. Finally we produce evidence of the effectiveness of the proposed method on both offline and online experiments with data spanning several weeks of real traffic from Criteo, a leader in performance advertising.
Tasks
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06409v2
PDF	http://arxiv.org/pdf/1707.06409v2.pdf
PWC	https://paperswithcode.com/paper/attribution-modeling-increases-efficiency-of
Repo
Framework

On the Development of Intelligent Agents for MOBA Games


Title	On the Development of Intelligent Agents for MOBA Games
Authors	Victor do Nascimento Silva, Luiz Chaimowicz
Abstract	Multiplayer Online Battle Arena (MOBA) is one of the most played game genres nowadays. With the increasing growth of this genre, it becomes necessary to develop effective intelligent agents to play alongside or against human players. In this paper we address the problem of agent development for MOBA games. We implement a two-layered architecture agent that handles both navigation and game mechanics. This architecture relies on the use of Influence Maps, a widely used approach for tactical analysis. Several experiments were performed using {\em League of Legends} as a testbed, and show promising results in this highly dynamic real-time context.
Tasks	League of Legends
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02789v1
PDF	http://arxiv.org/pdf/1706.02789v1.pdf
PWC	https://paperswithcode.com/paper/on-the-development-of-intelligent-agents-for
Repo
Framework

Predicting Cognitive Decline with Deep Learning of Brain Metabolism and Amyloid Imaging


Title	Predicting Cognitive Decline with Deep Learning of Brain Metabolism and Amyloid Imaging
Authors	Hongyoon Choi, Kyong Hwan Jin
Abstract	For effective treatment of Alzheimer disease (AD), it is important to identify subjects who are most likely to exhibit rapid cognitive decline. Herein, we developed a novel framework based on a deep convolutional neural network which can predict future cognitive decline in mild cognitive impairment (MCI) patients using flurodeoxyglucose and florbetapir positron emission tomography (PET). The architecture of the network only relies on baseline PET studies of AD and normal subjects as the training dataset. Feature extraction and complicated image preprocessing including nonlinear warping are unnecessary for our approach. Accuracy of prediction (84.2%) for conversion to AD in MCI patients outperformed conventional feature-based quantification approaches. ROC analyses revealed that performance of CNN-based approach was significantly higher than that of the conventional quantification methods (p < 0.05). Output scores of the network were strongly correlated with the longitudinal change in cognitive measurements. These results show the feasibility of deep learning as a tool for predicting disease outcome using brain images.
Tasks
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06033v1
PDF	http://arxiv.org/pdf/1704.06033v1.pdf
PWC	https://paperswithcode.com/paper/predicting-cognitive-decline-with-deep
Repo
Framework

Generative Adversarial Models for People Attribute Recognition in Surveillance


Title	Generative Adversarial Models for People Attribute Recognition in Surveillance
Authors	Matteo Fabbri, Simone Calderara, Rita Cucchiara
Abstract	In this paper we propose a deep architecture for detecting people attributes (e.g. gender, race, clothing …) in surveillance contexts. Our proposal explicitly deal with poor resolution and occlusion issues that often occur in surveillance footages by enhancing the images by means of Deep Convolutional Generative Adversarial Networks (DCGAN). Experiments show that by combining both our Generative Reconstruction and Deep Attribute Classification Network we can effectively extract attributes even when resolution is poor and in presence of strong occlusions up to 80% of the whole person figure.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02240v1
PDF	http://arxiv.org/pdf/1707.02240v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-models-for-people
Repo
Framework

