July 29, 2019

2866 words 14 mins read

Paper Group ANR 1

A PatchMatch-based Dense-field Algorithm for Video Copy-Move Detection and Localization. Using the SLEUTH urban growth model to simulate the impacts of future policy scenarios on urban land use in the Tehran metropolitan area in Iran. MEBoost: Variable Selection in the Presence of Measurement Error. NAG: Network for Adversary Generation. Multi-arme …

A PatchMatch-based Dense-field Algorithm for Video Copy-Move Detection and Localization


Title	A PatchMatch-based Dense-field Algorithm for Video Copy-Move Detection and Localization
Authors	Luca D’Amiano, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Abstract	We propose a new algorithm for the reliable detection and localization of video copy-move forgeries. Discovering well crafted video copy-moves may be very difficult, especially when some uniform background is copied to occlude foreground objects. To reliably detect both additive and occlusive copy-moves we use a dense-field approach, with invariant features that guarantee robustness to several post-processing operations. To limit complexity, a suitable video-oriented version of PatchMatch is used, with a multiresolution search strategy, and a focus on volumes of interest. Performance assessment relies on a new dataset, designed ad hoc, with realistic copy-moves and a wide variety of challenging situations. Experimental results show the proposed method to detect and localize video copy-moves with good accuracy even in adverse conditions.
Tasks
Published	2017-03-14
URL	http://arxiv.org/abs/1703.04636v1
PDF	http://arxiv.org/pdf/1703.04636v1.pdf
PWC	https://paperswithcode.com/paper/a-patchmatch-based-dense-field-algorithm-for
Repo
Framework

Using the SLEUTH urban growth model to simulate the impacts of future policy scenarios on urban land use in the Tehran metropolitan area in Iran


Title	Using the SLEUTH urban growth model to simulate the impacts of future policy scenarios on urban land use in the Tehran metropolitan area in Iran
Authors	Shaghayegh Kargozar Nahavandya, Lalit Kumar, Pedram Ghamisi
Abstract	The SLEUTH model, based on the Cellular Automata (CA), can be applied to city development simulation in metropolitan areas. In this study the SLEUTH model was used to model the urban expansion and predict the future possible behavior of the urban growth in Tehran. The fundamental data were five Landsat TM and ETM images of 1988, 1992, 1998, 2001 and 2010. Three scenarios were designed to simulate the spatial pattern. The first scenario assumed historical urbanization mode would persist and the only limitations for development were height and slope. The second one was a compact scenario which makes the growth mostly internal and limited the expansion of suburban areas. The last scenario proposed a polycentric urban structure which let the little patches grow without any limitation and would not consider the areas beyond the specific buffer zone from the larger patches for development. Results showed that the urban growth rate was greater in the first scenario in comparison with the other two scenarios. Also it was shown that the third scenario was more suitable for Tehran since it could avoid undesirable effects such as congestion and pollution and was more in accordance with the conditions of Tehran city.
Tasks
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01089v1
PDF	http://arxiv.org/pdf/1708.01089v1.pdf
PWC	https://paperswithcode.com/paper/using-the-sleuth-urban-growth-model-to
Repo
Framework

MEBoost: Variable Selection in the Presence of Measurement Error


Title	MEBoost: Variable Selection in the Presence of Measurement Error
Authors	Benjamin Brown, Timothy Weaver, Julian Wolfson
Abstract	We present a novel method for variable selection in regression models when covariates are measured with error. The iterative algorithm we propose, MEBoost, follows a path defined by estimating equations that correct for covariate measurement error. Via simulation, we evaluated our method and compare its performance to the recently-proposed Convex Conditioned Lasso (CoCoLasso) and to the “naive” Lasso which does not correct for measurement error. Increasing the degree of measurement error increased prediction error and decreased the probability of accurate covariate selection, but this loss of accuracy was least pronounced when using MEBoost. We illustrate the use of MEBoost in practice by analyzing data from the Box Lunch Study, a clinical trial in nutrition where several variables are based on self-report and hence measured with error.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02349v3
PDF	http://arxiv.org/pdf/1701.02349v3.pdf
PWC	https://paperswithcode.com/paper/meboost-variable-selection-in-the-presence-of
Repo
Framework

