October 17, 2019

3196 words 16 mins read

Paper Group ANR 715

Gated Recurrent Networks for Seizure Detection. Collective decision for open set recognition. Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder. Saliency Guided Hierarchical Robust Visual Tracking. Shallow Cue Guided Deep Visual Tracking via Mixed Models. Capturing Variabilities from Computed …

Gated Recurrent Networks for Seizure Detection


Title	Gated Recurrent Networks for Seizure Detection
Authors	Meysam Golmohammadi, Saeedeh Ziyabari, Vinit Shah, Eva Von Weltin, Christopher Campbell, Iyad Obeid, Joseph Picone
Abstract	Recurrent Neural Networks (RNNs) with sophisticated units that implement a gating mechanism have emerged as powerful technique for modeling sequential signals such as speech or electroencephalography (EEG). The latter is the focus on this paper. A significant big data resource, known as the TUH EEG Corpus (TUEEG), has recently become available for EEG research, creating a unique opportunity to evaluate these recurrent units on the task of seizure detection. In this study, we compare two types of recurrent units: long short-term memory units (LSTM) and gated recurrent units (GRU). These are evaluated using a state of the art hybrid architecture that integrates Convolutional Neural Networks (CNNs) with RNNs. We also investigate a variety of initialization methods and show that initialization is crucial since poorly initialized networks cannot be trained. Furthermore, we explore regularization of these convolutional gated recurrent networks to address the problem of overfitting. Our experiments revealed that convolutional LSTM networks can achieve significantly better performance than convolutional GRU networks. The convolutional LSTM architecture with proper initialization and regularization delivers 30% sensitivity at 6 false alarms per 24 hours.
Tasks	EEG, Seizure Detection
Published	2018-01-03
URL	http://arxiv.org/abs/1801.02471v1
PDF	http://arxiv.org/pdf/1801.02471v1.pdf
PWC	https://paperswithcode.com/paper/gated-recurrent-networks-for-seizure
Repo
Framework

Collective decision for open set recognition


Title	Collective decision for open set recognition
Authors	Chuanxing Geng, Songcan Chen
Abstract	In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively coming in batch. Recognizers in decision either reject or categorize them to some known class using empirically-set threshold. Thus the decision threshold plays a key role. However, the selection for it usually depends on the knowledge of known classes, inevitably incurring risks due to lacking available information from unknown classes. On the other hand, a more realistic OSR system should NOT just rest on a reject decision but should go further, especially for discovering the hidden unknown classes among the reject instances, whereas existing OSR methods do not pay special attention. In this paper, we introduce a novel collective/batch decision strategy with an aim to extend existing OSR for new class discovery while considering correlations among the testing instances. Specifically, a collective decision-based OSR framework (CD-OSR) is proposed by slightly modifying the Hierarchical Dirichlet process (HDP). Thanks to HDP, our CD-OSR does not need to define the decision threshold and can implement the open set recognition and new class discovery simultaneously. Finally, extensive experiments on benchmark datasets indicate the validity of CD-OSR.
Tasks	Open Set Learning
Published	2018-06-29
URL	https://arxiv.org/abs/1806.11258v5
PDF	https://arxiv.org/pdf/1806.11258v5.pdf
PWC	https://paperswithcode.com/paper/collective-decision-for-open-set-recognition
Repo
Framework

Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder


Title	Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
Authors	Yaxiang Fan, Gongjian Wen, Deren Li, Shaohua Qiu, Martin D. Levine
Abstract	We present a novel end-to-end partially supervised deep learning approach for video anomaly detection and localization using only normal samples. The insight that motivates this study is that the normal samples can be associated with at least one Gaussian component of a Gaussian Mixture Model (GMM), while anomalies either do not belong to any Gaussian component. The method is based on Gaussian Mixture Variational Autoencoder, which can learn feature representations of the normal samples as a Gaussian Mixture Model trained using deep learning. A Fully Convolutional Network (FCN) that does not contain a fully-connected layer is employed for the encoder-decoder structure to preserve relative spatial coordinates between the input image and the output feature map. Based on the joint probabilities of each of the Gaussian mixture components, we introduce a sample energy based method to score the anomaly of image test patches. A two-stream network framework is employed to combine the appearance and motion anomalies, using RGB frames for the former and dynamic flow images, for the latter. We test our approach on two popular benchmarks (UCSD Dataset and Avenue Dataset). The experimental results verify the superiority of our method compared to the state of the arts.
Tasks	Anomaly Detection
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11223v1
PDF	http://arxiv.org/pdf/1805.11223v1.pdf
PWC	https://paperswithcode.com/paper/video-anomaly-detection-and-localization-via
Repo
Framework