Supervising Unsupervised Learning


Title	Supervising Unsupervised Learning
Authors	Vikas K. Garg, Adam Kalai
Abstract	We introduce a framework to leverage knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets. Our perspective avoids the subjectivity inherent in unsupervised learning by reducing it to supervised learning, and provides a principled way to evaluate unsupervised algorithms. We demonstrate the versatility of our framework via simple agnostic bounds on unsupervised problems. In the context of clustering, our approach helps choose the number of clusters and the clustering algorithm, remove the outliers, and provably circumvent the Kleinberg’s impossibility result. Experimental results across hundreds of problems demonstrate improved performance on unsupervised data with simple algorithms, despite the fact that our problems come from heterogeneous domains. Additionally, our framework lets us leverage deep networks to learn common features from many such small datasets, and perform zero shot learning.
Tasks	Zero-Shot Learning
Published	2017-09-14
URL	http://arxiv.org/abs/1709.05262v2
PDF	http://arxiv.org/pdf/1709.05262v2.pdf
PWC	https://paperswithcode.com/paper/supervising-unsupervised-learning
Repo
Framework

Characterizing Diabetes, Diet, Exercise, and Obesity Comments on Twitter


Title	Characterizing Diabetes, Diet, Exercise, and Obesity Comments on Twitter
Authors	Amir Karami, Alicia A. Dahl, Gabrielle Turner-McGrievy, Hadi Kharrazi, Jr. George Shaw
Abstract	Social media provide a platform for users to express their opinions and share information. Understanding public health opinions on social media, such as Twitter, offers a unique approach to characterizing common health issues such as diabetes, diet, exercise, and obesity (DDEO), however, collecting and analyzing a large scale conversational public health data set is a challenging research task. The goal of this research is to analyze the characteristics of the general public’s opinions in regard to diabetes, diet, exercise and obesity (DDEO) as expressed on Twitter. A multi-component semantic and linguistic framework was developed to collect Twitter data, discover topics of interest about DDEO, and analyze the topics. From the extracted 4.5 million tweets, 8% of tweets discussed diabetes, 23.7% diet, 16.6% exercise, and 51.7% obesity. The strongest correlation among the topics was determined between exercise and obesity. Other notable correlations were: diabetes and obesity, and diet and obesity DDEO terms were also identified as subtopics of each of the DDEO topics. The frequent subtopics discussed along with Diabetes, excluding the DDEO terms themselves, were blood pressure, heart attack, yoga, and Alzheimer. The non-DDEO subtopics for Diet included vegetarian, pregnancy, celebrities, weight loss, religious, and mental health, while subtopics for Exercise included computer games, brain, fitness, and daily plan. Non-DDEO subtopics for Obesity included Alzheimer, cancer, and children. With 2.67 billion social media users in 2016, publicly available data such as Twitter posts can be utilized to support clinical providers, public health experts, and social scientists in better understanding common public opinions in regard to diabetes, diet, exercise, and obesity.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07916v1
PDF	http://arxiv.org/pdf/1709.07916v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-diabetes-diet-exercise-and
Repo
Framework

A 3D Object Detection and Pose Estimation Pipeline Using RGB-D Images


Title	A 3D Object Detection and Pose Estimation Pipeline Using RGB-D Images
Authors	Ruotao He, Juan Rojas, Yisheng Guan
Abstract	3D object detection and pose estimation has been studied extensively in recent decades for its potential applications in robotics. However, there still remains challenges when we aim at detecting multiple objects while retaining low false positive rate in cluttered environments. This paper proposes a robust 3D object detection and pose estimation pipeline based on RGB-D images, which can detect multiple objects simultaneously while reducing false positives. Detection begins with template matching and yields a set of template matches. A clustering algorithm then groups templates of similar spatial location and produces multiple-object hypotheses. A scoring function evaluates the hypotheses using their associated templates and non-maximum suppression is adopted to remove duplicate results based on the scores. Finally, a combination of point cloud processing algorithms are used to compute objects’ 3D poses. Existing object hypotheses are verified by computing the overlap between model and scene points. Experiments demonstrate that our approach provides competitive results comparable to the state-of-the-arts and can be applied to robot random bin-picking.
Tasks	3D Object Detection, Object Detection, Pose Estimation
Published	2017-03-11
URL	http://arxiv.org/abs/1703.03940v1
PDF	http://arxiv.org/pdf/1703.03940v1.pdf
PWC	https://paperswithcode.com/paper/a-3d-object-detection-and-pose-estimation
Repo
Framework

