May 7, 2019

2714 words 13 mins read

Paper Group ANR 81

Review of the Fingerprint Liveness Detection (LivDet) competition series: 2009 to 2015. Learning Gaze Transitions from Depth to Improve Video Saliency Estimation. Principled Option Learning in Markov Decision Processes. The use of deep learning in image segmentation, classification and detection. A pre-semantics for counterfactual conditionals and …

Review of the Fingerprint Liveness Detection (LivDet) competition series: 2009 to 2015


Title	Review of the Fingerprint Liveness Detection (LivDet) competition series: 2009 to 2015
Authors	Luca Ghiani, David A. Yambay, Valerio Mura, Gian Luca Marcialis, Fabio Roli, Stephanie A. Schuckers
Abstract	A spoof attack, a subset of presentation attacks, is the use of an artificial replica of a biometric in an attempt to circumvent a biometric sensor. Liveness detection, or presentation attack detection, distinguishes between live and fake biometric traits and is based on the principle that additional information can be garnered above and beyond the data procured by a standard authentication system to determine if a biometric measure is authentic. The goals for the Liveness Detection (LivDet) competitions are to compare software-based fingerprint liveness detection and artifact detection algorithms (Part 1), as well as fingerprint systems which incorporate liveness detection or artifact detection capabilities (Part 2), using a standardized testing protocol and large quantities of spoof and live tests. The competitions are open to all academic and industrial institutions which have a solution for either softwarebased or system-based fingerprint liveness detection. The LivDet competitions have been hosted in 2009, 2011, 2013 and 2015 and have shown themselves to provide a crucial look at the current state of the art in liveness detection schemes. There has been a noticeable increase in the number of participants in LivDet competitions as well as a noticeable decrease in error rates across competitions. Participants have grown from four to the most recent thirteen submissions for Fingerprint Part 1. Fingerprints Part 2 has held steady at two submissions each competition in 2011 and 2013 and only one for the 2015 edition. The continuous increase of competitors demonstrates a growing interest in the topic.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01648v1
PDF	http://arxiv.org/pdf/1609.01648v1.pdf
PWC	https://paperswithcode.com/paper/review-of-the-fingerprint-liveness-detection
Repo
Framework

Learning Gaze Transitions from Depth to Improve Video Saliency Estimation


Title	Learning Gaze Transitions from Depth to Improve Video Saliency Estimation
Authors	G. Leifman, D. Rudoy, T. Swedish, E. Bayro-Corrochano, R. Raskar
Abstract	In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing RGBD videos on regular 2D screens. We train a generative convolutional neural network which predicts a saliency map for a frame, given the fixation map of the previous frame. Saliency estimation in this scenario is highly important since in the near future 3D video content will be easily acquired and yet hard to display. This can be explained, on the one hand, by the dramatic improvement of 3D-capable acquisition equipment. On the other hand, despite the considerable progress in 3D display technologies, most of the 3D displays are still expensive and require wearing special glasses. To evaluate the performance of our approach, we present a new comprehensive database of eye-fixation ground-truth for RGBD videos. Our experiments indicate that integrating depth into video saliency calculation is beneficial. We demonstrate that our approach outperforms state-of-the-art methods for video saliency, achieving 15% relative improvement.
Tasks	Saliency Prediction
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03669v1
PDF	http://arxiv.org/pdf/1603.03669v1.pdf
PWC	https://paperswithcode.com/paper/learning-gaze-transitions-from-depth-to
Repo
Framework

Principled Option Learning in Markov Decision Processes


Title	Principled Option Learning in Markov Decision Processes
Authors	Roy Fox, Michal Moshkovitz, Naftali Tishby
Abstract	It is well known that options can make planning more efficient, among their many benefits. Thus far, algorithms for autonomously discovering a set of useful options were heuristic. Naturally, a principled way of finding a set of useful options may be more promising and insightful. In this paper we suggest a mathematical characterization of good sets of options using tools from information theory. This characterization enables us to find conditions for a set of options to be optimal and an algorithm that outputs a useful set of options and illustrate the proposed algorithm in simulation.
Tasks
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05524v3
PDF	http://arxiv.org/pdf/1609.05524v3.pdf
PWC	https://paperswithcode.com/paper/principled-option-learning-in-markov-decision
Repo
Framework

