October 20, 2019

3174 words 15 mins read

Paper Group ANR 81

Weakly-supervised Contextualization of Knowledge Graph Facts. Human Action Recognition and Prediction: A Survey. Distributed Inference for Linear Support Vector Machine. Blur-Countering Keypoint Detection via Eigenvalue Asymmetry. Jointly identifying opinion mining elements and fuzzy measurement of opinion intensity to analyze product features. Tig …

Weakly-supervised Contextualization of Knowledge Graph Facts


Title	Weakly-supervised Contextualization of Knowledge Graph Facts
Authors	Nikos Voskarides, Edgar Meij, Ridho Reinanda, Abhinav Khaitan, Miles Osborne, Giorgio Stefanoni, Prabhanjan Kambadur, Maarten de Rijke
Abstract	Knowledge graphs (KGs) model facts about the world, they consist of nodes (entities such as companies and people) that are connected by edges (relations such as founderOf). Facts encoded in KGs are frequently used by search applications to augment result pages. When presenting a KG fact to the user, providing other facts that are pertinent to that main fact can enrich the user experience and support exploratory information needs. KG fact contextualization is the task of augmenting a given KG fact with additional and useful KG facts. The task is challenging because of the large size of KGs, discovering other relevant facts even in a small neighborhood of the given fact results in an enormous amount of candidates. We introduce a neural fact contextualization method (NFCM) to address the KG fact contextualization task. NFCM first generates a set of candidate facts in the neighborhood of a given fact and then ranks the candidate facts using a supervised learning to rank model. The ranking model combines features that we automatically learn from data and that represent the query-candidate facts with a set of hand-crafted features we devised or adjusted for this task. In order to obtain the annotations required to train the learning to rank model at scale, we generate training data automatically using distant supervision on a large entity-tagged text corpus. We show that ranking functions learned on this data are effective at contextualizing KG facts. Evaluation using human assessors shows that it significantly outperforms several competitive baselines.
Tasks	Knowledge Graphs, Learning-To-Rank
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02393v2
PDF	http://arxiv.org/pdf/1805.02393v2.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-contextualization-of
Repo
Framework

Human Action Recognition and Prediction: A Survey


Title	Human Action Recognition and Prediction: A Survey
Authors	Yu Kong, Yun Fu
Abstract	Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action recognition and prediction from videos are such tasks, where action recognition is to infer human actions (present state) based upon complete action executions, and action prediction to predict human actions (future state) based upon incomplete action executions. These two tasks have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as visual surveillance, autonomous driving vehicle, entertainment, and video retrieval, etc. Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction. In this paper, we survey the complete state-of-the-art techniques in the action recognition and prediction. Existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions are also provided with systematic discussions.
Tasks	Autonomous Driving, Temporal Action Localization, Video Retrieval
Published	2018-06-28
URL	http://arxiv.org/abs/1806.11230v2
PDF	http://arxiv.org/pdf/1806.11230v2.pdf
PWC	https://paperswithcode.com/paper/human-action-recognition-and-prediction-a
Repo
Framework

Distributed Inference for Linear Support Vector Machine


Title	Distributed Inference for Linear Support Vector Machine
Authors	Xiaozhou Wang, Zhuoyi Yang, Xi Chen, Weidong Liu
Abstract	The growing size of modern data brings many new challenges to existing statistical inference methodologies and theories, and calls for the development of distributed inferential approaches. This paper studies distributed inference for linear support vector machine (SVM) for the binary classification task. Despite a vast literature on SVM, much less is known about the inferential properties of SVM, especially in a distributed setting. In this paper, we propose a multi-round distributed linear-type (MDL) estimator for conducting inference for linear SVM. The proposed estimator is computationally efficient. In particular, it only requires an initial SVM estimator and then successively refines the estimator by solving simple weighted least squares problem. Theoretically, we establish the Bahadur representation of the estimator. Based on the representation, the asymptotic normality is further derived, which shows that the MDL estimator achieves the optimal statistical efficiency, i.e., the same efficiency as the classical linear SVM applying to the entire data set in a single machine setup. Moreover, our asymptotic result avoids the condition on the number of machines or data batches, which is commonly assumed in distributed estimation literature, and allows the case of diverging dimension. We provide simulation studies to demonstrate the performance of the proposed MDL estimator.
Tasks
Published	2018-11-29
URL	https://arxiv.org/abs/1811.11922v2
PDF	https://arxiv.org/pdf/1811.11922v2.pdf
PWC	https://paperswithcode.com/paper/distributed-inference-for-linear-support
Repo
Framework

