July 28, 2019

3158 words 15 mins read

Paper Group ANR 241

Cheryl’s Birthday. Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN. Approximation of probability density functions on the Euclidean group parametrized by dual quaternions. Job Detection in Twitter. Fast Gesture Recognition with Multiple Stream Discrete HMMs on 3D Skeletons. Accurate Motion Estimation through Random Sample …

Cheryl’s Birthday


Title	Cheryl’s Birthday
Authors	Hans van Ditmarsch, Michael Ian Hartley, Barteld Kooi, Jonathan Welton, Joseph B. W. Yeo
Abstract	We present four logic puzzles and after that their solutions. Joseph Yeo designed ‘Cheryl’s Birthday’. Mike Hartley came up with a novel solution for ‘One Hundred Prisoners and a Light Bulb’. Jonathan Welton designed ‘A Blind Guess’ and ‘Abby’s Birthday’. Hans van Ditmarsch and Barteld Kooi authored the puzzlebook ‘One Hundred Prisoners and a Light Bulb’ that contains other knowledge puzzles, and that can also be found on the webpage http://personal.us.es/hvd/lightbulb.html dedicated to the book.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1708.02654v1
PDF	http://arxiv.org/pdf/1708.02654v1.pdf
PWC	https://paperswithcode.com/paper/cheryls-birthday
Repo
Framework

Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN


Title	Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
Authors	Xiangteng He, Yuxin Peng, Junjie Zhao
Abstract	Discriminative localization is essential for fine-grained image classification task, which devotes to recognizing hundreds of subcategories in the same basic-level category. Reflecting on discriminative regions of objects, key differences among different subcategories are subtle and local. Existing methods generally adopt a two-stage learning framework: The first stage is to localize the discriminative regions of objects, and the second is to encode the discriminative features for training classifiers. However, these methods generally have two limitations: (1) Separation of the two-stage learning is time-consuming. (2) Dependence on object and parts annotations for discriminative localization learning leads to heavily labor-consuming labeling. It is highly challenging to address these two important limitations simultaneously. Existing methods only focus on one of them. Therefore, this paper proposes the discriminative localization approach via saliency-guided Faster R-CNN to address the above two limitations at the same time, and our main novelties and advantages are: (1) End-to-end network based on Faster R-CNN is designed to simultaneously localize discriminative regions and encode discriminative features, which accelerates classification speed. (2) Saliency-guided localization learning is proposed to localize the discriminative region automatically, avoiding labor-consuming labeling. Both are jointly employed to simultaneously accelerate classification speed and eliminate dependence on object and parts annotations. Comparing with the state-of-the-art methods on the widely-used CUB-200-2011 dataset, our approach achieves both the best classification accuracy and efficiency.
Tasks	Fine-Grained Image Classification, Image Classification
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08295v1
PDF	http://arxiv.org/pdf/1709.08295v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-discriminative-localization-via
Repo
Framework

Approximation of probability density functions on the Euclidean group parametrized by dual quaternions


Title	Approximation of probability density functions on the Euclidean group parametrized by dual quaternions
Authors	Muriel Lang
Abstract	Perception is fundamental to many robot application areas especially in service robotics. Our aim is to perceive and model an unprepared kitchen scenario with many objects. We start with the perception of a single target object. The modeling relies especially on fusing and merging of weak information from the sensors of the robot in order to localize objects. This requires the representation of various probability distributions of pose in $S_3 \times \mathbb{R}^3$ as orientation and position have to be localized. In this thesis I present a framework for probabilistic modeling of poses in $S_3 \times \mathbb{R}^3$ that represents a large class of probability distributions and provides among others the operations of the fusion and the merge of estimates. Further it offers the propagation of uncertain information data. I work out why we choose to represent the orientation part of a pose by a unit quaternion. The translation part is described either by a 3-dimensional vector or by a purely imaginary quaternion. This depends on whether we define the probability density function or whether we want to represent a transformation which consists of a rotation and a translation by a dual quaternion. A basic probability den- sity function over the poses is defined by a tangent point on the hypersphere and a 6-dimensional Gaussian distribution. The hypersphere is embedded to the R4 which is representing a unit quaternions whereas the Gaussian is defined over the product of the tangent space of the sphere and of the space of translations. The projection of this Gaussian to the hypersphere induces a distribution over poses in $S_3 \times \mathbb{R}^3$. The set of mixtures of projected Gaussians can approximate the probability density functions that arise in our application. Moreover it is closed under the operations introduced in this framework and allows for an efficient implementation.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1707.00532v1
PDF	http://arxiv.org/pdf/1707.00532v1.pdf
PWC	https://paperswithcode.com/paper/approximation-of-probability-density
Repo
Framework

