October 16, 2019

3052 words 15 mins read

Paper Group ANR 1014

MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses. Human Activity Recognition in RGB-D Videos by Dynamic Images. Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach. On Convergence of Moments for Approximating Processes and Applications to Surrogate Models. Who Killed Albert Einstein? F …

MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses


Title	MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses
Authors	Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Alessio Del Bue, Fabio Galasso, Marco Cristani
Abstract	Recent approaches on trajectory forecasting use tracklets to predict the future positions of pedestrians exploiting Long Short Term Memory (LSTM) architectures. This paper shows that adding vislets, that is, short sequences of head pose estimations, allows to increase significantly the trajectory forecasting performance. We then propose to use vislets in a novel framework called MX-LSTM, capturing the interplay between tracklets and vislets thanks to a joint unconstrained optimization of full covariance matrices during the LSTM backpropagation. At the same time, MX-LSTM predicts the future head poses, increasing the standard capabilities of the long-term trajectory forecasting approaches. With standard head pose estimators and an attentional-based social pooling, MX-LSTM scores the new trajectory forecasting state-of-the-art in all the considered datasets (Zara01, Zara02, UCY, and TownCentre) with a dramatic margin when the pedestrians slow down, a case where most of the forecasting approaches struggle to provide an accurate solution.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00652v1
PDF	http://arxiv.org/pdf/1805.00652v1.pdf
PWC	https://paperswithcode.com/paper/mx-lstm-mixing-tracklets-and-vislets-to
Repo
Framework

Human Activity Recognition in RGB-D Videos by Dynamic Images


Title	Human Activity Recognition in RGB-D Videos by Dynamic Images
Authors	Snehasis Mukherjee, Leburu Anvitha, T. Mohana Lahari
Abstract	Human Activity Recognition in RGB-D videos has been an active research topic during the last decade. However, no efforts have been found in the literature, for recognizing human activity in RGB-D videos where several performers are performing simultaneously. In this paper we introduce such a challenging dataset with several performers performing the activities. We present a novel method for recognizing human activities in such videos. The proposed method aims in capturing the motion information of the whole video by producing a dynamic image corresponding to the input video. We use two parallel ResNext-101 to produce the dynamic images for the RGB video and depth video separately. The dynamic images contain only the motion information and hence, the unnecessary background information are eliminated. We send the two dynamic images extracted from the RGB and Depth videos respectively, through a fully connected layer of neural networks. The proposed dynamic image reduces the complexity of the recognition process by extracting a sparse matrix from a video. However, the proposed system maintains the required motion information for recognizing the activity. The proposed method has been tested on the MSR Action 3D dataset and has shown comparable performances with respect to the state-of-the-art. We also apply the proposed method on our own dataset, where the proposed method outperforms the state-of-the-art approaches.
Tasks	Activity Recognition, Human Activity Recognition
Published	2018-07-09
URL	http://arxiv.org/abs/1807.02947v1
PDF	http://arxiv.org/pdf/1807.02947v1.pdf
PWC	https://paperswithcode.com/paper/human-activity-recognition-in-rgb-d-videos-by
Repo
Framework

Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach


Title	Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach
Authors	Mehmet Necip Kurt, Oyetunji Ogundijo, Chong Li, Xiaodong Wang
Abstract	Early detection of cyber-attacks is crucial for a safe and reliable operation of the smart grid. In the literature, outlier detection schemes making sample-by-sample decisions and online detection schemes requiring perfect attack models have been proposed. In this paper, we formulate the online attack/anomaly detection problem as a partially observable Markov decision process (POMDP) problem and propose a universal robust online detection algorithm using the framework of model-free reinforcement learning (RL) for POMDPs. Numerical studies illustrate the effectiveness of the proposed RL-based algorithm in timely and accurate detection of cyber-attacks targeting the smart grid.
Tasks	Anomaly Detection, Cyber Attack Detection, Outlier Detection
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05258v1
PDF	http://arxiv.org/pdf/1809.05258v1.pdf
PWC	https://paperswithcode.com/paper/online-cyber-attack-detection-in-smart-grid-a
Repo
Framework

On Convergence of Moments for Approximating Processes and Applications to Surrogate Models