Blur-Countering Keypoint Detection via Eigenvalue Asymmetry


Title	Blur-Countering Keypoint Detection via Eigenvalue Asymmetry
Authors	Chao Zhang, Xuequan Lu, Takuya Akashi
Abstract	Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blur (e.g., motion blur, out-of-focus, and space-variant) remarkably increase challenges for keypoint detection. As a result, those methods have limited performance. To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images. Specifically, we first present a distance metric for derivative distributions, which preserves the distinctiveness of patch pairs well under blur. We then model the asymmetry by utilizing the difference of squared eigenvalues based on the distance metric. To make it scale-robust, we also extend it to scale space. The proposed detector is efficient as the main computational cost is the square of derivatives at each pixel. Extensive visual and quantitative results show that our method outperforms current approaches under different types and degrees of blur. Without any parallelization, our implementation\footnote{We will make our code publicly available upon the acceptance.} achieves real-time performance for low-resolution images (e.g., $320\times240$ pixel).
Tasks	Keypoint Detection
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01456v1
PDF	http://arxiv.org/pdf/1809.01456v1.pdf
PWC	https://paperswithcode.com/paper/blur-countering-keypoint-detection-via
Repo
Framework

Jointly identifying opinion mining elements and fuzzy measurement of opinion intensity to analyze product features


Title	Jointly identifying opinion mining elements and fuzzy measurement of opinion intensity to analyze product features
Authors	Haiqing Zhang, Aicha Sekhari, Yacine Ouzrout, Abdelaziz Bouras
Abstract	Opinion mining mainly involves three elements: feature and feature-of relations, opinion expressions and the related opinion attributes (e.g. Polarity), and feature-opinion relations. Although many works have emerged to achieve its aim of gaining information, the previous researches typically handled each of the three elements in isolation, which cannot give sufficient information extraction results; hence, the complexity and the running time of information extraction is increased. In this paper, we propose an opinion mining extraction algorithm to jointly discover the main opinion mining elements. Specifically, the algorithm automatically builds kernels to combine closely related words into new terms from word level to phrase level based on dependency relations; and we ensure the accuracy of opinion expressions and polarity based on: fuzzy measurements, opinion degree intensifiers, and opinion patterns. The 3458 analyzed reviews show that the proposed algorithm can effectively identify the main elements simultaneously and outperform the baseline methods. The proposed algorithm is used to analyze the features among heterogeneous products in the same category. The feature-by-feature comparison can help to select the weaker features and recommend the correct specifications from the beginning life of a product. From this comparison, some interesting observations are revealed. For example, the negative polarity of video dimension is higher than the product usability dimension for a product. Yet, enhancing the dimension of product usability can more effectively improve the product (C) 2015 Elsevier Ltd. All rights reserved.
Tasks	Opinion Mining
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05827v1
PDF	http://arxiv.org/pdf/1811.05827v1.pdf
PWC	https://paperswithcode.com/paper/jointly-identifying-opinion-mining-elements
Repo
Framework