Job Detection in Twitter


Title	Job Detection in Twitter
Authors	Besat Kassaie
Abstract	In this report, we propose a new application for twitter data called \textit{job detection}. We identify people’s job category based on their tweets. As a preliminary work, we limited our task to identify only IT workers from other job holders. We have used and compared both simple bag of words model and a document representation based on Skip-gram model. Our results show that the model based on Skip-gram, achieves a 76% precision and 82% recall.
Tasks
Published	2017-01-11
URL	http://arxiv.org/abs/1701.03092v1
PDF	http://arxiv.org/pdf/1701.03092v1.pdf
PWC	https://paperswithcode.com/paper/job-detection-in-twitter
Repo
Framework

Fast Gesture Recognition with Multiple Stream Discrete HMMs on 3D Skeletons


Title	Fast Gesture Recognition with Multiple Stream Discrete HMMs on 3D Skeletons
Authors	Guido Borghi, Roberto Vezzani, Rita Cucchiara
Abstract	HMMs are widely used in action and gesture recognition due to their implementation simplicity, low computational requirement, scalability and high parallelism. They have worth performance even with a limited training set. All these characteristics are hard to find together in other even more accurate methods. In this paper, we propose a novel double-stage classification approach, based on Multiple Stream Discrete Hidden Markov Models (MSD-HMM) and 3D skeleton joint data, able to reach high performances maintaining all advantages listed above. The approach allows both to quickly classify pre-segmented gestures (offline classification), and to perform temporal segmentation on streams of gestures (online classification) faster than real time. We test our system on three public datasets, MSRAction3D, UTKinect-Action and MSRDailyAction, and on a new dataset, Kinteract Dataset, explicitly created for Human Computer Interaction (HCI). We obtain state of the art performances on all of them.
Tasks	Gesture Recognition
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02931v1
PDF	http://arxiv.org/pdf/1703.02931v1.pdf
PWC	https://paperswithcode.com/paper/fast-gesture-recognition-with-multiple-stream
Repo
Framework

Accurate Motion Estimation through Random Sample Aggregated Consensus


Title	Accurate Motion Estimation through Random Sample Aggregated Consensus
Authors	Martin Rais, Gabriele Facciolo, Enric Meinhardt-Llopis, Jean-Michel Morel, Antoni Buades, Bartomeu Coll
Abstract	We reconsider the classic problem of estimating accurately a 2D transformation from point matches between images containing outliers. RANSAC discriminates outliers by randomly generating minimalistic sampled hypotheses and verifying their consensus over the input data. Its response is based on the single hypothesis that obtained the largest inlier support. In this article we show that the resulting accuracy can be improved by aggregating all generated hypotheses. This yields RANSAAC, a framework that improves systematically over RANSAC and its state-of-the-art variants by statistically aggregating hypotheses. To this end, we introduce a simple strategy that allows to rapidly average 2D transformations, leading to an almost negligible extra computational cost. We give practical applications on projective transforms and homography+distortion models and demonstrate a significant performance gain in both cases.
Tasks	Motion Estimation
Published	2017-01-19
URL	http://arxiv.org/abs/1701.05268v1
PDF	http://arxiv.org/pdf/1701.05268v1.pdf
PWC	https://paperswithcode.com/paper/accurate-motion-estimation-through-random
Repo
Framework


Title	Integrating sentiment and social structure to determine preference alignments: The Irish Marriage Referendum
Authors	David J. P. O’Sullivan, Guillermo Garduño-Hernández, James P. Gleeson, Mariano Beguerisse-Díaz
Abstract	We examine the relationship between social structure and sentiment through the analysis of a large collection of tweets about the Irish Marriage Referendum of 2015. We obtain the sentiment of every tweet with the hashtags #marref and #marriageref that was posted in the days leading to the referendum, and construct networks to aggregate sentiment and use it to study the interactions among users. Our results show that the sentiment of mention tweets posted by users is correlated with the sentiment of received mentions, and there are significantly more connections between users with similar sentiment scores than among users with opposite scores in the mention and follower networks. We combine the community structure of the two networks with the activity level of the users and sentiment scores to find groups of users who support voting `yes' or` no’ in the referendum. There were numerous conversations between users on opposing sides of the debate in the absence of follower connections, which suggests that there were efforts by some users to establish dialogue and debate across ideological divisions. Our analysis shows that social structure can be integrated successfully with sentiment to analyse and understand the disposition of social media users. These results have potential applications in the integration of data and meta-data to study opinion dynamics, public opinion modelling, and polling.
Tasks
Published	2017-01-01
URL	http://arxiv.org/abs/1701.00289v2
PDF	http://arxiv.org/pdf/1701.00289v2.pdf
PWC	https://paperswithcode.com/paper/integrating-sentiment-and-social-structure-to
Repo
Framework

