今日学术视野(2016.03.04)
cs.AI - 人工智能cs.CL - 计算与语言
cs.CR - 加密与安全
cs.CV - 机器视觉与模式识别
cs.CY - 计算与社会
cs.DL - 数字图书馆
cs.DS - 数据结构与算法
cs.GT - 计算机科学与游戏理论
cs.HC - 人机接口
cs.IR - 信息检索
cs.LG - 自动学习
cs.SI - 社交网络与信息网络
math.OC - 优化与控制
math.ST - 统计理论
physics.soc-ph - 物理学与社会
q-bio.PE - 人口与发展
q-fin.RM - 风险管理
stat.ML - (统计)机器学习
• Filter based Taxonomy Modification for Improving Hierarchical Classification
• Character-based Neural Machine Translation
• Learning Word Segmentation Representations to Improve Named Entity Recognition for Chinese Social Media
• Decapitation via Digital Epidemics: A Bio-Inspired Transmissive Attack
• A Nonlinear Weighted Total Variation Image Reconstruction Algorithm for Electrical Capacitance Tomography
• Automatic segmentation of lizard spots using an active contour model
• Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features
• Learnt quasi-transitive similarity for retrieval from large collections of faces
• MOT16: A Benchmark for Multi-Object Tracking
• Shallow and Deep Convolutional Networks for Saliency Prediction
• Synthesized Classifiers for Zero-Shot Learning
• US-Cut: Interactive Algorithm for rapid Detection and Segmentation of Liver Tumors in Ultrasound Acquisitions
• Weakly Supervised Localization using Deep Feature Maps
• Are you Charlie or Ahmed? Cultural pluralism in Charlie Hebdo response on Twitter
• The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data
• Grand Challenges in Measuring and Characterizing Scholarly Impact
• Compressing Graphs and Indexes with Recursive Graph Bisection
• A Game-Theoretic Approach for Detection of Overlapping Communities in Dynamic Complex Networks
• Crowdsourcing On-street Parking Space Detection
• Hybrid Collaborative Filtering with Neural Networks Romaric Gaudel
• Asymptotic behavior of $\ell_p$-based Laplacian regularization in semi-supervised learning
• Continuous Deep Q-Learning with Model-based Acceleration
• Equity forecast: Predicting long term stock price movement using machine learning
• LOFS: Library of Online Streaming Feature Selection
• PLATO: Policy Learning using Adaptive Trajectory Optimization
• Probabilistic Relational Model Benchmark Generation
• Solving Combinatorial Games using Products, Projections and Lexicographically Optimal Bases
• Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization
• Fetishizing Food in Digital Age: #foodporn Around the World
• Distributed Estimation of Dynamic Parameters : Regret Analysis
• Beta generated Kumaraswamy-G and other new families of distributions
• Randomly Weighted Averages: A Multivariate Case
• Specification Test based on Convolution-type Distribution Function Estimates for Non-linear Auto-regressive Processes
• The Arrow of Time in Multivariate Time Series
• Truncated Random Measures
• Incompatibility boundaries for properties of community partitions
• Flies as Ship Captains? Digital Evolution Unravels Selective Pressures to Avoid Collision in Drosophila
• The Value of A Statistical Life in Absence of Panel Data: What can we do?
• Automatic Differentiation Variational Inference
• Molecular Graph Convolutions: Moving Beyond Fingerprints
·····································
• Filter based Taxonomy Modification for Improving Hierarchical Classification
Azad Naik, Huzefa Rangwala
http://arxiv.org/abs/1603.00772v1
Large scale classification of data organized as a hierarchy of classes has received significant attention in the literature. Top-Down (TD) Hierarchical Classification (HC), which exploits the hierarchical structure during the learning process is an effective method for dealing with problems at scale due to its computational benefits. However, its accuracy suffers due to error propagation i.e., prediction errors made at higher levels in the hierarchy cannot be corrected at lower levels. One of the main reasons behind errors at the higher levels is the presence of inconsistent nodes and links that are introduced due to the arbitrary process of creating these hierarchies by domain experts. In this paper, we propose two efficient data driven filter based approaches for hierarchical structure modification: (i) Flattening (local and global) approach that identifies and removes inconsistent nodes present within the hierarchy and (ii) Rewiring approach modifies parent-child relationships to improve the classification performance of learned models. Our extensive empirical evaluation of the proposed approaches on several image and text datasets shows improved performance over competing approaches.
