May 6, 2019

3176 words 15 mins read

Paper Group ANR 158

Learning to Sketch Human Facial Portraits using Personal Styles by Case-Based Reasoning. A novel online multi-label classifier for high-speed streaming data applications. I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification. Probabilistic Feature Selection and Classification Vector Machine. Fault Detection …

Learning to Sketch Human Facial Portraits using Personal Styles by Case-Based Reasoning


Title	Learning to Sketch Human Facial Portraits using Personal Styles by Case-Based Reasoning
Authors	Bingwen Jin, Songhua Xu, Weidong Geng
Abstract	This paper employs case-based reasoning (CBR) to capture the personal styles of individual artists and generate the human facial portraits from photos accordingly. For each human artist to be mimicked, a series of cases are firstly built-up from her/his exemplars of source facial photo and hand-drawn sketch, and then its stylization for facial photo is transformed as a style-transferring process of iterative refinement by looking-for and applying best-fit cases in a sense of style optimization. Two models, fitness evaluation model and parameter estimation model, are learned for case retrieval and adaptation respectively from these cases. The fitness evaluation model is to decide which case is best-fitted to the sketching of current interest, and the parameter estimation model is to automate case adaptation. The resultant sketch is synthesized progressively with an iterative loop of retrieval and adaptation of candidate cases until the desired aesthetic style is achieved. To explore the effectiveness and advantages of the novel approach, we experimentally compare the sketch portraits generated by the proposed method with that of a state-of-the-art example-based facial sketch generation algorithm as well as a couple commercial software packages. The comparisons reveal that our CBR based synthesis method for facial portraits is superior both in capturing and reproducing artists’ personal illustration styles to the peer methods.
Tasks
Published	2016-07-10
URL	http://arxiv.org/abs/1607.02715v2
PDF	http://arxiv.org/pdf/1607.02715v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-sketch-human-facial-portraits
Repo
Framework

A novel online multi-label classifier for high-speed streaming data applications


Title	A novel online multi-label classifier for high-speed streaming data applications
Authors	Rajasekar Venkatesan, Meng Joo Er, Mihika Dave, Mahardhika Pratama, Shiqian Wu
Abstract	In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of the input data sample belongs to one or more than one of the target labels. The traditional binary and multi-class classification where each sample belongs to only one target class forms the subset of multi-label classification. Multi-label classification problems are far more complex than binary and multi-class classification problems, as both the number of target labels and each of the target labels corresponding to each of the input samples are to be identified. The proposed work exploits the high-speed nature of the extreme learning machines to achieve real-time multi-label classification of streaming data. A new threshold-based online sequential learning algorithm is proposed for high speed and streaming data classification of multi-label problems. The proposed method is experimented with six different datasets from different application domains such as multimedia, text, and biology. The hamming loss, accuracy, training time and testing time of the proposed technique is compared with nine different state-of-the-art methods. Experimental studies shows that the proposed technique outperforms the existing multi-label classifiers in terms of performance and speed.
Tasks	Multi-Label Classification
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00086v1
PDF	http://arxiv.org/pdf/1609.00086v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-online-multi-label-classifier-for
Repo
Framework