Title	On Convergence of Moments for Approximating Processes and Applications to Surrogate Models
Authors	Ansgar Steland
Abstract	We study critera for a pair $ ({ X_n } $, $ { Y_n }) $ of approximating processes which guarantee closeness of moments by generalizing known results for the special case that $ Y_n = Y $ for all $n$ and $ X_n $ converges to $Y$ in probability. This problem especially arises when working with surrogate models, e.g. to enrich observed data by simulated data, where the surrogates $Y_n$'s are constructed to justify that they approximate the $ X_n $'s. The results of this paper deal with sequences of random variables. Since this framework does not cover many applications where surrogate models such as deep neural networks are used to approximate more general stochastic processes, we extend the results to the more general framework of random fields of stochastic processes. This framework especially covers image data and sequences of images. We show that uniform integrability is sufficient, and this holds even for the case of processes provided they satisfy a weak stationarity condition.
Tasks
Published	2018-04-28
URL	http://arxiv.org/abs/1804.10821v1
PDF	http://arxiv.org/pdf/1804.10821v1.pdf
PWC	https://paperswithcode.com/paper/on-convergence-of-moments-for-approximating
Repo
Framework

Who Killed Albert Einstein? From Open Data to Murder Mystery Games


Title	Who Killed Albert Einstein? From Open Data to Murder Mystery Games
Authors	Gabriella A. B. Barros, Michael Cerny Green, Antonios Liapis, Julian Togelius
Abstract	This paper presents a framework for generating adventure games from open data. Focusing on the murder mystery type of adventure games, the generator is able to transform open data from Wikipedia articles, OpenStreetMap and images from Wikimedia Commons into WikiMysteries. Every WikiMystery game revolves around the murder of a person with a Wikipedia article and populates the game with suspects who must be arrested by the player if guilty of the murder or absolved if innocent. Starting from only one person as the victim, an extensive generative pipeline finds suspects, their alibis, and paths connecting them from open data, transforms open data into cities, buildings, non-player characters, locks and keys and dialog options. The paper describes in detail each generative step, provides a specific playthrough of one WikiMystery where Albert Einstein is murdered, and evaluates the outcomes of games generated for the 100 most influential people of the 20th century.
Tasks
Published	2018-02-14
URL	http://arxiv.org/abs/1802.05219v1
PDF	http://arxiv.org/pdf/1802.05219v1.pdf
PWC	https://paperswithcode.com/paper/who-killed-albert-einstein-from-open-data-to
Repo
Framework

Effective Character-augmented Word Embedding for Machine Reading Comprehension


Title	Effective Character-augmented Word Embedding for Machine Reading Comprehension
Authors	Zhuosheng Zhang, Yafang Huang, Pengfei Zhu, Hai Zhao
Abstract	Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-the-art baselines on various public benchmarks.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02772v1
PDF	http://arxiv.org/pdf/1808.02772v1.pdf
PWC	https://paperswithcode.com/paper/effective-character-augmented-word-embedding
Repo
Framework

Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner


Title	Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner
Authors	Yoseob Han, Jingu Kang, Jong Chul Ye
Abstract	For homeland and transportation security applications, 2D X-ray explosive detection system (EDS) have been widely used, but they have limitations in recognizing 3D shape of the hidden objects. Among various types of 3D computed tomography (CT) systems to address this issue, this paper is interested in a stationary CT using fixed X-ray sources and detectors. However, due to the limited number of projection views, analytic reconstruction algorithms produce severe streaking artifacts. Inspired by recent success of deep learning approach for sparse view CT reconstruction, here we propose a novel image and sinogram domain deep learning architecture for 3D reconstruction from very sparse view measurement. The algorithm has been tested with the real data from a prototype 9-view dual energy stationary CT EDS carry-on baggage scanner developed by GEMSS Medical Systems, Korea, which confirms the superior reconstruction performance over the existing approaches.
Tasks	3D Reconstruction, Computed Tomography (CT)
Published	2018-01-04
URL	http://arxiv.org/abs/1801.01258v1
PDF	http://arxiv.org/pdf/1801.01258v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-reconstruction-for-9-view-dual
Repo
Framework

Metric Learning with Dynamically Generated Pairwise Constraints for Ear Recognition


Title	Metric Learning with Dynamically Generated Pairwise Constraints for Ear Recognition
Authors	Ibrahim Omara, Hongzhi Zhang, Faqiang Wang, Wangmeng Zuo
Abstract	Ear recognition task is known as predicting whether two ear images belong to the same person or not. In this paper, we present a novel metric learning method for ear recognition. This method is formulated as a pairwise constrained optimization problem. In each training cycle, this method selects the nearest similar and dissimilar neighbors of each sample to construct the pairwise constraints, and then solve the optimization problem by the iterated Bregman projections. Experiments are conducted on AMI, USTB II and WPUT databases. The results show that the proposed approach can achieve promising recognition rates in ear recognition, and its training process is much more efficient than the other competing metric learning methods.
Tasks	Metric Learning
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09630v1
PDF	http://arxiv.org/pdf/1803.09630v1.pdf
PWC	https://paperswithcode.com/paper/metric-learning-with-dynamically-generated
Repo
Framework