• Character-based Neural Machine Translation
Marta R. Costa-Jussà, José A. R. Fonollosa
http://arxiv.org/abs/1603.00810v1
Named entity recognition, and other information extraction tasks, frequently use linguistic features such as part of speech tags or chunkings. For languages where word boundaries are not readily identified in text, word segmentation is a key first step to generating features for an NER system. While using word boundary tags as features are helpful, the signals that aid in identifying these boundaries may provide richer information for an NER system. New state-of-the-art word segmentation systems use neural models to learn representations for predicting word boundaries. We show that these same representations, jointly trained with an NER system, yield significant improvements in NER for Chinese social media. In our experiments, jointly training NER and word segmentation with an LSTM-CRF model yields nearly 5% absolute improvement over previously published results.
• Decapitation via Digital Epidemics: A Bio-Inspired Transmissive Attack
Pin-Yu Chen, Ching-Chao Lin, Shin-Ming Cheng, Hsu-Chun Hsiao, Chun-Ying Huang
http://arxiv.org/abs/1603.00588v1
The evolution of communication technology and the proliferation of electronic devices have rendered adversaries powerful means for targeted attacks via all sorts of accessible resources. In particular, owing to the intrinsic interdependency and ubiquitous connectivity of modern communication systems, adversaries can devise malware that propagates through intermediate hosts to approach the target, which we refer to as transmissive attacks. Inspired by biology, the transmission pattern of such an attack in the digital space much resembles the spread of an epidemic in real life. This paper elaborates transmissive attacks, summarizes the utility of epidemic models in communication systems, and draws connections between transmissive attacks and epidemic models. Simulations, experiments, and ongoing research challenges on transmissive attacks are also addressed.
• A Nonlinear Weighted Total Variation Image Reconstruction Algorithm for Electrical Capacitance Tomography
Kezhi Li, Daniel Holland
http://arxiv.org/abs/1603.00816v1
Based on the techniques of iterative soft thresholding on total variation penalty and adaptive reweighted compressive sensing, a new iterative reconstruction algorithm for electrical capacitance tomography (ECT) is proposed. This algorithm encourages sharp changes in the ECT image and overcomes the disadvantage of the $l_1$ minimization by equipping the total variation an adaptive weighted depending on the reconstructed image. Moreover, the nonlinear effect is also partially reduced due to the adoption of the updated accurate sensitivity matrix. Simulation results show that it recovers ECT images more precisely and therefore suitable for the imaging of multiphase systems in industrial or medical applications.
• Automatic segmentation of lizard spots using an active contour model
Jhony Giraldo, Augusto Salazar
http://arxiv.org/abs/1603.00841v1
We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as a means of computing the similarity between two sets, (ii) introduce transitivity meta-features based on the similarity of salient modes of appearance variation between sets, (iii) show how quasi-transitivity can be learnt from such features without any labelling or manual intervention, and (iv) demonstrate the effectiveness of the proposed methodology through experiments on the notoriously challenging YouTube database and two successful baselines from the literature.
• MOT16: A Benchmark for Multi-Object Tracking
Anton Milan, Laura Leal-Taixe, Ian Reid, Stefan Roth, Konrad Schindler
http://arxiv.org/abs/1603.00831v1
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for reseach. Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods. The first release of the benchmark focuses on multiple people tracking, since pedestrians are by far the most studied object in the tracking community. This paper accompanies a new release of the MOTChallenge benchmark. Unlike the initial release, all videos of MOT16 have been carefully annotated following a consistent protocol. Moreover, it not only offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.
• Shallow and Deep Convolutional Networks for Saliency Prediction
Junting Pan, Kevin McGuinness, Elisa Sayrol, Noel O'Connor, Xavier Giro-i-Nieto
http://arxiv.org/abs/1603.00845v1
The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet). The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train end-to-end architectures that are both fast and accurate. Two designs are proposed: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification. To the authors knowledge, these are the first end-to-end CNNs trained and tested for the purpose of saliency prediction.
• Synthesized Classifiers for Zero-Shot Learning
Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha
http://arxiv.org/abs/1603.00550v1
Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual features. To this end, we introduce a set of “phantom” object classes whose coordinates live in both the semantic space and the model space. Serving as bases in a dictionary, they can be optimized from labeled data such that the synthesized real object classifiers achieve optimal discriminative performance. We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen classes.