I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification


Title	I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification
Authors	Ran Dubin, Amit Dvir, Ofir Pele, Ofer Hadar
Abstract	Desktops and laptops can be maliciously exploited to violate privacy. There are two main types of attack scenarios: active and passive. In this paper, we consider the passive scenario where the adversary does not interact actively with the device, but he is able to eavesdrop on the network traffic of the device from the network side. Most of the Internet traffic is encrypted and thus passive attacks are challenging. Previous research has shown that information can be extracted from encrypted multimedia streams. This includes video title classification of non HTTP adaptive streams (non-HAS). This paper presents an algorithm for encrypted HTTP adaptive video streaming title classification. We show that an external attacker can identify the video title from video HTTP adaptive streams (HAS) sites such as YouTube. To the best of our knowledge, this is the first work that shows this. We provide a large data set of 10000 YouTube video streams of 100 popular video titles (each title downloaded 100 times) as examples for this task. The dataset was collected under real-world network conditions. We present several machine algorithms for the task and run a through set of experiments, which shows that our classification accuracy is more than 95%. We also show that our algorithms are able to classify video titles that are not in the training set as unknown and some of the algorithms are also able to eliminate false prediction of video titles and instead report unknown. Finally, we evaluate our algorithms robustness to delays and packet losses at test time and show that a solution that uses SVM is the most robust against these changes given enough training data. We provide the dataset and the crawler for future research.
Tasks
Published	2016-02-01
URL	http://arxiv.org/abs/1602.00490v2
PDF	http://arxiv.org/pdf/1602.00490v2.pdf
PWC	https://paperswithcode.com/paper/i-know-what-you-saw-last-minute-encrypted
Repo
Framework

Probabilistic Feature Selection and Classification Vector Machine


Title	Probabilistic Feature Selection and Classification Vector Machine
Authors	Bingbing Jiang, Chang Li, Maarten de Rijke, Xin Yao, Huanhuan Chen
Abstract	Sparse Bayesian learning is a state-of-the-art supervised learning algorithm that can choose a subset of relevant samples from the input data and make reliable probabilistic predictions. However, in the presence of high-dimensional data with irrelevant features, traditional sparse Bayesian classifiers suffer from performance degradation and low efficiency by failing to eliminate irrelevant features. To tackle this problem, we propose a novel sparse Bayesian embedded feature selection method that adopts truncated Gaussian distributions as both sample and feature priors. The proposed method, called probabilistic feature selection and classification vector machine (PFCVMLP ), is able to simultaneously select relevant features and samples for classification tasks. In order to derive the analytical solutions, Laplace approximation is applied to compute approximate posteriors and marginal likelihoods. Finally, parameters and hyperparameters are optimized by the type-II maximum likelihood method. Experiments on three datasets validate the performance of PFCVMLP along two dimensions: classification performance and effectiveness for feature selection. Finally, we analyze the generalization performance and derive a generalization error bound for PFCVMLP . By tightening the bound, the importance of feature selection is demonstrated.
Tasks	Feature Selection
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05486v3
PDF	http://arxiv.org/pdf/1609.05486v3.pdf
PWC	https://paperswithcode.com/paper/probabilistic-feature-selection-and
Repo
Framework

Fault Detection Engine in Intelligent Predictive Analytics Platform for DCIM


Title	Fault Detection Engine in Intelligent Predictive Analytics Platform for DCIM
Authors	Bodhisattwa Prasad Majumder, Ayan Sengupta, Sajal jain, Parikshit Bhaduri
Abstract	With the advancement of huge data generation and data handling capability, Machine Learning and Probabilistic modelling enables an immense opportunity to employ predictive analytics platform in high security critical industries namely data centers, electricity grids, utilities, airport etc. where downtime minimization is one of the primary objectives. This paper proposes a novel, complete architecture of an intelligent predictive analytics platform, Fault Engine, for huge device network connected with electrical/information flow. Three unique modules, here proposed, seamlessly integrate with available technology stack of data handling and connect with middleware to produce online intelligent prediction in critical failure scenarios. The Markov Failure module predicts the severity of a failure along with survival probability of a device at any given instances. The Root Cause Analysis model indicates probable devices as potential root cause employing Bayesian probability assignment and topological sort. Finally, a community detection algorithm produces correlated clusters of device in terms of failure probability which will further narrow down the search space of finding route cause. The whole Engine has been tested with different size of network with simulated failure environments and shows its potential to be scalable in real-time implementation.
Tasks	Community Detection, Fault Detection
Published	2016-10-16
URL	http://arxiv.org/abs/1610.04872v1
PDF	http://arxiv.org/pdf/1610.04872v1.pdf
PWC	https://paperswithcode.com/paper/fault-detection-engine-in-intelligent
Repo
Framework