Unsupervised Real-Time Control through Variational Empowerment


Title	Unsupervised Real-Time Control through Variational Empowerment
Authors	Maximilian Karl, Maximilian Soelch, Philip Becker-Ehmck, Djalel Benbouzid, Patrick van der Smagt, Justin Bayer
Abstract	We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control. Empowerment, being the channel capacity between actions and states, maximises the influence of an agent on its near future. It has been shown to be a good model of biological behaviour in the absence of an extrinsic goal. But empowerment is also prohibitively hard to compute, especially in nonlinear continuous spaces. We introduce an efficient, amortised method for learning empowerment-maximising policies. We demonstrate that our algorithm can reliably handle continuous dynamical systems using system dynamics learned from raw data. The resulting policies consistently drive the agents into states where they can use their full potential.
Tasks
Published	2017-10-13
URL	http://arxiv.org/abs/1710.05101v1
PDF	http://arxiv.org/pdf/1710.05101v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-real-time-control-through
Repo
Framework

Deep Object-Centric Representations for Generalizable Robot Learning


Title	Deep Object-Centric Representations for Generalizable Robot Learning
Authors	Coline Devin, Pieter Abbeel, Trevor Darrell, Sergey Levine
Abstract	Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as an object-centric prior for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy. A task-independent meta-attention locates possible objects in the scene, and a task-specific attention identifies which objects are predictive of the trajectories. The scope of the task-specific attention is easily adjusted by showing demonstrations with distractor objects or with diverse relevant objects. Our results indicate that this approach exhibits good generalization across object instances using very few samples, and can be used to learn a variety of manipulation tasks using reinforcement learning.
Tasks
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04225v3
PDF	http://arxiv.org/pdf/1708.04225v3.pdf
PWC	https://paperswithcode.com/paper/deep-object-centric-representations-for
Repo
Framework

Running Time Analysis of the (1+1)-EA for OneMax and LeadingOnes under Bit-wise Noise


Title	Running Time Analysis of the (1+1)-EA for OneMax and LeadingOnes under Bit-wise Noise
Authors	Chao Qian, Chao Bian, Wu Jiang, Ke Tang
Abstract	In many real-world optimization problems, the objective function evaluation is subject to noise, and we cannot obtain the exact objective value. Evolutionary algorithms (EAs), a type of general-purpose randomized optimization algorithm, have shown able to solve noisy optimization problems well. However, previous theoretical analyses of EAs mainly focused on noise-free optimization, which makes the theoretical understanding largely insufficient. Meanwhile, the few existing theoretical studies under noise often considered the one-bit noise model, which flips a randomly chosen bit of a solution before evaluation; while in many realistic applications, several bits of a solution can be changed simultaneously. In this paper, we study a natural extension of one-bit noise, the bit-wise noise model, which independently flips each bit of a solution with some probability. We analyze the running time of the (1+1)-EA solving OneMax and LeadingOnes under bit-wise noise for the first time, and derive the ranges of the noise level for polynomial and super-polynomial running time bounds. The analysis on LeadingOnes under bit-wise noise can be easily transferred to one-bit noise, and improves the previously known results. Since our analysis discloses that the (1+1)-EA can be efficient only under low noise levels, we also study whether the sampling strategy can bring robustness to noise. We prove that using sampling can significantly increase the largest noise level allowing a polynomial running time, that is, sampling is robust to noise.
Tasks
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00956v1
PDF	http://arxiv.org/pdf/1711.00956v1.pdf
PWC	https://paperswithcode.com/paper/running-time-analysis-of-the-11-ea-for-onemax
Repo
Framework

EC3: Combining Clustering and Classification for Ensemble Learning


Title	EC3: Combining Clustering and Classification for Ensemble Learning
Authors	Tanmoy Chakraborty
Abstract	Classification and clustering algorithms have been proved to be successful individually in different contexts. Both of them have their own advantages and limitations. For instance, although classification algorithms are more powerful than clustering methods in predicting class labels of objects, they do not perform well when there is a lack of sufficient manually labeled reliable data. On the other hand, although clustering algorithms do not produce label information for objects, they provide supplementary constraints (e.g., if two objects are clustered together, it is more likely that the same label is assigned to both of them) that one can leverage for label prediction of a set of unknown objects. Therefore, systematic utilization of both these types of algorithms together can lead to better prediction performance. In this paper, We propose a novel algorithm, called EC3 that merges classification and clustering together in order to support both binary and multi-class classification. EC3 is based on a principled combination of multiple classification and multiple clustering methods using an optimization function. We theoretically show the convexity and optimality of the problem and solve it by block coordinate descent method. We additionally propose iEC3, a variant of EC3 that handles imbalanced training data. We perform an extensive experimental analysis by comparing EC3 and iEC3 with 14 baseline methods (7 well-known standalone classifiers, 5 ensemble classifiers, and 2 existing methods that merge classification and clustering) on 13 standard benchmark datasets. We show that our methods outperform other baselines for every single dataset, achieving at most 10% higher AUC. Moreover our methods are faster (1.21 times faster than the best baseline), more resilient to noise and class imbalance than the best baseline method.
Tasks
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08591v1
PDF	http://arxiv.org/pdf/1708.08591v1.pdf
PWC	https://paperswithcode.com/paper/ec3-combining-clustering-and-classification
Repo
Framework