Optimization for L1-Norm Error Fitting via Data Aggregation


Title	Optimization for L1-Norm Error Fitting via Data Aggregation
Authors	Young Woong Park
Abstract	We propose a data aggregation-based algorithm with monotonic convergence to a global optimum for a generalized version of the L1-norm error fitting model with an assumption of the fitting function. The proposed algorithm generalizes the recent algorithm in the literature, aggregate and iterative disaggregate (AID), which selectively solves three specific L1-norm error fitting problems. With the proposed algorithm, any L1-norm error fitting model can be solved optimally if it follows the form of the L1-norm error fitting problem and if the fitting function satisfies the assumption. The proposed algorithm can also solve multi-dimensional fitting problems with arbitrary constraints on the fitting coefficients matrix. The generalized problem includes popular models such as regression and the orthogonal Procrustes problem. The results of the computational experiment show that the proposed algorithms are faster than the state-of-the-art benchmarks for L1-norm regression subset selection and L1-norm regression over a sphere. Further, the relative performance of the proposed algorithm improves as data size increases.
Tasks
Published	2017-03-15
URL	https://arxiv.org/abs/1703.04864v3
PDF	https://arxiv.org/pdf/1703.04864v3.pdf
PWC	https://paperswithcode.com/paper/optimization-for-l1-norm-error-fitting-via
Repo
Framework

Zero-Shot Transfer Learning for Event Extraction


Title	Zero-Shot Transfer Learning for Event Extraction
Authors	Lifu Huang, Heng Ji, Kyunghyun Cho, Clare R. Voss
Abstract	Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort. In this work, we take a fresh look at event extraction and model it as a grounding problem. We design a transferable neural architecture, mapping event mentions and types jointly into a shared semantic space using structural and compositional neural networks, where the type of each event mention can be determined by the closest of all candidate types . By leveraging (1)~available manual annotations for a small set of existing event types and (2)~existing event ontologies, our framework applies to new event types without requiring additional annotation. Experiments on both existing event types (e.g., ACE, ERE) and new event types (e.g., FrameNet) demonstrate the effectiveness of our approach. \textit{Without any manual annotations} for 23 new event types, our zero-shot framework achieved performance comparable to a state-of-the-art supervised model which is trained from the annotations of 500 event mentions.
Tasks	Transfer Learning
Published	2017-07-04
URL	http://arxiv.org/abs/1707.01066v1
PDF	http://arxiv.org/pdf/1707.01066v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-transfer-learning-for-event
Repo
Framework

Improved Neural Relation Detection for Knowledge Base Question Answering


Title	Improved Neural Relation Detection for Knowledge Base Question Answering
Authors	Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, Bowen Zhou
Abstract	Relation detection is a core component for many NLP applications including Knowledge Base Question Answering (KBQA). In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning that detects KB relations given an input question. Our method uses deep residual bidirectional LSTMs to compare questions and relation names via different hierarchies of abstraction. Additionally, we propose a simple KBQA system that integrates entity linking and our proposed relation detector to enable one enhance another. Experimental results evidence that our approach achieves not only outstanding relation detection performance, but more importantly, it helps our KBQA system to achieve state-of-the-art accuracy for both single-relation (SimpleQuestions) and multi-relation (WebQSP) QA benchmarks.
Tasks	Entity Linking, Knowledge Base Question Answering, Question Answering
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06194v2
PDF	http://arxiv.org/pdf/1704.06194v2.pdf
PWC	https://paperswithcode.com/paper/improved-neural-relation-detection-for
Repo
Framework