Video Captioning with Multi-Faceted Attention


Title	Video Captioning with Multi-Faceted Attention
Authors	Xiang Long, Chuang Gan, Gerard de Melo
Abstract	Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual features and model structures, they do not fully exploit relevant semantic information. We present an extensible approach to jointly leverage several sorts of visual features and semantic attributes. Our novel architecture builds on LSTMs for sentence generation, with several attention layers and two multimodal layers. The attention mechanism learns to automatically select the most salient visual features or semantic attributes, and the multimodal layer yields overall representations for the input and outputs of the sentence generation component. Experimental results on the challenging MSVD and MSR-VTT datasets show that our framework outperforms the state-of-the-art approaches, while ground truth based semantic attributes are able to further elevate the output quality to a near-human level.
Tasks	Information Retrieval, Video Captioning
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00234v1
PDF	http://arxiv.org/pdf/1612.00234v1.pdf
PWC	https://paperswithcode.com/paper/video-captioning-with-multi-faceted-attention
Repo
Framework

An analytic comparison of regularization methods for Gaussian Processes


Title	An analytic comparison of regularization methods for Gaussian Processes
Authors	Hossein Mohammadi, Rodolphe Le Riche, Nicolas Durrande, Eric Touboul, Xavier Bay
Abstract	Gaussian Processes (GPs) are a popular approach to predict the output of a parameterized experiment. They have many applications in the field of Computer Experiments, in particular to perform sensitivity analysis, adaptive design of experiments and global optimization. Nearly all of the applications of GPs require the inversion of a covariance matrix that, in practice, is often ill-conditioned. Regularization methodologies are then employed with consequences on the GPs that need to be better understood.The two principal methods to deal with ill-conditioned covariance matrices are i) pseudoinverse and ii) adding a positive constant to the diagonal (the so-called nugget regularization).The first part of this paper provides an algebraic comparison of PI and nugget regularizations. Redundant points, responsible for covariance matrix singularity, are defined. It is proven that pseudoinverse regularization, contrarily to nugget regularization, averages the output values and makes the variance zero at redundant points. However, pseudoinverse and nugget regularizations become equivalent as the nugget value vanishes. A measure for data-model discrepancy is proposed which serves for choosing a regularization technique.In the second part of the paper, a distribution-wise GP is introduced that interpolates Gaussian distributions instead of data points. Distribution-wise GP can be seen as an improved regularization method for GPs.
Tasks	Gaussian Processes
Published	2016-02-02
URL	http://arxiv.org/abs/1602.00853v3
PDF	http://arxiv.org/pdf/1602.00853v3.pdf
PWC	https://paperswithcode.com/paper/an-analytic-comparison-of-regularization
Repo
Framework

Adaptive Subgradient Methods for Online AUC Maximization


Title	Adaptive Subgradient Methods for Online AUC Maximization
Authors	Yi Ding, Peilin Zhao, Steven C. H. Hoi, Yew-Soon Ong
Abstract	Learning for maximizing AUC performance is an important research problem in Machine Learning and Artificial Intelligence. Unlike traditional batch learning methods for maximizing AUC which often suffer from poor scalability, recent years have witnessed some emerging studies that attempt to maximize AUC by single-pass online learning approaches. Despite their encouraging results reported, the existing online AUC maximization algorithms often adopt simple online gradient descent approaches that fail to exploit the geometrical knowledge of the data observed during the online learning process, and thus could suffer from relatively larger regret. To address the above limitation, in this work, we explore a novel algorithm of Adaptive Online AUC Maximization (AdaOAM) which employs an adaptive gradient method that exploits the knowledge of historical gradients to perform more informative online learning. The new adaptive updating strategy of the AdaOAM is less sensitive to the parameter settings and maintains the same time complexity as previous non-adaptive counterparts. Additionally, we extend the algorithm to handle high-dimensional sparse data (SAdaOAM) and address sparsity in the solution by performing lazy gradient updating. We analyze the theoretical bounds and evaluate their empirical performance on various types of data sets. The encouraging empirical results obtained clearly highlighted the effectiveness and efficiency of the proposed algorithms.
Tasks
Published	2016-02-01
URL	http://arxiv.org/abs/1602.00351v1
PDF	http://arxiv.org/pdf/1602.00351v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-subgradient-methods-for-online-auc
Repo
Framework

Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection


Title	Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection
Authors	Wen-Sheng Chu, Fernando De la Torre, Jeffrey F. Cohn
Abstract	Facial action units (AUs) are essential to decode human facial expressions. Researchers have focused on training AU detectors with a variety of features and classifiers. However, several issues remain. These are spatial representation, temporal modeling, and AU correlation. Unlike most studies that tackle these issues separately, we propose a hybrid network architecture to jointly address them. Specifically, spatial representations are extracted by a Convolutional Neural Network (CNN), which, as analyzed in this paper, is able to reduce person-specific biases caused by hand-crafted features (eg, SIFT and Gabor). To model temporal dependencies, Long Short-Term Memory (LSTMs) are stacked on top of these representations, regardless of the lengths of input videos. The outputs of CNNs and LSTMs are further aggregated into a fusion network to produce per-frame predictions of 12 AUs. Our network naturally addresses the three issues, and leads to superior performance compared to existing methods that consider these issues independently. Extensive experiments were conducted on two large spontaneous datasets, GFT and BP4D, containing more than 400,000 frames coded with 12 AUs. On both datasets, we report significant improvement over a standard multi-label CNN and feature-based state-of-the-art. Finally, we provide visualization of the learned AU models, which, to our best knowledge, reveal how machines see facial AUs for the first time.
Tasks	Action Unit Detection, Facial Action Unit Detection
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00911v1
PDF	http://arxiv.org/pdf/1608.00911v1.pdf
PWC	https://paperswithcode.com/paper/modeling-spatial-and-temporal-cues-for-multi
Repo
Framework


Title	Pricing Vehicle Sharing with Proximity Information
Authors	Jakub Marecek, Robert Shorten, Jia Yuan Yu
Abstract	For vehicle sharing schemes, where drop-off positions are not fixed, we propose a pricing scheme, where the price depends in part on the distance between where a vehicle is being dropped off and where the closest shared vehicle is parked. Under certain restrictive assumptions, we show that this pricing leads to a socially optimal spread of the vehicles within a region.
Tasks
Published	2016-01-25
URL	http://arxiv.org/abs/1601.06672v1
PDF	http://arxiv.org/pdf/1601.06672v1.pdf
PWC	https://paperswithcode.com/paper/pricing-vehicle-sharing-with-proximity
Repo
Framework

Dynamic Privacy For Distributed Machine Learning Over Network


Title	Dynamic Privacy For Distributed Machine Learning Over Network
Authors	Tao Zhang, Quanyan Zhu
Abstract	Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops two methods to provide differential privacy to distributed learning algorithms over a network. We first decentralize the learning algorithm using the alternating direction method of multipliers (ADMM), and propose the methods of dual variable perturbation and primal variable perturbation to provide dynamic differential privacy. The two mechanisms lead to algorithms that can provide privacy guarantees under mild conditions of the convexity and differentiability of the loss function and the regularizer. We study the performance of the algorithms, and show that the dual variable perturbation outperforms its primal counterpart. To design an optimal privacy mechanisms, we analyze the fundamental tradeoff between privacy and accuracy, and provide guidelines to choose privacy parameters. Numerical experiments using customer information database are performed to corroborate the results on privacy and utility tradeoffs and design.
Tasks
Published	2016-01-14
URL	http://arxiv.org/abs/1601.03466v3
PDF	http://arxiv.org/pdf/1601.03466v3.pdf
PWC	https://paperswithcode.com/paper/dynamic-privacy-for-distributed-machine
Repo
Framework