• US-Cut: Interactive Algorithm for rapid Detection and Segmentation of Liver Tumors in Ultrasound Acquisitions
Jan Egger, Philip Voglreiter, Mark Dokter, Michael Hofmann, Xiaojun Chen, Wolfram G. Zoller, Dieter Schmalstieg, Alexander Hann
http://arxiv.org/abs/1603.00546v1
Ultrasound (US) is the most commonly used liver imaging modality worldwide. It plays an important role in follow-up of cancer patients with liver metastases. We present an interactive segmentation approach for liver tumors in US acquisitions. Due to the low image quality and the low contrast between the tumors and the surrounding tissue in US images, the segmentation is very challenging. Thus, the clinical practice still relies on manual measurement and outlining of the tumors in the US images. We target this problem by applying an interactive segmentation algorithm to the US data, allowing the user to get real-time feedback of the segmentation results. The algorithm has been developed and tested hand-in-hand by physicians and computer scientists to make sure a future practical usage in a clinical setting is feasible. To cover typical acquisitions from the clinical routine, the approach has been evaluated with dozens of datasets where the tumors are hyperechoic (brighter), hypoechoic (darker) or isoechoic (similar) in comparison to the surrounding liver tissue. Due to the interactive real-time behavior of the approach, it was possible even in difficult cases to find satisfying segmentations of the tumors within seconds and without parameter settings, and the average tumor deviation was only 1.4mm compared with manual measurements. However, the long term goal is to ease the volumetric acquisition of liver tumors in order to evaluate for treatment response. Additional aim is the registration of intraoperative US images via the interactive segmentations to the patient’s pre-interventional CT acquisitions.
• Weakly Supervised Localization using Deep Feature Maps
Archith J. Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan, B. S. Manjunath
http://arxiv.org/abs/1603.00489v1
Object localization is an important computer vision problem with a variety of applications. The lack of large scale object-level annotations and the relative abundance of image-level labels makes a compelling case for weak supervision in the object localization task. Deep Convolutional Neural Networks are a class of state-of-the-art methods for the related problem of object recognition. In this paper, we describe a novel object localization algorithm which uses classification networks trained on only image labels. This weakly supervised method leverages local spatial and semantic patterns captured in the convolutional layers of classification networks. We propose an efficient beam search based approach to detect and localize multiple objects in images. The proposed method significantly outperforms the state-of-the-art in standard object detection data-sets with a 8 point increase in mAP scores.
• Are you Charlie or Ahmed? Cultural pluralism in Charlie Hebdo response on Twitter
Jisun An, Haewoon Kwak, Yelena Mejova, Sonia Alonso Saenz De Oger, Braulio Gomez Fortes
http://arxiv.org/abs/1603.00646v1
We study the response to the Charlie Hebdo shootings of January 7, 2015 on Twitter across the globe. We ask whether the stances on the issue of freedom of speech can be modeled using established sociological theories, including Huntington’s culturalist Clash of Civilizations, and those taking into consideration social context, including Density and Interdependence theories. We find support for Huntington’s culturalist explanation, in that the established traditions and norms of one’s “civilization” predetermine some of one’s opinion. However, at an individual level, we also find social context to play a significant role, with non-Arabs living in Arab countries using #JeSuisAhmed (“I am Ahmed”) five times more often when they are embedded in a mixed Arab/non-Arab (mention) network. Among Arabs living in the West, we find a great variety of responses, not altogether associated with the size of their expatriate community, suggesting other variables to be at play.
• The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data
Niall Twomey, Tom Diethe, Meelis Kull, Hao Song, Massimo Camplani, Sion Hannuna, Xenofon Fafoutis, Ni Zhu, Pete Woznowski, Peter Flach, Ian Craddock
http://arxiv.org/abs/1603.00797v1
This paper details the data and the task for the Sensor Platform for HEalthcare in Residential Environment (SPHERE) Chal- lenge that will take place in conjunction with European Conference on Machine Learning and Principles and Practice of Knowledge Discov- ery (ECML-PKDD) 2016
• Grand Challenges in Measuring and Characterizing Scholarly Impact
Chaomei Chen
http://arxiv.org/abs/1603.00812v1
The constantly growing body of scholarly knowledge of science, technology, and humanities is an asset of the mankind. While new discoveries expand the existing knowledge, they may simultaneously render some of it obsolete. It is crucial for scientists and other stakeholders to keep their knowledge up to date. Policy makers, decision makers, and the general public also need an efficient communication of scientific knowledge. Several grand challenges concerning the creation, adaptation, and diffusion of scholarly knowledge, and advance quantitative and qualitative approaches to the study of scholarly knowledge are identified.
