May 7, 2019

2972 words 14 mins read

Paper Group ANR 9

Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding. Ranking Biomarkers Through Mutual Information. Active User Authentication for Smartphones: A Challenge Data Set and Benchmark Results. OPML: A One-Pass Closed-Form Solution for Online Metric Learning. Semi-supervised learning of local structured output …

Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding


Title	Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding
Authors	Su Zhu, Kai Yu
Abstract	This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the encoder-decoder model to fully utilize the power of deep learning. In the sequence labelling task, the input and output sequences are aligned word by word, while the attention mechanism cannot provide the exact alignment. To address this limitation, we propose a novel focus mechanism for encoder-decoder framework. Experiments on the standard ATIS dataset showed that BLSTM-LSTM with focus mechanism defined the new state-of-the-art by outperforming standard BLSTM and attention based encoder-decoder. Further experiments also show that the proposed model is more robust to speech recognition errors.
Tasks	Speech Recognition, Spoken Language Understanding
Published	2016-08-06
URL	http://arxiv.org/abs/1608.02097v2
PDF	http://arxiv.org/pdf/1608.02097v2.pdf
PWC	https://paperswithcode.com/paper/encoder-decoder-with-focus-mechanism-for
Repo
Framework

Ranking Biomarkers Through Mutual Information


Title	Ranking Biomarkers Through Mutual Information
Authors	Konstantinos Sechidis, Emily Turner, Paul D. Metcalfe, James Weatherall, Gavin Brown
Abstract	We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formalization of the problem will enable us to derive rankings of predictive/prognostic biomarkers, by estimating different, high dimensional, conditional mutual information terms. To estimate these terms, we suggest efficient low dimensional approximations, and we derive an empirical Bayes estimator, which is suitable for small or sparse datasets. Finally, we introduce a new visualisation tool that captures the prognostic and the predictive strength of a set of biomarkers. We believe this representation will prove to be a powerful tool in biomarker discovery.
Tasks
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01316v1
PDF	http://arxiv.org/pdf/1612.01316v1.pdf
PWC	https://paperswithcode.com/paper/ranking-biomarkers-through-mutual-information
Repo
Framework

Active User Authentication for Smartphones: A Challenge Data Set and Benchmark Results


Title	Active User Authentication for Smartphones: A Challenge Data Set and Benchmark Results
Authors	Upal Mahbub, Sayantan Sarkar, Vishal M. Patel, Rama Chellappa
Abstract	In this paper, automated user verification techniques for smartphones are investigated. A unique non-commercial dataset, the University of Maryland Active Authentication Dataset 02 (UMDAA-02) for multi-modal user authentication research is introduced. This paper focuses on three sensors - front camera, touch sensor and location service while providing a general description for other modalities. Benchmark results for face detection, face verification, touch-based user identification and location-based next-place prediction are presented, which indicate that more robust methods fine-tuned to the mobile platform are needed to achieve satisfactory verification accuracy. The dataset will be made available to the research community for promoting additional research.
Tasks	Face Detection, Face Verification
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07930v1
PDF	http://arxiv.org/pdf/1610.07930v1.pdf
PWC	https://paperswithcode.com/paper/active-user-authentication-for-smartphones-a
Repo
Framework

OPML: A One-Pass Closed-Form Solution for Online Metric Learning


Title	OPML: A One-Pass Closed-Form Solution for Online Metric Learning
Authors	Wenbin Li, Yang Gao, Lei Wang, Luping Zhou, Jing Huo, Yinghuan Shi
Abstract	To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper. Typically, the proposed OPML first adopts a one-pass triplet construction strategy, which aims to use only a very small number of triplets to approximate the representation ability of whole original triplets obtained by batch-manner methods. Then, OPML employs a closed-form solution to update the metric for new coming samples, which leads to a low space (i.e., $O(d)$) and time (i.e., $O(d^2)$) complexity, where $d$ is the feature dimensionality. In addition, an extension of OPML (namely COPML) is further proposed to enhance the robustness when in real case the first several samples come from the same class (i.e., cold start problem). In the experiments, we have systematically evaluated our methods (OPML and COPML) on three typical tasks, including UCI data classification, face verification, and abnormal event detection in videos, which aims to fully evaluate the proposed methods on different sample number, different feature dimensionalities and different feature extraction ways (i.e., hand-crafted and deeply-learned). The results show that OPML and COPML can obtain the promising performance with a very low computational cost. Also, the effectiveness of COPML under the cold start setting is experimentally verified.
Tasks	Face Verification, Metric Learning
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09178v1
PDF	http://arxiv.org/pdf/1609.09178v1.pdf
PWC	https://paperswithcode.com/paper/opml-a-one-pass-closed-form-solution-for
Repo
Framework