NAG: Network for Adversary Generation


Title	NAG: Network for Adversary Generation
Authors	Konda Reddy Mopuri, Utkarsh Ojha, Utsav Garg, R. Venkatesh Babu
Abstract	Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present optimization approaches that solve for a fooling objective with an imperceptibility constraint to craft the perturbations. However, for a given classifier, they generate one perturbation at a time, which is a single instance from the manifold of adversarial perturbations. Also, in order to build robust models, it is essential to explore the manifold of adversarial perturbations. In this paper, we propose for the first time, a generative approach to model the distribution of adversarial perturbations. The architecture of the proposed model is inspired from that of GANs and is trained using fooling and diversity objectives. Our trained generator network attempts to capture the distribution of adversarial perturbations for a given classifier and readily generates a wide variety of such perturbations. Our experimental evaluation demonstrates that perturbations crafted by our model (i) achieve state-of-the-art fooling rates, (ii) exhibit wide variety and (iii) deliver excellent cross model generalizability. Our work can be deemed as an important step in the process of inferring about the complex manifolds of adversarial perturbations.
Tasks
Published	2017-12-09
URL	http://arxiv.org/abs/1712.03390v2
PDF	http://arxiv.org/pdf/1712.03390v2.pdf
PWC	https://paperswithcode.com/paper/nag-network-for-adversary-generation
Repo
Framework

Multi-armed Bandit Problems with Strategic Arms


Title	Multi-armed Bandit Problems with Strategic Arms
Authors	Mark Braverman, Jieming Mao, Jon Schneider, S. Matthew Weinberg
Abstract	We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round. When pulled, the arm receives some private reward $v_a$ and can choose an amount $x_a$ to pass on to the principal (keeping $v_a-x_a$ for itself). All non-pulled arms get reward $0$. Each strategic arm tries to maximize its own utility over the course of $T$ rounds. Our goal is to design an algorithm for the principal incentivizing these arms to pass on as much of their private rewards as possible. When private rewards are stochastically drawn each round ($v_a^t \leftarrow D_a$), we show that: - Algorithms that perform well in the classic adversarial multi-armed bandit setting necessarily perform poorly: For all algorithms that guarantee low regret in an adversarial setting, there exist distributions $D_1,\ldots,D_k$ and an approximate Nash equilibrium for the arms where the principal receives reward $o(T)$. - Still, there exists an algorithm for the principal that induces a game among the arms where each arm has a dominant strategy. When each arm plays its dominant strategy, the principal sees expected reward $\mu’T - o(T)$, where $\mu'$ is the second-largest of the means $\mathbb{E}[D_{a}]$. This algorithm maintains its guarantee if the arms are non-strategic ($x_a = v_a$), and also if there is a mix of strategic and non-strategic arms.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1706.09060v1
PDF	http://arxiv.org/pdf/1706.09060v1.pdf
PWC	https://paperswithcode.com/paper/multi-armed-bandit-problems-with-strategic
Repo
Framework

Subspace Segmentation by Successive Approximations: A Method for Low-Rank and High-Rank Data with Missing Entries


Title	Subspace Segmentation by Successive Approximations: A Method for Low-Rank and High-Rank Data with Missing Entries
Authors	João Carvalho, Manuel Marques, João P. Costeira
Abstract	We propose a method to reconstruct and cluster incomplete high-dimensional data lying in a union of low-dimensional subspaces. Exploring the sparse representation model, we jointly estimate the missing data while imposing the intrinsic subspace structure. Since we have a non-convex problem, we propose an iterative method to reconstruct the data and provide a sparse similarity affinity matrix. This method is robust to initialization and achieves greater reconstruction accuracy than current methods, which dramatically improves clustering performance. Extensive experiments with synthetic and real data show that our approach leads to significant improvements in the reconstruction and segmentation, outperforming current state of the art for both low and high-rank data.
Tasks
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01467v1
PDF	http://arxiv.org/pdf/1709.01467v1.pdf
PWC	https://paperswithcode.com/paper/subspace-segmentation-by-successive
Repo
Framework

Identifying Nominals with No Head Match Co-references Using Deep Learning


Title	Identifying Nominals with No Head Match Co-references Using Deep Learning
Authors	M. Stone, R. Arora
Abstract	Identifying nominals with no head match is a long-standing challenge in coreference resolution with current systems performing significantly worse than humans. In this paper we present a new neural network architecture which outperforms the current state-of-the-art system on the English portion of the CoNLL 2012 Shared Task. This is done by using a logistic regression on features produced by two submodels, one of which is has the architecture proposed in [CM16a] while the other combines domain specific embeddings of the antecedent and the mention. We also propose some simple additional features which seem to improve performance for all models substantially, increasing F1 by almost 4% on basic logistic regression and other complex models.
Tasks	Coreference Resolution
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00936v1
PDF	http://arxiv.org/pdf/1710.00936v1.pdf
PWC	https://paperswithcode.com/paper/identifying-nominals-with-no-head-match-co
Repo
Framework