Saliency Guided Hierarchical Robust Visual Tracking


Title	Saliency Guided Hierarchical Robust Visual Tracking
Authors	Fangwen Tu, Shuzhi Sam Ge, Yazhe Tang, Chang Chieh Hang
Abstract	A saliency guided hierarchical visual tracking (SHT) algorithm containing global and local search phases is proposed in this paper. In global search, a top-down saliency model is novelly developed to handle abrupt motion and appearance variation problems. Nineteen feature maps are extracted first and combined with online learnt weights to produce the final saliency map and estimated target locations. After the evaluation of integration mechanism, the optimum candidate patch is passed to the local search. In local search, a superpixel based HSV histogram matching is performed jointly with an L2-RLS tracker to take both color distribution and holistic appearance feature of the object into consideration. Furthermore, a linear refinement search process with fast iterative solver is implemented to attenuate the possible negative influence of dominant particles. Both qualitative and quantitative experiments are conducted on a series of challenging image sequences. The superior performance of the proposed method over other state-of-the-art algorithms is demonstrated by comparative study.
Tasks	Visual Tracking
Published	2018-12-21
URL	http://arxiv.org/abs/1812.08973v1
PDF	http://arxiv.org/pdf/1812.08973v1.pdf
PWC	https://paperswithcode.com/paper/saliency-guided-hierarchical-robust-visual
Repo
Framework

Shallow Cue Guided Deep Visual Tracking via Mixed Models


Title	Shallow Cue Guided Deep Visual Tracking via Mixed Models
Authors	Fangwen Tu, Shuzhi Sam Ge, Chang Chieh Hang
Abstract	In this paper, a robust visual tracking approach via mixed model based convolutional neural networks (SDT) is developed. In order to handle abrupt or fast motion, a prior map is generated to facilitate the localization of region of interest (ROI) before the deep tracker is performed. A top-down saliency model with nineteen shallow cues are employed to construct the prior map with online learnt combination weights. Moreover, apart from a holistic deep learner, four local networks are also trained to learn different components of the target. The generated four local heat maps will facilitate to rectify the holistic map by eliminating the distracters to avoid drifting. Furthermore, to guarantee the instance for online update of high quality, a prioritised update strategy is implemented by casting the problem into a label noise problem. The selection probability is designed by considering both confidence values and bio-inspired memory for temporal information integration. Experiments are conducted qualitatively and quantitatively on a set of challenging image sequences. Comparative study demonstrates that the proposed algorithm outperforms other state-of-the-art methods.
Tasks	Visual Tracking
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08094v1
PDF	http://arxiv.org/pdf/1812.08094v1.pdf
PWC	https://paperswithcode.com/paper/shallow-cue-guided-deep-visual-tracking-via
Repo
Framework

Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks


Title	Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks
Authors	Umair Javaid, John A. Lee
Abstract	With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data demanding and since, medical data is not easily accessible, they suffer from data insufficiency. To deal with this limitation, different data augmentation techniques are used. Here, we propose a novel unsupervised data-driven approach for data augmentation that can generate 2D Computed Tomography (CT) images using a simple GAN. The generated CT images have good global and local features of a real CT image and can be used to augment the training datasets for effective learning. In this proof-of-concept study, we show that our proposed solution using GANs is able to capture some of the global and local CT variabilities. Our network is able to generate visually realistic CT images and we aim to further enhance its output by scaling it to a higher resolution and potentially from 2D to 3D.
Tasks	Computed Tomography (CT), Data Augmentation
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11504v1
PDF	http://arxiv.org/pdf/1805.11504v1.pdf
PWC	https://paperswithcode.com/paper/capturing-variabilities-from-computed
Repo
Framework

Relaxing and Restraining Queries for OBDA


Title	Relaxing and Restraining Queries for OBDA
Authors	Medina Andreşel, Yazmin Ibáñez-García, Magdalena Ortiz, Mantas Šimkus
Abstract	In ontology-based data access (OBDA), ontologies have been successfully employed for querying possibly unstructured and incomplete data. In this paper, we advocate using ontologies not only to formulate queries and compute their answers, but also for modifying queries by relaxing or restraining them, so that they can retrieve either more or less answers over a given dataset. Towards this goal, we first illustrate that some domain knowledge that could be naturally leveraged in OBDA can be expressed using complex role inclusions (CRI). Queries over ontologies with CRI are not first-order (FO) rewritable in general. We propose an extension of DL-Lite with CRI, and show that conjunctive queries over ontologies in this extension are FO rewritable. Our main contribution is a set of rules to relax and restrain conjunctive queries (CQs). Firstly, we define rules that use the ontology to produce CQs that are relaxations/restrictions over any dataset. Secondly, we introduce a set of data-driven rules, that leverage patterns in the current dataset, to obtain more fine-grained relaxations and restrictions.
Tasks
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02850v1
PDF	http://arxiv.org/pdf/1808.02850v1.pdf
PWC	https://paperswithcode.com/paper/relaxing-and-restraining-queries-for-obda
Repo
Framework

Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs


Title	Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs
Authors	Juraj Juraska, Marilyn Walker
Abstract	One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant domain and develop text analysis methods that systematically characterize types of sentences in the training data. We then automatically label the training data to allow us to conduct two kinds of experiments with a neural generator. First, we test the effect of training the system with different stylistic partitions and quantify the effect of smaller, but more stylistically controlled training data. Second, we propose a method of labeling the style variants during training, and show that we can modify the style of the generated utterances using our stylistic labels. We contrast and compare these methods that can be used with any existing large corpus, showing how they vary in terms of semantic quality and stylistic control.
Tasks	Text Generation
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05288v1
PDF	http://arxiv.org/pdf/1809.05288v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-variation-in-crowd-sourced
Repo
Framework

Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms


Title	Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms
Authors	Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando
Abstract	In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing with the signal reconstruction problem was proposed by Griffin and Lim. This method usually requires many iterations for the signal reconstruction process and depending on the inputs, it does not always produce high-quality audio signals. To overcome these shortcomings, we apply a learning-based approach to the signal reconstruction problem by modeling the signal reconstruction process using a deep neural network and training it using the idea of a generative adversarial network. Experimental evaluations revealed that our method was able to reconstruct signals faster with higher quality than the Griffin-Lim method.
Tasks
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02181v1
PDF	http://arxiv.org/pdf/1804.02181v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-network-based-approach
Repo
Framework

A Deeply-Recursive Convolutional Network for Crowd Counting


Title	A Deeply-Recursive Convolutional Network for Crowd Counting
Authors	Xinghao Ding, Zhirui Lin, Fujin He, Yu Wang, Yue Huang
Abstract	The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning. Recently, the convolutional neural network (CNN) based approaches have been shown to be more effective in crowd counting than traditional methods that use handcrafted features. However, the existing CNN-based methods still suffer from large number of parameters and large storage space, which require high storage and computing resources and thus limit the real-world application. Consequently, we propose a deeply-recursive network (DR-ResNet) based on ResNet blocks for crowd counting. The recursive structure makes the network deeper while keeping the number of parameters unchanged, which enhances network capability to capture statistical regularities in the context of the crowd. Besides, we generate a new dataset from the video-monitoring data of Beijing bus station. Experimental results have demonstrated that proposed method outperforms most state-of-the-art methods with far less number of parameters.
Tasks	Crowd Counting
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05633v1
PDF	http://arxiv.org/pdf/1805.05633v1.pdf
PWC	https://paperswithcode.com/paper/a-deeply-recursive-convolutional-network-for
Repo
Framework

Tempered Adversarial Networks


Title	Tempered Adversarial Networks
Authors	Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf
Abstract	Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset. We propose a simple modification that gives the generator control over the real samples which leads to a tempered learning process for both generator and discriminator. The real data distribution passes through a lens before being revealed to the discriminator, balancing the generator and discriminator by gradually revealing more detailed features necessary to produce high-quality results. The proposed module automatically adjusts the learning process to the current strength of the networks, yet is generic and easy to add to any GAN variant. In a number of experiments, we show that this can improve quality, stability and/or convergence speed across a range of different GAN architectures (DCGAN, LSGAN, WGAN-GP).
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04374v4
PDF	http://arxiv.org/pdf/1802.04374v4.pdf
PWC	https://paperswithcode.com/paper/tempered-adversarial-networks
Repo
Framework

A Convolutional Feature Map based Deep Network targeted towards Traffic Detection and Classification


Title	A Convolutional Feature Map based Deep Network targeted towards Traffic Detection and Classification
Authors	Baljit Kaur, Jhilik Bhattacharya
Abstract	This research mainly emphasizes on traffic detection thus essentially involving object detection and classification. The particular work discussed here is motivated from unsatisfactory attempts of re-using well known pre-trained object detection networks for domain specific data. In this course, some trivial issues leading to prominent performance drop are identified and ways to resolve them are discussed. For example, some simple yet relevant tricks regarding data collection and sampling prove to be very beneficial. Also, introducing a blur net to deal with blurred real time data is another important factor promoting performance elevation. We further study the neural network design issues for beneficial object classification and involve shared, region-independent convolutional features. Adaptive learning rates to deal with saddle points are also investigated and an average covariance matrix based pre-conditioned approach is proposed. We also introduce the use of optical flow features to accommodate orientation information. Experimental results demonstrate that this results in a steady rise in the performance rate.
Tasks	Object Classification, Object Detection, Optical Flow Estimation
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08769v1
PDF	http://arxiv.org/pdf/1805.08769v1.pdf
PWC	https://paperswithcode.com/paper/a-convolutional-feature-map-based-deep
Repo
Framework