The use of deep learning in image segmentation, classification and detection


Title	The use of deep learning in image segmentation, classification and detection
Authors	M. S. Badea, I. I. Felea, L. M. Florea, C. Vertan
Abstract	Recent years have shown that deep learned neural networks are a valuable tool in the field of computer vision. This paper addresses the use of two different kinds of network architectures, namely LeNet and Network in Network (NiN). They will be compared in terms of both performance and computational efficiency by addressing the classification and detection problems. In this paper, multiple databases will be used to test the networks. One of them contains images depicting burn wounds from pediatric cases, another one contains an extensive number of art images and other facial databases were used for facial keypoints detection.
Tasks	Semantic Segmentation
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09612v1
PDF	http://arxiv.org/pdf/1605.09612v1.pdf
PWC	https://paperswithcode.com/paper/the-use-of-deep-learning-in-image
Repo
Framework

A pre-semantics for counterfactual conditionals and similar logics


Title	A pre-semantics for counterfactual conditionals and similar logics
Authors	Karl Schlechta
Abstract	The elegant Stalnaker/Lewis semantics for counterfactual conditonals works with distances between models. But human beings certainly have no tables of models and distances in their head. We begin here an investigation using a more realistic picture, based on findings in neuroscience. We call it a pre-semantics, as its meaning is not a description of the world, but of the brain, whose structure is (partly) determined by the world it reasons about. In the final section, we reconsider the components, and postulate that there are no atomic pictures, we can always look inside.
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1701.00696v3
PDF	http://arxiv.org/pdf/1701.00696v3.pdf
PWC	https://paperswithcode.com/paper/a-pre-semantics-for-counterfactual
Repo
Framework

Exemplar-AMMs: Recognizing Crowd Movements from Pedestrian Trajectories


Title	Exemplar-AMMs: Recognizing Crowd Movements from Pedestrian Trajectories
Authors	Wenxi Liu, Rynson W. H. Lau, Xiaogang Wang, Dinesh Manocha
Abstract	In this paper, we present a novel method to recognize the types of crowd movement from crowd trajectories using agent-based motion models (AMMs). Our idea is to apply a number of AMMs, referred to as exemplar-AMMs, to describe the crowd movement. Specifically, we propose an optimization framework that filters out the unknown noise in the crowd trajectories and measures their similarity to the exemplar-AMMs to produce a crowd motion feature. We then address our real-world crowd movement recognition problem as a multi-label classification problem. Our experiments show that the proposed feature outperforms the state-of-the-art methods in recognizing both simulated and real-world crowd movements from their trajectories. Finally, we have created a synthetic dataset, SynCrowd, which contains 2D crowd trajectories in various scenarios, generated by various crowd simulators. This dataset can serve as a training set or benchmark for crowd analysis work.
Tasks	Multi-Label Classification
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09454v1
PDF	http://arxiv.org/pdf/1603.09454v1.pdf
PWC	https://paperswithcode.com/paper/exemplar-amms-recognizing-crowd-movements
Repo
Framework

Stochastic Shortest Path with Energy Constraints in POMDPs


Title	Stochastic Shortest Path with Energy Constraints in POMDPs
Authors	Tomáš Brázdil, Krishnendu Chatterjee, Martin Chmelík, Anchit Gupta, Petr Novotný
Abstract	We consider partially observable Markov decision processes (POMDPs) with a set of target states and positive integer costs associated with every transition. The traditional optimization objective (stochastic shortest path) asks to minimize the expected total cost until the target set is reached. We extend the traditional framework of POMDPs to model energy consumption, which represents a hard constraint. The energy levels may increase and decrease with transitions, and the hard constraint requires that the energy level must remain positive in all steps till the target is reached. First, we present a novel algorithm for solving POMDPs with energy levels, developing on existing POMDP solvers and using RTDP as its main method. Our second contribution is related to policy representation. For larger POMDP instances the policies computed by existing solvers are too large to be understandable. We present an automated procedure based on machine learning techniques that automatically extracts important decisions of the policy allowing us to compute succinct human readable policies. Finally, we show experimentally that our algorithm performs well and computes succinct policies on a number of POMDP instances from the literature that were naturally enhanced with energy levels.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07565v2
PDF	http://arxiv.org/pdf/1602.07565v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-shortest-path-with-energy
Repo
Framework