Tight Prediction Intervals Using Expanded Interval Minimization


Title	Tight Prediction Intervals Using Expanded Interval Minimization
Authors	Dongqi Su, Ying Yin Ting, Jason Ansel
Abstract	Prediction intervals are a valuable way of quantifying uncertainty in regression problems. Good prediction intervals should be both correct, containing the actual value between the lower and upper bound at least a target percentage of the time; and tight, having a small mean width of the bounds. Many prior techniques for generating prediction intervals make assumptions on the distribution of error, which causes them to work poorly for problems with asymmetric distributions. This paper presents Expanded Interval Minimization (EIM), a novel loss function for generating prediction intervals using neural networks. This loss function uses minibatch statistics to estimate the coverage and optimize the width of the prediction intervals. It does not make the same assumptions on the distributions of data and error as prior work. We compare to three published techniques and show EIM produces on average 1.37x tighter prediction intervals and in the worst case 1.06x tighter intervals across two large real-world datasets and varying coverage levels.
Tasks
Published	2018-06-28
URL	http://arxiv.org/abs/1806.11222v1
PDF	http://arxiv.org/pdf/1806.11222v1.pdf
PWC	https://paperswithcode.com/paper/tight-prediction-intervals-using-expanded
Repo
Framework

Question-Aware Sentence Gating Networks for Question and Answering


Title	Question-Aware Sentence Gating Networks for Question and Answering
Authors	Minjeong Kim, David Keetae Park, Hyungjong Noh, Yeonsoo Lee, Jaegul Choo
Abstract	Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words, phrases, and sentences in a document. This paper proposes the novel question-aware sentence gating networks that directly incorporate the sentence-level information into word-level encoding processes. To this end, our model first learns question-aware sentence representations and then dynamically combines them with word-level representations, resulting in semantically meaningful word representations for QA tasks. Experimental results demonstrate that our approach consistently improves the accuracy over existing baseline approaches on various QA datasets and bears the wide applicability to other neural network-based QA models.
Tasks	Question Answering, Reading Comprehension
Published	2018-07-20
URL	http://arxiv.org/abs/1807.07964v1
PDF	http://arxiv.org/pdf/1807.07964v1.pdf
PWC	https://paperswithcode.com/paper/question-aware-sentence-gating-networks-for
Repo
Framework

Data-Free/Data-Sparse Softmax Parameter Estimation with Structured Class Geometries


Title	Data-Free/Data-Sparse Softmax Parameter Estimation with Structured Class Geometries
Authors	Nisar Ahmed
Abstract	This note considers softmax parameter estimation when little/no labeled training data is available, but a priori information about the relative geometry of class label log-odds boundaries is available. It is shown that `data-free’ softmax model synthesis corresponds to solving a linear system of parameter equations, wherein desired dominant class log-odds boundaries are encoded via convex polytopes that decompose the input feature space. When solvable, the linear equations yield closed-form softmax parameter solution families using class boundary polytope specifications only. This allows softmax parameter learning to be implemented without expensive brute force data sampling and numerical optimization. The linear equations can also be adapted to constrained maximum likelihood estimation in data-sparse settings. Since solutions may also fail to exist for the linear parameter equations derived from certain polytope specifications, it is thus also shown that there exist probabilistic classification problems over m convexly separable classes for which the log-odds boundaries cannot be learned using an m-class softmax model. \|
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00728v2
PDF	http://arxiv.org/pdf/1806.00728v2.pdf
PWC	https://paperswithcode.com/paper/data-freedata-sparse-softmax-parameter
Repo
Framework