Semi-supervised learning of local structured output predictors


Title	Semi-supervised learning of local structured output predictors
Authors	Xin Du
Abstract	In this paper, we study the problem of semi-supervised structured output prediction, which aims to learn predictors for structured outputs, such as sequences, tree nodes, vectors, etc., from a set of data points of both input-output pairs and single inputs without outputs. The traditional methods to solve this problem usually learns one single predictor for all the data points, and ignores the variety of the different data points. Different parts of the data set may have different local distributions, and requires different optimal local predictors. To overcome this disadvantage of existing methods, we propose to learn different local predictors for neighborhoods of different data points, and the missing structured outputs simultaneously. In the neighborhood of each data point, we proposed to learn a linear predictor by minimizing both the complexity of the predictor and the upper bound of the structured prediction loss. The minimization is conducted by gradient descent algorithms. Experiments over four benchmark data sets, including DDSM mammography medical images, SUN natural image data set, Cora research paper data set, and Spanish news wire article sentence data set, show the advantages of the proposed method.
Tasks	Structured Prediction
Published	2016-04-11
URL	http://arxiv.org/abs/1604.03010v1
PDF	http://arxiv.org/pdf/1604.03010v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-of-local-structured
Repo
Framework

Federated Optimization: Distributed Machine Learning for On-Device Intelligence


Title	Federated Optimization: Distributed Machine Learning for On-Device Intelligence
Authors	Jakub Konečný, H. Brendan McMahan, Daniel Ramage, Peter Richtárik
Abstract	We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes. The goal is to train a high-quality centralized model. We refer to this setting as Federated Optimization. In this setting, communication efficiency is of the utmost importance and minimizing the number of rounds of communication is the principal goal. A motivating example arises when we keep the training data locally on users’ mobile devices instead of logging it to a data center for training. In federated optimziation, the devices are used as compute nodes performing computation on their local data in order to update a global model. We suppose that we have extremely large number of devices in the network — as many as the number of users of a given service, each of which has only a tiny fraction of the total data available. In particular, we expect the number of data points available locally to be much smaller than the number of devices. Additionally, since different users generate data with different patterns, it is reasonable to assume that no device has a representative sample of the overall distribution. We show that existing algorithms are not suitable for this setting, and propose a new algorithm which shows encouraging experimental results for sparse convex problems. This work also sets a path for future research needed in the context of \federated optimization.
Tasks	Distributed Optimization
Published	2016-10-08
URL	http://arxiv.org/abs/1610.02527v1
PDF	http://arxiv.org/pdf/1610.02527v1.pdf
PWC	https://paperswithcode.com/paper/federated-optimization-distributed-machine
Repo
Framework

Geometrically Convergent Distributed Optimization with Uncoordinated Step-Sizes


Title	Geometrically Convergent Distributed Optimization with Uncoordinated Step-Sizes
Authors	Angelia Nedić, Alex Olshevsky, Wei Shi, César A. Uribe
Abstract	A recent algorithmic family for distributed optimization, DIGing’s, have been shown to have geometric convergence over time-varying undirected/directed graphs. Nevertheless, an identical step-size for all agents is needed. In this paper, we study the convergence rates of the Adapt-Then-Combine (ATC) variation of the DIGing algorithm under uncoordinated step-sizes. We show that the ATC variation of DIGing algorithm converges geometrically fast even if the step-sizes are different among the agents. In addition, our analysis implies that the ATC structure can accelerate convergence compared to the distributed gradient descent (DGD) structure which has been used in the original DIGing algorithm.
Tasks	Distributed Optimization
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05877v1
PDF	http://arxiv.org/pdf/1609.05877v1.pdf
PWC	https://paperswithcode.com/paper/geometrically-convergent-distributed
Repo
Framework