PatchShuffle Regularization


Title	PatchShuffle Regularization
Authors	Guoliang Kang, Xuanyi Dong, Liang Zheng, Yi Yang
Abstract	This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named `PatchShuffle` that can be adopted in any classification-oriented CNN models. It is easy to implement: in each mini-batch, images or feature maps are randomly chosen to undergo a transformation such that pixels within each local patch are shuffled. Through generating images and feature maps with interior orderless patches, PatchShuffle creates rich local variations, reduces the risk of network overfitting, and can be viewed as a beneficial supplement to various kinds of training regularization techniques, such as weight decay, model ensemble and dropout. Experiments on four representative classification datasets show that PatchShuffle improves the generalization ability of CNN especially when the data is scarce. Moreover, we empirically illustrate that CNN models trained with PatchShuffle are more robust to noise and local changes in an image.
Tasks
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07103v1
PDF	http://arxiv.org/pdf/1707.07103v1.pdf
PWC	https://paperswithcode.com/paper/patchshuffle-regularization
Repo
Framework

The Block Point Process Model for Continuous-Time Event-Based Dynamic Networks


Title	The Block Point Process Model for Continuous-Time Event-Based Dynamic Networks
Authors	Ruthwik R. Junuthula, Maysam Haghdan, Kevin S. Xu, Vijay K. Devabhaktuni
Abstract	We consider the problem of analyzing timestamped relational events between a set of entities, such as messages between users of an on-line social network. Such data are often analyzed using static or discrete-time network models, which discard a significant amount of information by aggregating events over time to form network snapshots. In this paper, we introduce a block point process model (BPPM) for continuous-time event-based dynamic networks. The BPPM is inspired by the well-known stochastic block model (SBM) for static networks. We show that networks generated by the BPPM follow an SBM in the limit of a growing number of nodes. We use this property to develop principled and efficient local search and variational inference procedures initialized by regularized spectral clustering. We fit BPPMs with exponential Hawkes processes to analyze several real network data sets, including a Facebook wall post network with over 3,500 nodes and 130,000 events.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10967v2
PDF	http://arxiv.org/pdf/1711.10967v2.pdf
PWC	https://paperswithcode.com/paper/the-block-point-process-model-for-continuous
Repo
Framework

A WL-SPPIM Semantic Model for Document Classification


Title	A WL-SPPIM Semantic Model for Document Classification
Authors	Ming Li, Peilun Xiao, Ju Zhang
Abstract	In this paper, we explore SPPIM-based text classification method, and the experiment reveals that the SPPIM method is equal to or even superior than SGNS method in text classification task on three international and standard text datasets, namely 20newsgroups, Reuters52 and WebKB. Comparing to SGNS, although SPPMI provides a better solution, it is not necessarily better than SGNS in text classification tasks. Based on our analysis, SGNS takes into the consideration of weight calculation during decomposition process, so it has better performance than SPPIM in some standard datasets. Inspired by this, we propose a WL-SPPIM semantic model based on SPPIM model, and experiment shows that WL-SPPIM approach has better classification and higher scalability in the text classification task compared with LDA, SGNS and SPPIM approaches.
Tasks	Document Classification, Text Classification
Published	2017-05-26
URL	http://arxiv.org/abs/1706.01758v1
PDF	http://arxiv.org/pdf/1706.01758v1.pdf
PWC	https://paperswithcode.com/paper/a-wl-sppim-semantic-model-for-document
Repo
Framework

Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects


Title	Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects
Authors	Alexander Broad, Brenna Argall
Abstract	We present a novel object detection pipeline for localization and recognition in three dimensional environments. Our approach makes use of an RGB-D sensor and combines state-of-the-art techniques from the robotics and computer vision communities to create a robust, real-time detection system. We focus specifically on solving the object detection problem for tabletop scenes, a common environment for assistive manipulators. Our detection pipeline locates objects in a point cloud representation of the scene. These clusters are subsequently used to compute a bounding box around each object in the RGB space. Each defined patch is then fed into a Convolutional Neural Network (CNN) for object recognition. We also demonstrate that our region proposal method can be used to develop novel datasets that are both large and diverse enough to train deep learning models, and easy enough to collect that end-users can develop their own datasets. Lastly, we validate the resulting system through an extensive analysis of the accuracy and run-time of the full pipeline.
Tasks	Object Detection, Object Recognition
Published	2017-03-14
URL	http://arxiv.org/abs/1703.04665v1
PDF	http://arxiv.org/pdf/1703.04665v1.pdf
PWC	https://paperswithcode.com/paper/geometry-based-region-proposals-for-real-time
Repo
Framework