Properties of an N Time-Slice Dynamic Chain Event Graph


Title	Properties of an N Time-Slice Dynamic Chain Event Graph
Authors	Rodrigo A. Collazo, Jim Q. Smith
Abstract	A Dynamic Chain Event Graph (DCEG) provides a rich tree-based framework for modelling a dynamic process with highly asymmetric developments. An N Time-Slice DCEG (NT-DCEG) is a useful subclass of the DCEG class that exhibits a specific type of periodicity in its supporting tree graph and embodies a time-homogeneity assumption. Here some desired properties of an NT-DCEG is explored. In particular, we prove that the class of NT-DCEGs contains all discrete N time-slice Dynamic Bayesian Networks as special cases. We also develop a method to distributively construct an NT-DCEG model. By exploiting the topology of an NT-DCEG graph, we show how to construct intrinsic random variables which exhibit context-specific independences that can then be checked by domain experts. We also show how an NT-DCEG can be used to depict various structural and Granger causal hypotheses about a given process. Our methods are illustrated throughout using examples of dynamic multivariate processes describing inmate radicalisation in a prison.
Tasks
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09414v1
PDF	http://arxiv.org/pdf/1810.09414v1.pdf
PWC	https://paperswithcode.com/paper/properties-of-an-n-time-slice-dynamic-chain
Repo
Framework

Denoising Arterial Spin Labeling Cerebral Blood Flow Images Using Deep Learning


Title	Denoising Arterial Spin Labeling Cerebral Blood Flow Images Using Deep Learning
Authors	Danfeng Xie, Li Bai, Ze Wang
Abstract	Arterial spin labeling perfusion MRI is a noninvasive technique for measuring quantitative cerebral blood flow (CBF), but the measurement is subject to a low signal-to-noise-ratio(SNR). Various post-processing methods have been proposed to denoise ASL MRI but only provide moderate improvement. Deep learning (DL) is an emerging technique that can learn the most representative signal from data without prior modeling which can be highly complex and analytically indescribable. The purpose of this study was to assess whether the record breaking performance of DL can be translated into ASL MRI denoising. We used convolutional neural network (CNN) to build the DL ASL denosing model (DL-ASL) to inherently consider the inter-voxel correlations. To better guide DL-ASL training, we incorporated prior knowledge about ASL MRI: the structural similarity between ASL CBF map and grey matter probability map. A relatively large sample data were used to train the model which was subsequently applied to a new set of data for testing. Experimental results showed that DL-ASL achieved state-of-the-art denoising performance for ASL MRI as compared to current routine methods in terms of higher SNR, keeping CBF quantification quality while shorten the acquisition time by 75%, and automatic partial volume correction.
Tasks	Denoising
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09672v1
PDF	http://arxiv.org/pdf/1801.09672v1.pdf
PWC	https://paperswithcode.com/paper/denoising-arterial-spin-labeling-cerebral
Repo
Framework

Missing Value Imputation Based on Deep Generative Models


Title	Missing Value Imputation Based on Deep Generative Models
Authors	Hongbao Zhang, Pengtao Xie, Eric Xing
Abstract	Missing values widely exist in many real-world datasets, which hinders the performing of advanced data analytics. Properly filling these missing values is crucial but challenging, especially when the missing rate is high. Many approaches have been proposed for missing value imputation (MVI), but they are mostly heuristics-based, lacking a principled foundation and do not perform satisfactorily in practice. In this paper, we propose a probabilistic framework based on deep generative models for MVI. Under this framework, imputing the missing entries amounts to seeking a fixed-point solution between two conditional distributions defined on the missing entries and latent variables respectively. These distributions are parameterized by deep neural networks (DNNs) which possess high approximation power and can capture the nonlinear relationships between missing entries and the observed values. The learning of weight parameters of DNNs is performed by maximizing an approximation of the log-likelihood of observed values. We conducted extensive evaluation on 13 datasets and compared with 11 baselines methods, where our methods largely outperforms the baselines.
Tasks	Imputation
Published	2018-08-05
URL	http://arxiv.org/abs/1808.01684v1
PDF	http://arxiv.org/pdf/1808.01684v1.pdf
PWC	https://paperswithcode.com/paper/missing-value-imputation-based-on-deep
Repo
Framework