Distributed Online Optimization in Dynamic Environments Using Mirror Descent


Title	Distributed Online Optimization in Dynamic Environments Using Mirror Descent
Authors	Shahin Shahrampour, Ali Jadbabaie
Abstract	This work addresses decentralized online optimization in non-stationary environments. A network of agents aim to track the minimizer of a global time-varying convex function. The minimizer evolves according to a known dynamics corrupted by an unknown, unstructured noise. At each time, the global function can be cast as a sum of a finite number of local functions, each of which is assigned to one agent in the network. Moreover, the local functions become available to agents sequentially, and agents do not have a prior knowledge of the future cost functions. Therefore, agents must communicate with each other to build an online approximation of the global function. We propose a decentralized variation of the celebrated Mirror Descent, developed by Nemirovksi and Yudin. Using the notion of Bregman divergence in lieu of Euclidean distance for projection, Mirror Descent has been shown to be a powerful tool in large-scale optimization. Our algorithm builds on Mirror Descent, while ensuring that agents perform a consensus step to follow the global function and take into account the dynamics of the global minimizer. To measure the performance of the proposed online algorithm, we compare it to its offline counterpart, where the global functions are available a priori. The gap between the two is called dynamic regret. We establish a regret bound that scales inversely in the spectral gap of the network, and more notably it represents the deviation of minimizer sequence with respect to the given dynamics. We then show that our results subsume a number of results in distributed optimization. We demonstrate the application of our method to decentralized tracking of dynamic parameters and verify the results via numerical experiments.
Tasks	Distributed Optimization
Published	2016-09-09
URL	http://arxiv.org/abs/1609.02845v1
PDF	http://arxiv.org/pdf/1609.02845v1.pdf
PWC	https://paperswithcode.com/paper/distributed-online-optimization-in-dynamic
Repo
Framework

Learning zeroth class dictionary for human action recognition


Title	Learning zeroth class dictionary for human action recognition
Authors	Jia-xin Cai, Xin Tang, Lifang Zhang, Guocan Feng
Abstract	In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the second-phase dictionary is built for recognition using reconstruction errors of the first-phase dictionary as input features. We propose a “zeroth class” trick for detecting undiscriminating frames of the test video and eliminating them before voting on the action categories. Experimental results on benchmarks demonstrate the effectiveness of our method.
Tasks	Dictionary Learning, Temporal Action Localization
Published	2016-03-13
URL	http://arxiv.org/abs/1603.04015v3
PDF	http://arxiv.org/pdf/1603.04015v3.pdf
PWC	https://paperswithcode.com/paper/learning-zeroth-class-dictionary-for-human
Repo
Framework

A Novel Motion Detection Method Resistant to Severe Illumination Changes


Title	A Novel Motion Detection Method Resistant to Severe Illumination Changes
Authors	Sahar Yousefi, M. T. Manzuri Shalmani, Jeremy Lin, Marius Staring
Abstract	Recently, there has been a considerable attention given to the motion detection problem due to the explosive growth of its applications in video analysis and surveillance systems. While the previous approaches can produce good results, an accurate detection of motion remains a challenging task due to the difficulties raised by illumination variations, occlusion, camouflage, burst physical motion, dynamic texture, and environmental changes such as those on climate changes, sunlight changes during a day, etc. In this paper, we propose a novel per-pixel motion descriptor for both motion detection and dynamic texture segmentation which outperforms the current methods in the literature particularly in severe scenarios. The proposed descriptor is based on two complementary three-dimensional-discrete wavelet transform (3D-DWT) and three-dimensional wavelet leader. In this approach, a feature vector is extracted for each pixel by applying a novel three dimensional wavelet-based motion descriptor. Then, the extracted features are clustered by a clustering method such as well-known k-means algorithm or Gaussian Mixture Model (GMM). The experimental results demonstrate the effectiveness of our proposed method compared to the other motion detection approaches from the literature. The application of the proposed method and additional experimental results for the different datasets are available at (http://dspl.ce.sharif.edu/motiondetector.html).
Tasks	Motion Detection
Published	2016-12-11
URL	http://arxiv.org/abs/1612.03382v6
PDF	http://arxiv.org/pdf/1612.03382v6.pdf
PWC	https://paperswithcode.com/paper/a-novel-motion-detection-method-resistant-to
Repo
Framework

Automatic detection of moving objects in video surveillance


Title	Automatic detection of moving objects in video surveillance
Authors	Larbi Guezouli, Hanane Belhani
Abstract	This work is in the field of video surveillance including motion detection. The video surveillance is one of essential techniques for automatic video analysis to extract crucial information or relevant scenes in video surveillance systems. The aim of our work is to propose solutions for the automatic detection of moving objects in real time with a surveillance camera. The detected objects are objects that have some geometric shape (circle, ellipse, square, and rectangle).
Tasks	Motion Detection
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03617v1
PDF	http://arxiv.org/pdf/1608.03617v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-moving-objects-in
Repo
Framework