An ensemble-based online learning algorithm for streaming data


Title	An ensemble-based online learning algorithm for streaming data
Authors	Tien Thanh Nguyen, Thi Thu Thuy Nguyen, Xuan Cuong Pham, Alan Wee-Chung Liew, James C. Bezdek
Abstract	In this study, we introduce an ensemble-based approach for online machine learning. The ensemble of base classifiers in our approach is obtained by learning Naive Bayes classifiers on different training sets which are generated by projecting the original training set to lower dimensional space. We propose a mechanism to learn sequences of data using data chunks paradigm. The experiments conducted on a number of UCI datasets and one synthetic dataset demonstrate that the proposed approach performs significantly better than some well-known online learning algorithms.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.07938v1
PDF	http://arxiv.org/pdf/1704.07938v1.pdf
PWC	https://paperswithcode.com/paper/an-ensemble-based-online-learning-algorithm
Repo
Framework

Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference


Title	Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
Authors	Abhishek Kumar, Prasanna Sattigeri, P. Thomas Fletcher
Abstract	Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while also predicting the class label. Motivated by the ability of the GANs generator to capture the data manifold well, we propose to estimate the tangent space to the data manifold using GANs and employ it to inject invariances into the classifier. In the process, we propose enhancements over existing methods for learning the inverse mapping (i.e., the encoder) which greatly improves in terms of semantic similarity of the reconstructed sample with the input sample. We observe considerable empirical gains in semi-supervised learning over baselines, particularly in the cases when the number of labeled examples is low. We also provide insights into how fake examples influence the semi-supervised learning procedure.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08850v2
PDF	http://arxiv.org/pdf/1705.08850v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-with-gans-manifold
Repo
Framework

An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization


Title	An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization
Authors	Reshad Hosseini, Suvrit Sra
Abstract	We consider maximum likelihood estimation for Gaussian Mixture Models (Gmms). This task is almost invariably solved (in theory and practice) via the Expectation Maximization (EM) algorithm. EM owes its success to various factors, of which is its ability to fulfill positive definiteness constraints in closed form is of key importance. We propose an alternative to EM by appealing to the rich Riemannian geometry of positive definite matrices, using which we cast Gmm parameter estimation as a Riemannian optimization problem. Surprisingly, such an out-of-the-box Riemannian formulation completely fails and proves much inferior to EM. This motivates us to take a closer look at the problem geometry, and derive a better formulation that is much more amenable to Riemannian optimization. We then develop (Riemannian) batch and stochastic gradient algorithms that outperform EM, often substantially. We provide a non-asymptotic convergence analysis for our stochastic method, which is also the first (to our knowledge) such global analysis for Riemannian stochastic gradient. Numerous empirical results are included to demonstrate the effectiveness of our methods.
Tasks
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03267v1
PDF	http://arxiv.org/pdf/1706.03267v1.pdf
PWC	https://paperswithcode.com/paper/an-alternative-to-em-for-gaussian-mixture
Repo
Framework

Whale Optimization Based Energy-Efficient Cluster Head Selection Algorithm for Wireless Sensor Networks


Title	Whale Optimization Based Energy-Efficient Cluster Head Selection Algorithm for Wireless Sensor Networks
Authors	Ashwin R Jadhav, T. Shankar
Abstract	Wireless Sensor Network (WSN) consists of many individual sensors that are deployed in the area of interest. These sensor nodes have major energy constraints as they are small and their battery can’t be replaced. They collaborate together in order to gather, transmit and forward the sensed data to the base station. Consequently, data transmission is one of the biggest reasons for energy depletion in WSN. Clustering is one of the most effective techniques for energy efficient data transmission in WSN. In this paper, an energy efficient cluster head selection algorithm which is based on Whale Optimization Algorithm (WOA) called WOA-Clustering (WOA-C) is proposed. Accordingly, the proposed algorithm helps in selection of energy aware cluster heads based on a fitness function which considers the residual energy of the node and the sum of energy of adjacent nodes. The proposed algorithm is evaluated for network lifetime, energy efficiency, throughput and overall stability. Furthermore, the performance of WOA-C is evaluated against other standard contemporary routing protocols such as LEACH. Extensive simulations show the superior performance of the proposed algorithm in terms of residual energy, network lifetime and longer stability period.
Tasks
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09389v1
PDF	http://arxiv.org/pdf/1711.09389v1.pdf
PWC	https://paperswithcode.com/paper/whale-optimization-based-energy-efficient
Repo
Framework