Human-like generalization in a machine through predicate learning


Title	Human-like generalization in a machine through predicate learning
Authors	Leonidas A. A. Doumas, Guillermo Puebla, Andrea E. Martin
Abstract	Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance, but machine systems reliably struggle to generalize information to untrained situations. We describe a neural network model that is trained to play one video game (Breakout) and demonstrates one-shot generalization to a new game (Pong). The model generalizes by learning representations that are functionally and formally symbolic from training data, without feedback, and without requiring that structured representations be specified a priori. The model uses unsupervised comparison to discover which characteristics of the input are invariant, and to learn relational predicates; it then applies these predicates to arguments in a symbolic fashion, using oscillatory regularities in network firing to dynamically bind predicates to arguments. We argue that models of human cognition must account for far-reaching and flexible generalization, and that in order to do so, models must be able to discover symbolic representations from unstructured data, a process we call predicate learning. Only then can models begin to adequately explain where human-like representations come from, why human cognition is the way it is, and why it continues to differ from machine intelligence in crucial ways.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01709v3
PDF	http://arxiv.org/pdf/1806.01709v3.pdf
PWC	https://paperswithcode.com/paper/human-like-generalization-in-a-machine
Repo
Framework

Local Differential Privacy for Evolving Data


Title	Local Differential Privacy for Evolving Data
Authors	Matthew Joseph, Aaron Roth, Jonathan Ullman, Bo Waggoner
Abstract	There are now several large scale deployments of differential privacy used to collect statistical information about users. However, these deployments periodically recollect the data and recompute the statistics using algorithms designed for a single use. As a result, these systems do not provide meaningful privacy guarantees over long time scales. Moreover, existing techniques to mitigate this effect do not apply in the “local model” of differential privacy that these systems use. In this paper, we introduce a new technique for local differential privacy that makes it possible to maintain up-to-date statistics over time, with privacy guarantees that degrade only in the number of changes in the underlying distribution rather than the number of collection periods. We use our technique for tracking a changing statistic in the setting where users are partitioned into an unknown collection of groups, and at every time period each user draws a single bit from a common (but changing) group-specific distribution. We also provide an application to frequency and heavy-hitter estimation.
Tasks
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07128v3
PDF	http://arxiv.org/pdf/1802.07128v3.pdf
PWC	https://paperswithcode.com/paper/local-differential-privacy-for-evolving-data
Repo
Framework

Modelling Identity Rules with Neural Networks


Title	Modelling Identity Rules with Neural Networks
Authors	Tillman Weyde, Radha Manisha Kopparti
Abstract	In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem and answer, as well as raise, questions about integrating structures for inductive bias into neural networks. Examples of abstract patterns are the sequence patterns ABA and ABB where A or B can be any object. These were introduced by Marcus et al (1999) who also found that 7 month old infants recognise these patterns in sequences that use an unfamiliar vocabulary while simple recurrent neural networks do not.This result has been contested in the literature but it is confirmed by our experiments. We also show that the inability to generalise extends to different, previously untested, settings. We propose a new approach to modify standard neural network architectures, called Relation Based Patterns (RBP) with different variants for classification and prediction. Our experiments show that neural networks with the appropriate RBP structure achieve perfect classification and prediction performance on synthetic data, including mixed concrete and abstract patterns. RBP also improves neural network performance in experiments with real-world sequence prediction tasks. We discuss these finding in terms of challenges for neural network models and identify consequences from this result in terms of developing inductive biases for neural network learning.
Tasks
Published	2018-12-06
URL	https://arxiv.org/abs/1812.02616v2
PDF	https://arxiv.org/pdf/1812.02616v2.pdf
PWC	https://paperswithcode.com/paper/modelling-identity-rules-with-neural-networks
Repo
Framework

Fast Rotational Sparse Coding


Title	Fast Rotational Sparse Coding
Authors	Michael T. McCann, Vincent Andrearczyk, Michael Unser, Adrien Depeursinge
Abstract	We propose an algorithm for rotational sparse coding along with an efficient implementation using steerability. Sparse coding (also called dictionary learning) is an important technique in image processing, useful in inverse problems, compression, and analysis; however, the usual formulation fails to capture an important aspect of the structure of images: images are formed from building blocks, e.g., edges, lines, or points, that appear at different locations, orientations, and scales. The sparse coding problem can be reformulated to explicitly account for these transforms, at the cost of increased computation. In this work, we propose an algorithm for a rotational version of sparse coding that is based on K-SVD with additional rotation operations. We then propose a method to accelerate these rotations by learning the dictionary in a steerable basis. Our experiments on patch coding and texture classification demonstrate that the proposed algorithm is fast enough for practical use and compares favorably to standard sparse coding.
Tasks	Dictionary Learning, Texture Classification
Published	2018-06-12
URL	https://arxiv.org/abs/1806.04374v2
PDF	https://arxiv.org/pdf/1806.04374v2.pdf
PWC	https://paperswithcode.com/paper/fast-rotational-sparse-coding
Repo
Framework