Deep CTR Prediction in Display Advertising


Title	Deep CTR Prediction in Display Advertising
Authors	Junxuan Chen, Baigui Sun, Hao Li, Hongtao Lu, Xian-Sheng Hua
Abstract	Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model. However, LR model lacks the ability of extracting complex and intrinsic nonlinear features from handcrafted high-dimensional image features, which limits its effectiveness. To solve this issue, in this paper, we introduce a novel deep neural network (DNN) based model that directly predicts the CTR of an image ad based on raw image pixels and other basic features in one step. The DNN model employs convolution layers to automatically extract representative visual features from images, and nonlinear CTR features are then learned from visual features and other contextual features by using fully-connected layers. Empirical evaluations on a real world dataset with over 50 million records demonstrate the effectiveness and efficiency of this method.
Tasks	Click-Through Rate Prediction
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06018v1
PDF	http://arxiv.org/pdf/1609.06018v1.pdf
PWC	https://paperswithcode.com/paper/deep-ctr-prediction-in-display-advertising
Repo
Framework

Coherent Dialogue with Attention-based Language Models


Title	Coherent Dialogue with Attention-based Language Models
Authors	Hongyuan Mei, Mohit Bansal, Matthew R. Walter
Abstract	We model coherent conversation continuation via RNN-based dialogue models equipped with a dynamic attention mechanism. Our attention-RNN language model dynamically increases the scope of attention on the history as the conversation continues, as opposed to standard attention (or alignment) models with a fixed input scope in a sequence-to-sequence model. This allows each generated word to be associated with the most relevant words in its corresponding conversation history. We evaluate the model on two popular dialogue datasets, the open-domain MovieTriples dataset and the closed-domain Ubuntu Troubleshoot dataset, and achieve significant improvements over the state-of-the-art and baselines on several metrics, including complementary diversity-based metrics, human evaluation, and qualitative visualizations. We also show that a vanilla RNN with dynamic attention outperforms more complex memory models (e.g., LSTM and GRU) by allowing for flexible, long-distance memory. We promote further coherence via topic modeling-based reranking.
Tasks	Language Modelling
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06997v1
PDF	http://arxiv.org/pdf/1611.06997v1.pdf
PWC	https://paperswithcode.com/paper/coherent-dialogue-with-attention-based
Repo
Framework

Improved Knowledge Base Completion by Path-Augmented TransR Model


Title	Improved Knowledge Base Completion by Path-Augmented TransR Model
Authors	Wenhao Huang, Ge Li, Zhi Jin
Abstract	Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link prediction. In our approach, we base PTransR model on TransR, which is the best one-hop model at present. Then we regularize TransR with information of relation paths. In our experiment, we evaluate PTransR on the task of entity prediction. Experimental results show that PTransR outperforms previous models.
Tasks	Knowledge Base Completion, Link Prediction
Published	2016-10-06
URL	http://arxiv.org/abs/1610.04073v1
PDF	http://arxiv.org/pdf/1610.04073v1.pdf
PWC	https://paperswithcode.com/paper/improved-knowledge-base-completion-by-path
Repo
Framework

Deep Neural Networks Under Stress


Title	Deep Neural Networks Under Stress
Authors	Micael Carvalho, Matthieu Cord, Sandra Avila, Nicolas Thome, Eduardo Valle
Abstract	In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets. The properties of their features remain, however, largely unstudied under the transfer perspective. In this work, we present an extensive analysis of the resiliency of feature vectors extracted from deep models, with special focus on the trade-off between performance and compression rate. By introducing perturbations to image descriptions extracted from a deep convolutional neural network, we change their precision and number of dimensions, measuring how it affects the final score. We show that deep features are more robust to these disturbances when compared to classical approaches, achieving a compression rate of 98.4%, while losing only 0.88% of their original score for Pascal VOC 2007.
Tasks	Transfer Learning
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03498v2
PDF	http://arxiv.org/pdf/1605.03498v2.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-under-stress
Repo
Framework