Streaming Label Learning for Modeling Labels on the Fly


Title	Streaming Label Learning for Modeling Labels on the Fly
Authors	Shan You, Chang Xu, Yunhe Wang, Chao Xu, Dacheng Tao
Abstract	It is challenging to handle a large volume of labels in multi-label learning. However, existing approaches explicitly or implicitly assume that all the labels in the learning process are given, which could be easily violated in changing environments. In this paper, we define and study streaming label learning (SLL), i.e., labels are arrived on the fly, to model newly arrived labels with the help of the knowledge learned from past labels. The core of SLL is to explore and exploit the relationships between new labels and past labels and then inherit the relationship into hypotheses of labels to boost the performance of new classifiers. In specific, we use the label self-representation to model the label relationship, and SLL will be divided into two steps: a regression problem and a empirical risk minimization (ERM) problem. Both problems are simple and can be efficiently solved. We further show that SLL can generate a tighter generalization error bound for new labels than the general ERM framework with trace norm or Frobenius norm regularization. Finally, we implement extensive experiments on various benchmark datasets to validate the new setting. And results show that SLL can effectively handle the constantly emerging new labels and provides excellent classification performance.
Tasks	Multi-Label Learning
Published	2016-04-19
URL	http://arxiv.org/abs/1604.05449v1
PDF	http://arxiv.org/pdf/1604.05449v1.pdf
PWC	https://paperswithcode.com/paper/streaming-label-learning-for-modeling-labels
Repo
Framework

Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers


Title	Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers
Authors	Adam McCarthy, Christopher K. I. Williams
Abstract	Bedside monitors in Intensive Care Units (ICUs) frequently sound incorrectly, slowing response times and desensitising nurses to alarms (Chambrin, 2001), causing true alarms to be missed (Hug et al., 2011). We compare sliding window predictors with recurrent predictors to classify patient state-of-health from ICU multivariate time series; we report slightly improved performance for the RNN for three out of four targets.
Tasks	Time Series
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00662v1
PDF	http://arxiv.org/pdf/1612.00662v1.pdf
PWC	https://paperswithcode.com/paper/predicting-patient-state-of-health-using
Repo
Framework

Improved Sparse Low-Rank Matrix Estimation


Title	Improved Sparse Low-Rank Matrix Estimation
Authors	Ankit Parekh, Ivan W. Selesnick
Abstract	We address the problem of estimating a sparse low-rank matrix from its noisy observation. We propose an objective function consisting of a data-fidelity term and two parameterized non-convex penalty functions. Further, we show how to set the parameters of the non-convex penalty functions, in order to ensure that the objective function is strictly convex. The proposed objective function better estimates sparse low-rank matrices than a convex method which utilizes the sum of the nuclear norm and the $\ell_1$ norm. We derive an algorithm (as an instance of ADMM) to solve the proposed problem, and guarantee its convergence provided the scalar augmented Lagrangian parameter is set appropriately. We demonstrate the proposed method for denoising an audio signal and an adjacency matrix representing protein interactions in the `Escherichia coli’ bacteria. \|
Tasks	Denoising
Published	2016-04-29
URL	http://arxiv.org/abs/1605.00042v2
PDF	http://arxiv.org/pdf/1605.00042v2.pdf
PWC	https://paperswithcode.com/paper/improved-sparse-low-rank-matrix-estimation
Repo
Framework

Improving Automated Patent Claim Parsing: Dataset, System, and Experiments


Title	Improving Automated Patent Claim Parsing: Dataset, System, and Experiments
Authors	Mengke Hu, David Cinciruk, John MacLaren Walsh
Abstract	Off-the-shelf natural language processing software performs poorly when parsing patent claims owing to their use of irregular language relative to the corpora built from news articles and the web typically utilized to train this software. Stopping short of the extensive and expensive process of accumulating a large enough dataset to completely retrain parsers for patent claims, a method of adapting existing natural language processing software towards patent claims via forced part of speech tag correction is proposed. An Amazon Mechanical Turk collection campaign organized to generate a public corpus to train such an improved claim parsing system is discussed, identifying lessons learned during the campaign that can be of use in future NLP dataset collection campaigns with AMT. Experiments utilizing this corpus and other patent claim sets measure the parsing performance improvement garnered via the claim parsing system. Finally, the utility of the improved claim parsing system within other patent processing applications is demonstrated via experiments showing improved automated patent subject classification when the new claim parsing system is utilized to generate the features.
Tasks
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01744v1
PDF	http://arxiv.org/pdf/1605.01744v1.pdf
PWC	https://paperswithcode.com/paper/improving-automated-patent-claim-parsing
Repo
Framework