Attention-based Natural Language Person Retrieval


Title	Attention-based Natural Language Person Retrieval
Authors	Tao Zhou, Muhao Chen, Jie Yu, Demetri Terzopoulos
Abstract	Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system based on an attention mechanism. More specifically, given the description of a person, the goal is to localize the person in an image. To this end, we first construct a benchmark dataset for natural language person retrieval. To do so, we generate bounding boxes for persons in a public image dataset from the segmentation masks, which are then annotated with descriptions and attributes using the Amazon Mechanical Turk. We then adopt a region proposal network in Faster R-CNN as a candidate region generator. The cropped images based on the region proposals as well as the whole images with attention weights are fed into Convolutional Neural Networks for visual feature extraction, while the natural language expression and attributes are input to Bidirectional Long Short- Term Memory (BLSTM) models for text feature extraction. The visual and text features are integrated to score region proposals, and the one with the highest score is retrieved as the output of our system. The experimental results show significant improvement over the state-of-the-art method for generic object retrieval and this line of research promises to benefit search in surveillance video footage.
Tasks	Image Classification, Person Retrieval
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08923v1
PDF	http://arxiv.org/pdf/1705.08923v1.pdf
PWC	https://paperswithcode.com/paper/attention-based-natural-language-person
Repo
Framework

Bayesian Learning of Consumer Preferences for Residential Demand Response


Title	Bayesian Learning of Consumer Preferences for Residential Demand Response
Authors	Mikhail V. Goubko, Sergey O. Kuznetsov, Alexey A. Neznanov, Dmitry I. Ignatov
Abstract	In coming years residential consumers will face real-time electricity tariffs with energy prices varying day to day, and effective energy saving will require automation - a recommender system, which learns consumer’s preferences from her actions. A consumer chooses a scenario of home appliance use to balance her comfort level and the energy bill. We propose a Bayesian learning algorithm to estimate the comfort level function from the history of appliance use. In numeric experiments with datasets generated from a simulation model of a consumer interacting with small home appliances the algorithm outperforms popular regression analysis tools. Our approach can be extended to control an air heating and conditioning system, which is responsible for up to half of a household’s energy bill.
Tasks	Recommendation Systems
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08757v1
PDF	http://arxiv.org/pdf/1701.08757v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-learning-of-consumer-preferences-for
Repo
Framework

Discovery of potential collaboration networks from open knowledge sources


Title	Discovery of potential collaboration networks from open knowledge sources
Authors	Nelson Piedra, Janneth Chicaiza, Jorge Lopez-Vargas, Edmundo Tovar
Abstract	Scientific publishing conveys the outputs of an academic or research activity, in this sense; it also reflects the efforts and issues in which people engage. To identify potential collaborative networks one of the simplest approaches is to leverage the co-authorship relations. In this approach, semantic and hierarchic relationships defined by a Knowledge Organization System are used in order to improve the system’s ability to recommend potential networks beyond the lexical or syntactic analysis of the topics or concepts that are of interest to academics.
Tasks
Published	2017-11-08
URL	http://arxiv.org/abs/1711.03537v1
PDF	http://arxiv.org/pdf/1711.03537v1.pdf
PWC	https://paperswithcode.com/paper/discovery-of-potential-collaboration-networks
Repo
Framework

Joint DOA Estimation and Array Calibration Using Multiple Parametric Dictionary Learning


Title	Joint DOA Estimation and Array Calibration Using Multiple Parametric Dictionary Learning
Authors	H. Ghanbari, H. Zayyani, E. Yazdian
Abstract	This letter proposes a multiple parametric dictionary learning algorithm for direction of arrival (DOA) estimation in presence of array gain-phase error and mutual coupling. It jointly solves both the DOA estimation and array imperfection problems to yield a robust DOA estimation in presence of array imperfection errors and off-grid. In the proposed method, a multiple parametric dictionary learning-based algorithm with an steepest-descent iteration is used for learning the parametric perturbation matrices and the steering matrix simultaneously. It also exploits the multiple snapshots information to enhance the performance of DOA estimation. Simulation results show the efficiency of the proposed algorithm when both off-grid problem and array imperfection exist.
Tasks	Calibration, Dictionary Learning
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07299v1
PDF	http://arxiv.org/pdf/1707.07299v1.pdf
PWC	https://paperswithcode.com/paper/joint-doa-estimation-and-array-calibration
Repo
Framework