Kernel-based Reconstruction of Space-time Functions on Dynamic Graphs


Title	Kernel-based Reconstruction of Space-time Functions on Dynamic Graphs
Authors	Daniel Romero, Vassilis N. Ioannidis, Georgios B. Giannakis
Abstract	Graph-based methods pervade the inference toolkits of numerous disciplines including sociology, biology, neuroscience, physics, chemistry, and engineering. A challenging problem encountered in this context pertains to determining the attributes of a set of vertices given those of another subset at possibly different time instants. Leveraging spatiotemporal dynamics can drastically reduce the number of observed vertices, and hence the cost of sampling. Alleviating the limited flexibility of existing approaches, the present paper broadens the existing kernel-based graph function reconstruction framework to accommodate time-evolving functions over possibly time-evolving topologies. This approach inherits the versatility and generality of kernel-based methods, for which no knowledge on distributions or second-order statistics is required. Systematic guidelines are provided to construct two families of space-time kernels with complementary strengths. The first facilitates judicious control of regularization on a space-time frequency plane, whereas the second can afford time-varying topologies. Batch and online estimators are also put forth, and a novel kernel Kalman filter is developed to obtain these estimates at affordable computational cost. Numerical tests with real data sets corroborate the merits of the proposed methods relative to competing alternatives.
Tasks
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03615v2
PDF	http://arxiv.org/pdf/1612.03615v2.pdf
PWC	https://paperswithcode.com/paper/kernel-based-reconstruction-of-space-time
Repo
Framework

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos


Title	Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos
Authors	Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin
Abstract	In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and motion detection networks are employed to localise and score actions from colour images and optical flow. In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap. In stage 3, sequences of detection boxes most likely to be associated with a single action instance, called action tubes, are constructed by solving two energy maximisation problems via dynamic programming. While in the first pass, action paths spanning the whole video are built by linking detection boxes over time using their class-specific scores and their spatial overlap, in the second pass, temporal trimming is performed by ensuring label consistency for all constituting detection boxes. We demonstrate the performance of our algorithm on the challenging UCF101, J-HMDB-21 and LIRIS-HARL datasets, achieving new state-of-the-art results across the board and significantly increasing detection speed at test time. We achieve a huge leap forward in action detection performance and report a 20% and 11% gain in mAP (mean average precision) on UCF-101 and J-HMDB-21 datasets respectively when compared to the state-of-the-art.
Tasks	Action Detection, Motion Detection, Optical Flow Estimation
Published	2016-08-04
URL	http://arxiv.org/abs/1608.01529v1
PDF	http://arxiv.org/pdf/1608.01529v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-detecting-multiple-space
Repo
Framework

A Fuzzy Logic System to Analyze a Student’s Lifestyle


Title	A Fuzzy Logic System to Analyze a Student’s Lifestyle
Authors	Sourish Ghosh, Aaditya Sanjay Boob, Nishant Nikhil, Nayan Raju Vysyaraju, Ankit Kumar
Abstract	A college student’s life can be primarily categorized into domains such as education, health, social and other activities which may include daily chores and travelling time. Time management is crucial for every student. A self realisation of one’s daily time expenditure in various domains is therefore essential to maximize one’s effective output. This paper presents how a mobile application using Fuzzy Logic and Global Positioning System (GPS) analyzes a student’s lifestyle and provides recommendations and suggestions based on the results.
Tasks
Published	2016-10-13
URL	http://arxiv.org/abs/1610.03957v2
PDF	http://arxiv.org/pdf/1610.03957v2.pdf
PWC	https://paperswithcode.com/paper/a-fuzzy-logic-system-to-analyze-a-students
Repo
Framework

Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts


Title	Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
Authors	Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
Abstract	Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive. In the last couple of years, we have observed images of digits, indoor scenes, birds, chairs, etc. being automatically generated. The expressive power of image generators have also been enhanced by introducing several forms of conditioning variables such as object names, sentences, bounding box and key-point locations. In this work, we propose a novel deep conditional generative adversarial network architecture that takes its strength from the semantic layout and scene attributes integrated as conditioning variables. We show that our architecture is able to generate realistic outdoor scene images under different conditions, e.g. day-night, sunny-foggy, with clear object boundaries.
Tasks	Image Generation
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00215v1
PDF	http://arxiv.org/pdf/1612.00215v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-generate-images-of-outdoor-scenes
Repo
Framework