Baidu Apollo EM Motion Planner


Title	Baidu Apollo EM Motion Planner
Authors	Haoyang Fan, Fan Zhu, Changchun Liu, Liangliang Zhang, Li Zhuang, Dong Li, Weicheng Zhu, Jiangtao Hu, Hongye Li, Qi Kong
Abstract	In this manuscript, we introduce a real-time motion planning system based on the Baidu Apollo (open source) autonomous driving platform. The developed system aims to address the industrial level-4 motion planning problem while considering safety, comfort and scalability. The system covers multilane and single-lane autonomous driving in a hierarchical manner: (1) The top layer of the system is a multilane strategy that handles lane-change scenarios by comparing lane-level trajectories computed in parallel. (2) Inside the lane-level trajectory generator, it iteratively solves path and speed optimization based on a Frenet frame. (3) For path and speed optimization, a combination of dynamic programming and spline-based quadratic programming is proposed to construct a scalable and easy-to-tune framework to handle traffic rules, obstacle decisions and smoothness simultaneously. The planner is scalable to both highway and lower-speed city driving scenarios. We also demonstrate the algorithm through scenario illustrations and on-road test results. The system described in this manuscript has been deployed to dozens of Baidu Apollo autonomous driving vehicles since Apollo v1.5 was announced in September 2017. As of May 16th, 2018, the system has been tested under 3,380 hours and approximately 68,000 kilometers (42,253 miles) of closed-loop autonomous driving under various urban scenarios. The algorithm described in this manuscript is available at https://github.com/ApolloAuto/apollo/tree/master/modules/planning.
Tasks	Autonomous Driving, Motion Planning
Published	2018-07-20
URL	http://arxiv.org/abs/1807.08048v1
PDF	http://arxiv.org/pdf/1807.08048v1.pdf
PWC	https://paperswithcode.com/paper/baidu-apollo-em-motion-planner
Repo
Framework

Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation


Title	Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
Authors	Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi
Abstract	Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels. When RL models overfit, even slight modifications to the environment can result in poor agent performance. This paper explores how procedurally generated levels during training can increase generality. We show that for some games procedural level generation enables generalization to new levels within the same distribution. Additionally, it is possible to achieve better performance with less data by manipulating the difficulty of the levels in response to the performance of the agent. The generality of the learned behaviors is also evaluated on a set of human-designed levels. The results suggest that the ability to generalize to human-designed levels highly depends on the design of the level generators. We apply dimensionality reduction and clustering techniques to visualize the generators’ distributions of levels and analyze to what degree they can produce levels similar to those designed by a human.
Tasks	Dimensionality Reduction
Published	2018-06-28
URL	http://arxiv.org/abs/1806.10729v5
PDF	http://arxiv.org/pdf/1806.10729v5.pdf
PWC	https://paperswithcode.com/paper/illuminating-generalization-in-deep
Repo
Framework

Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation


Title	Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation
Authors	Amarjot Singh, Nick Kingsbury
Abstract	This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation. The proposed generative architecture is able to train rapidly from relatively small labeled datasets using the introduced structural priors. In addition, the number of filters in each layer of the architecture is optimized resulting in a computationally efficient architecture. The G-SHDL network produces state-of-the-art classification performance against unsupervised and semi-supervised learning on two image datasets. Advantages of the G-SHDL network over supervised methods are demonstrated with experiments performed on training datasets of reduced size.
Tasks	Semantic Segmentation
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03374v2
PDF	http://arxiv.org/pdf/1802.03374v2.pdf
PWC	https://paperswithcode.com/paper/generative-scatternet-hybrid-deep-learning-g
Repo
Framework

Quantified Markov Logic Networks


Title	Quantified Markov Logic Networks
Authors	Víctor Gutiérrez-Basulto, Jean Christoph Jung, Ondrej Kuzelka
Abstract	Markov Logic Networks (MLNs) are well-suited for expressing statistics such as “with high probability a smoker knows another smoker” but not for expressing statements such as “there is a smoker who knows most other smokers”, which is necessary for modeling, e.g. influencers in social networks. To overcome this shortcoming, we study quantified MLNs which generalize MLNs by introducing statistical universal quantifiers, allowing to express also the latter type of statistics in a principled way. Our main technical contribution is to show that the standard reasoning tasks in quantified MLNs, maximum a posteriori and marginal inference, can be reduced to their respective MLN counterparts in polynomial time.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01183v3
PDF	http://arxiv.org/pdf/1807.01183v3.pdf
PWC	https://paperswithcode.com/paper/quantified-markov-logic-networks
Repo
Framework

Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework


Title	Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework
Authors	Shun Kiyono, Jun Suzuki, Kentaro Inui
Abstract	The current success of deep neural networks (DNNs) in an increasingly broad range of tasks involving artificial intelligence strongly depends on the quality and quantity of labeled training data. In general, the scarcity of labeled data, which is often observed in many natural language processing tasks, is one of the most important issues to be addressed. Semi-supervised learning (SSL) is a promising approach to overcoming this issue by incorporating a large amount of unlabeled data. In this paper, we propose a novel scalable method of SSL for text classification tasks. The unique property of our method, Mixture of Expert/Imitator Networks, is that imitator networks learn to “imitate” the estimated label distribution of the expert network over the unlabeled data, which potentially contributes a set of features for the classification. Our experiments demonstrate that the proposed method consistently improves the performance of several types of baseline DNNs. We also demonstrate that our method has the more data, better performance property with promising scalability to the amount of unlabeled data.
Tasks	Text Classification
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05788v2
PDF	http://arxiv.org/pdf/1810.05788v2.pdf
PWC	https://paperswithcode.com/paper/mixture-of-expertimitator-networks-scalable
Repo
Framework

SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection


Title	SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection
Authors	Ang Li, Zejian Yuan
Abstract	Detecting the occlusion from stereo images or video frames is important to many computer vision applications. Previous efforts focus on bundling it with the computation of disparity or optical flow, leading to a chicken-and-egg problem. In this paper, we leverage convolutional neural network to liberate the occlusion detection task from the interleaved, traditional calculation framework. We propose a Symmetric Network (SymmNet) to directly exploit information from an image pair, without estimating disparity or motion in advance. The proposed network is structurally left-right symmetric to learn the binocular occlusion simultaneously, aimed at jointly improving both results. The comprehensive experiments show that our model achieves state-of-the-art results on detecting the stereo and motion occlusion.
Tasks	Optical Flow Estimation
Published	2018-07-03
URL	http://arxiv.org/abs/1807.00959v2
PDF	http://arxiv.org/pdf/1807.00959v2.pdf
PWC	https://paperswithcode.com/paper/symmnet-a-symmetric-convolutional-neural
Repo
Framework

Analyzing Business Process Anomalies Using Autoencoders


Title	Analyzing Business Process Anomalies Using Autoencoders
Authors	Timo Nolle, Stefan Luettgen, Alexander Seeliger, Max Mühlhäuser
Abstract	Businesses are naturally interested in detecting anomalies in their internal processes, because these can be indicators for fraud and inefficiencies. Within the domain of business intelligence, classic anomaly detection is not very frequently researched. In this paper, we propose a method, using autoencoders, for detecting and analyzing anomalies occurring in the execution of a business process. Our method does not rely on any prior knowledge about the process and can be trained on a noisy dataset already containing the anomalies. We demonstrate its effectiveness by evaluating it on 700 different datasets and testing its performance against three state-of-the-art anomaly detection methods. This paper is an extension of our previous work from 2016 [30]. Compared to the original publication we have further refined the approach in terms of performance and conducted an elaborate evaluation on more sophisticated datasets including real-life event logs from the Business Process Intelligence Challenges of 2012 and 2017. In our experiments our approach reached an F1 score of 0.87, whereas the best unaltered state-of-the-art approach reached an F1 score of 0.72. Furthermore, our approach can be used to analyze the detected anomalies in terms of which event within one execution of the process causes the anomaly.
Tasks	Anomaly Detection
Published	2018-03-03
URL	http://arxiv.org/abs/1803.01092v1
PDF	http://arxiv.org/pdf/1803.01092v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-business-process-anomalies-using
Repo
Framework