Multivariate Gaussian Network Structure Learning


Title	Multivariate Gaussian Network Structure Learning
Authors	Xingqi Du, Subhashis Ghosal
Abstract	We consider a graphical model where a multivariate normal vector is associated with each node of the underlying graph and estimate the graphical structure. We minimize a loss function obtained by regressing the vector at each node on those at the remaining ones under a group penalty. We show that the proposed estimator can be computed by a fast convex optimization algorithm. We show that as the sample size increases, the estimated regression coefficients and the correct graphical structure are correctly estimated with probability tending to one. By extensive simulations, we show the superiority of the proposed method over comparable procedures. We apply the technique on two real datasets. The first one is to identify gene and protein networks showing up in cancer cell lines, and the second one is to reveal the connections among different industries in the US.
Tasks
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05552v1
PDF	http://arxiv.org/pdf/1709.05552v1.pdf
PWC	https://paperswithcode.com/paper/multivariate-gaussian-network-structure
Repo
Framework

On Consistency of Graph-based Semi-supervised Learning


Title	On Consistency of Graph-based Semi-supervised Learning
Authors	Chengan Du, Yunpeng Zhao, Feng Wang
Abstract	Graph-based semi-supervised learning is one of the most popular methods in machine learning. Some of its theoretical properties such as bounds for the generalization error and the convergence of the graph Laplacian regularizer have been studied in computer science and statistics literatures. However, a fundamental statistical property, the consistency of the estimator from this method has not been proved. In this article, we study the consistency problem under a non-parametric framework. We prove the consistency of graph-based learning in the case that the estimated scores are enforced to be equal to the observed responses for the labeled data. The sample sizes of both labeled and unlabeled data are allowed to grow in this result. When the estimated scores are not required to be equal to the observed responses, a tuning parameter is used to balance the loss function and the graph Laplacian regularizer. We give a counterexample demonstrating that the estimator for this case can be inconsistent. The theoretical findings are supported by numerical studies.
Tasks
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06177v2
PDF	http://arxiv.org/pdf/1703.06177v2.pdf
PWC	https://paperswithcode.com/paper/on-consistency-of-graph-based-semi-supervised
Repo
Framework

Multiple Images Recovery Using a Single Affine Transformation


Title	Multiple Images Recovery Using a Single Affine Transformation
Authors	Bo Jiang, Chris Ding, Bin Luo
Abstract	In many real-world applications, image data often come with noises, corruptions or large errors. One approach to deal with noise image data is to use data recovery techniques which aim to recover the true uncorrupted signals from the observed noise images. In this paper, we first introduce a novel corruption recovery transformation (CRT) model which aims to recover multiple (or a collection of) corrupted images using a single affine transformation. Then, we show that the introduced CRT can be efficiently constructed through learning from training data. Once CRT is learned, we can recover the true signals from the new incoming/test corrupted images explicitly. As an application, we apply our CRT to image recognition task. Experimental results on six image datasets demonstrate that the proposed CRT model is effective in recovering noise image data and thus leads to better recognition results.
Tasks
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08066v1
PDF	http://arxiv.org/pdf/1705.08066v1.pdf
PWC	https://paperswithcode.com/paper/multiple-images-recovery-using-a-single
Repo
Framework

Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning


Title	Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning
Authors	Lingjing Wang, Yi Fang
Abstract	Recent advancements in deep learning opened new opportunities for learning a high-quality 3D model from a single 2D image given sufficient training on large-scale data sets. However, the significant imbalance between available amount of images and 3D models, and the limited availability of labeled 2D image data (i.e. manually annotated pairs between images and their corresponding 3D models), severely impacts the training of most supervised deep learning methods in practice. In this paper, driven by a novel design of adversarial networks, we have developed an unsupervised learning paradigm to reconstruct 3D models from a single 2D image, which is free of manually annotated pairwise input image and its associated 3D model. Particularly, the paradigm begins with training an adaption network via autoencoder with adversarial loss, which embeds unpaired 2D synthesized image domain with real world image domain to a shared latent vector space. Then, we jointly train a 3D deconvolutional network to transform the latent vector space to the 3D object space together with the embedding process. Our experiments verify our network’s robust and superior performance in handling 3D volumetric object generation from a single 2D image.
Tasks	3D Reconstruction
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09312v1
PDF	http://arxiv.org/pdf/1711.09312v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-3d-reconstruction-from-a-single
Repo
Framework