• Compressing Graphs and Indexes with Recursive Graph Bisection
Laxman Dhulipala, Igor Kabiljo, Brian Karrer, Giuseppe Ottaviano, Sergey Pupyrev, Alon Shalita
http://arxiv.org/abs/1602.08820v1
Graph reordering is a powerful technique to increase the locality of the representations of graphs, which can be helpful in several applications. We study how the technique can be used to improve compression of graphs and inverted indexes. We extend the recent theoretical model of Chierichetti et al. (KDD 2009) for graph compression, and show how it can be employed for compression-friendly reordering of social networks and web graphs and for assigning document identifiers in inverted indexes. We design and implement a novel theoretically sound reordering algorithm that is based on recursive graph bisection. Our experiments show a significant improvement of the compression rate of graph and indexes over existing heuristics. The new method is relatively simple and allows efficient parallel and distributed implementations, which is demonstrated on graphs with billions of vertices and hundreds of billions of edges.
• A Game-Theoretic Approach for Detection of Overlapping Communities in Dynamic Complex Networks
Elham Havvaei, Narsingh Deo
http://arxiv.org/abs/1603.00509v1
The validation of any database mining methodology goes through an evaluation process where benchmarks availability is essential. In this paper, we aim to randomly generate relational database benchmarks that allow to check probabilistic dependencies among the attributes. We are particularly interested in Probabilistic Relational Models (PRMs), which extend Bayesian Networks (BNs) to a relational data mining context and enable effective and robust reasoning over relational data. Even though a panoply of works have focused, separately , on the generation of random Bayesian networks and relational databases, no work has been identified for PRMs on that track. This paper provides an algorithmic approach for generating random PRMs from scratch to fill this gap. The proposed method allows to generate PRMs as well as synthetic relational data from a randomly generated relational schema and a random set of probabilistic dependencies. This can be of interest not only for machine learning researchers to evaluate their proposals in a common framework, but also for databases designers to evaluate the effectiveness of the components of a database management system.
• Solving Combinatorial Games using Products, Projections and Lexicographically Optimal Bases
Swati Gupta, Michel Goemans, Patrick Jaillet
http://arxiv.org/abs/1603.00522v1
What food is so good as to be considered pornographic? Worldwide, the popular #foodporn hashtag has been used to share appetizing pictures of peoples' favorite culinary experiences. But social scientists ask whether #foodporn promotes an unhealthy relationship with food, as pornography would contribute to an unrealistic view of sexuality. In this study, we examine nearly 10 million Instagram posts by 1.7 million users worldwide. An overwhelming (and uniform across the nations) obsession with chocolate and cake shows the domination of sugary dessert over local cuisines. Yet, we find encouraging traits in the association of emotion and health-related topics with #foodporn, suggesting food can serve as motivation for a healthy lifestyle. Social approval also favors the healthy posts, with users posting with healthy hashtags having an average of 1,000 more followers than those with unhealthy ones. Finally, we perform a demographic analysis which shows nation-wide trends of behavior, such as a strong relationship (r=0.51) between the GDP per capita and the attention to healthiness of their favorite food. Our results expose a new facet of food “pornography”, revealing potential avenues for utilizing this precarious notion for promoting healthy lifestyles.
• Distributed Estimation of Dynamic Parameters : Regret Analysis
Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie
http://arxiv.org/abs/1603.00576v1
A new generalization of the family of Kumaraswamy-G distribution is proposed by constructing beta generated Kumaraswamy-G distribution. Three recently proposed families namely the Garhy generated family (Garhy et al., 2016), Beta-Dagum distribution and Beta-Singh-Maddala distribution (Domma and Condino, 2016) are seen as particular case of the proposed distribution among others. Useful expansions of the pdf and the cdf of the proposed family is derived and seen as infinite mixtures of the Kumaraswamy-G distribution Moments, moment generating function, quantile power series, random sample generation, density function of order statistics and their expansions, R\‘enyi entropies, asymptotes and shapes are also investigated. Two methods of parameter estimation are presented. Finally, some new classes of beta generated families are proposed for future investigations.
• Randomly Weighted Averages: A Multivariate Case
Hazhir Homei
http://arxiv.org/abs/1603.00596v1
转自：http://blog.sina.com.cn/s/blog_5396ee050102wlrq.html
页:
[1]