Correlation Filter Selection for Visual Tracking Using Reinforcement Learning


Title	Correlation Filter Selection for Visual Tracking Using Reinforcement Learning
Authors	Yanchun Xie, Jimin Xiao, Kaizhu Huang, Jeyarajan Thiyagalingam, Yao Zhao
Abstract	Correlation filter has been proven to be an effective tool for a number of approaches in visual tracking, particularly for seeking a good balance between tracking accuracy and speed. However, correlation filter based models are susceptible to wrong updates stemming from inaccurate tracking results. To date, little effort has been devoted towards handling the correlation filter update problem. In this paper, we propose a novel approach to address the correlation filter update problem. In our approach, we update and maintain multiple correlation filter models in parallel, and we use deep reinforcement learning for the selection of an optimal correlation filter model among them. To facilitate the decision process in an efficient manner, we propose a decision-net to deal target appearance modeling, which is trained through hundreds of challenging videos using proximal policy optimization and a lightweight learning network. An exhaustive evaluation of the proposed approach on the OTB100 and OTB2013 benchmarks show that the approach is effective enough to achieve the average success rate of 62.3% and the average precision score of 81.2%, both exceeding the performance of traditional correlation filter based trackers.
Tasks	Visual Tracking
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03196v1
PDF	http://arxiv.org/pdf/1811.03196v1.pdf
PWC	https://paperswithcode.com/paper/correlation-filter-selection-for-visual
Repo
Framework

Confiding in and Listening to Virtual Agents: The Effect of Personality


Title	Confiding in and Listening to Virtual Agents: The Effect of Personality
Authors	Jingyi Li, Michelle X. Zhou, Huahai Yang, Gloria Mark
Abstract	We present an intelligent virtual interviewer that engages with a user in a text-based conversation and automatically infers the user’s psychological traits, such as personality. We investigate how the personality of a virtual interviewer influences a user’s behavior from two perspectives: the user’s willingness to confide in, and listen to, a virtual interviewer. We have developed two virtual interviewers with distinct personalities and deployed them in a real-world recruiting event. We present findings from completed interviews with 316 actual job applicants. Notably, users are more willing to confide in and listen to a virtual interviewer with a serious, assertive personality. Moreover, users’ personality traits, inferred from their chat text, influence their perception of a virtual interviewer, and their willingness to confide in and listen to a virtual interviewer. Finally, we discuss the implications of our work on building hyper-personalized, intelligent agents based on user traits.
Tasks
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00746v1
PDF	http://arxiv.org/pdf/1811.00746v1.pdf
PWC	https://paperswithcode.com/paper/confiding-in-and-listening-to-virtual-agents
Repo
Framework

Moving Objects Analytics: Survey on Future Location & Trajectory Prediction Methods


Title	Moving Objects Analytics: Survey on Future Location & Trajectory Prediction Methods
Authors	Harris Georgiou, Sophia Karagiorgou, Yannis Kontoulis, Nikos Pelekis, Petros Petrou, David Scarlatti, Yannis Theodoridis
Abstract	The tremendous growth of positioning technologies and GPS enabled devices has produced huge volumes of tracking data during the recent years. This source of information constitutes a rich input for data analytics processes, either offline (e.g. cluster analysis, hot motion discovery) or online (e.g. short-term forecasting of forthcoming positions). This paper focuses on predictive analytics for moving objects (could be pedestrians, cars, vessels, planes, animals, etc.) and surveys the state-of-the-art in the context of future location and trajectory prediction. We provide an extensive review of over 50 works, also proposing a novel taxonomy of predictive algorithms over moving objects. We also list the properties of several real datasets used in the past for validation purposes of those works and, motivated by this, we discuss challenges that arise in the transition from conventional to Big Data applications. CCS Concepts: Information systems > Spatial-temporal systems; Information systems > Data analytics; Information systems > Data mining; Computing methodologies > Machine learning Additional Key Words and Phrases: mobility data, moving object trajectories, trajectory prediction, future location prediction.
Tasks	Trajectory Prediction
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04639v1
PDF	http://arxiv.org/pdf/1807.04639v1.pdf
PWC	https://paperswithcode.com/paper/moving-objects-analytics-survey-on-future
Repo
Framework