Understanding Visual Concepts with Continuation Learning


Title	Understanding Visual Concepts with Continuation Learning
Authors	William F. Whitney, Michael Chang, Tejas Kulkarni, Joshua B. Tenenbaum
Abstract	We introduce a neural network architecture and a learning algorithm to produce factorized symbolic representations. We propose to learn these concepts by observing consecutive frames, letting all the components of the hidden representation except a small discrete set (gating units) be predicted from the previous frame, and let the factors of variation in the next frame be represented entirely by these discrete gated units (corresponding to symbolic representations). We demonstrate the efficacy of our approach on datasets of faces undergoing 3D transformations and Atari 2600 games.
Tasks	Atari Games
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06822v1
PDF	http://arxiv.org/pdf/1602.06822v1.pdf
PWC	https://paperswithcode.com/paper/understanding-visual-concepts-with
Repo
Framework

Randomized Distributed Mean Estimation: Accuracy vs Communication


Title	Randomized Distributed Mean Estimation: Accuracy vs Communication
Authors	Jakub Konečný, Peter Richtárik
Abstract	We consider the problem of estimating the arithmetic average of a finite collection of real vectors stored in a distributed fashion across several compute nodes subject to a communication budget constraint. Our analysis does not rely on any statistical assumptions about the source of the vectors. This problem arises as a subproblem in many applications, including reduce-all operations within algorithms for distributed and federated optimization and learning. We propose a flexible family of randomized algorithms exploring the trade-off between expected communication cost and estimation error. Our family contains the full-communication and zero-error method on one extreme, and an $\epsilon$-bit communication and ${\cal O}\left(1/(\epsilon n)\right)$ error method on the opposite extreme. In the special case where we communicate, in expectation, a single bit per coordinate of each vector, we improve upon existing results by obtaining $\mathcal{O}(r/n)$ error, where $r$ is the number of bits used to represent a floating point value.
Tasks
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07555v1
PDF	http://arxiv.org/pdf/1611.07555v1.pdf
PWC	https://paperswithcode.com/paper/randomized-distributed-mean-estimation
Repo
Framework

The Bees Algorithm for the Vehicle Routing Problem


Title	The Bees Algorithm for the Vehicle Routing Problem
Authors	Aish Fenton
Abstract	In this thesis we present a new algorithm for the Vehicle Routing Problem called the Enhanced Bees Algorithm. It is adapted from a fairly recent algorithm, the Bees Algorithm, which was developed for continuous optimisation problems. We show that the results obtained by the Enhanced Bees Algorithm are competitive with the best meta-heuristics available for the Vehicle Routing Problem (within 0.5% of the optimal solution for common benchmark problems). We show that the algorithm has good runtime performance, producing results within 2% of the optimal solution within 60 seconds, making it suitable for use within real world dispatch scenarios.
Tasks
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05448v1
PDF	http://arxiv.org/pdf/1605.05448v1.pdf
PWC	https://paperswithcode.com/paper/the-bees-algorithm-for-the-vehicle-routing
Repo
Framework

On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent


Title	On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent
Authors	Bo Han, Ivor W. Tsang, Ling Chen
Abstract	The convergence of Stochastic Gradient Descent (SGD) using convex loss functions has been widely studied. However, vanilla SGD methods using convex losses cannot perform well with noisy labels, which adversely affect the update of the primal variable in SGD methods. Unfortunately, noisy labels are ubiquitous in real world applications such as crowdsourcing. To handle noisy labels, in this paper, we present a family of robust losses for SGD methods. By employing our robust losses, SGD methods successfully reduce negative effects caused by noisy labels on each update of the primal variable. We not only reveal that the convergence rate is O(1/T) for SGD methods using robust losses, but also provide the robustness analysis on two representative robust losses. Comprehensive experimental results on six real-world datasets show that SGD methods using robust losses are obviously more robust than other baseline methods in most situations with fast convergence.
Tasks
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01623v1
PDF	http://arxiv.org/pdf/1605.01623v1.pdf
PWC	https://paperswithcode.com/paper/on-the-convergence-of-a-family-of-robust
Repo
Framework