January 27, 2020

3136 words 15 mins read

Paper Group ANR 1071

Vocal Interactivity in Crowds, Flocks and Swarms: Implications for Voice User Interfaces. SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches. Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata. Change Detection in Noisy Dynamic Networks: A Spectral Embedding Approach. Revisiting Adversarial A …

Vocal Interactivity in Crowds, Flocks and Swarms: Implications for Voice User Interfaces


Title	Vocal Interactivity in Crowds, Flocks and Swarms: Implications for Voice User Interfaces
Authors	Roger K. Moore
Abstract	Recent years have seen an explosion in the availability of Voice User Interfaces. However, user surveys suggest that there are issues with respect to usability, and it has been hypothesised that contemporary voice-enabled systems are missing crucial behaviours relating to user engagement and vocal interactivity. However, it is well established that such ostensive behaviours are ubiquitous in the animal kingdom, and that vocalisation provides a means through which interaction may be coordinated and managed between individuals and within groups. Hence, this paper reports results from a study aimed at identifying generic mechanisms that might underpin coordinated collective vocal behaviour with a particular focus on closed-loop negative-feedback control as a powerful regulatory process. A computer-based real-time simulation of vocal interactivity is described which has provided a number of insights, including the enumeration of a number of key control variables that may be worthy of further investigation.
Tasks
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11656v1
PDF	https://arxiv.org/pdf/1907.11656v1.pdf
PWC	https://paperswithcode.com/paper/vocal-interactivity-in-crowds-flocks-and
Repo
Framework

SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches


Title	SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches
Authors	Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis
Abstract	Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07169v1
PDF	http://arxiv.org/pdf/1903.07169v1.pdf
PWC	https://paperswithcode.com/paper/superpatchmatch-an-algorithm-for-robust
Repo
Framework

Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata


Title	Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata
Authors	Charlotte Rudnik, Thibault Ehrhart, Olivier Ferret, Denis Teyssou, Raphaël Troncy, Xavier Tannier
Abstract	News agencies produce thousands of multimedia stories describing events happening in the world that are either scheduled such as sports competitions, political summits and elections, or breaking events such as military conflicts, terrorist attacks, natural disasters, etc. When writing up those stories, journalists refer to contextual background and to compare with past similar events. However, searching for precise facts described in stories is hard. In this paper, we propose a general method that leverages the Wikidata knowledge base to produce semantic annotations of news articles. Next, we describe a semantic search engine that supports both keyword based search in news articles and structured data search providing filters for properties belonging to specific event schemas that are automatically inferred.
Tasks
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05557v1
PDF	http://arxiv.org/pdf/1904.05557v1.pdf
PWC	https://paperswithcode.com/paper/searching-news-articles-using-an-event
Repo
Framework

Change Detection in Noisy Dynamic Networks: A Spectral Embedding Approach


Title	Change Detection in Noisy Dynamic Networks: A Spectral Embedding Approach
Authors	Isuru Udayangani Hewapathirana, Dominic Lee, Elena Moltchanova, Jeanette McLeod
Abstract	Change detection in dynamic networks is an important problem in many areas, such as fraud detection, cyber intrusion detection and health care monitoring. It is a challenging problem because it involves a time sequence of graphs, each of which is usually very large and sparse with heterogeneous vertex degrees, resulting in a complex, high dimensional mathematical object. Spectral embedding methods provide an effective way to transform a graph to a lower dimensional latent Euclidean space that preserves the underlying structure of the network. Although change detection methods that use spectral embedding are available, they do not address sparsity and degree heterogeneity that usually occur in noisy real-world graphs and a majority of these methods focus on changes in the behaviour of the overall network. In this paper, we adapt previously developed techniques in spectral graph theory and propose a novel concept of applying Procrustes techniques to embedded points for vertices in a graph to detect changes in entity behaviour. Our spectral embedding approach not only addresses sparsity and degree heterogeneity issues, but also obtains an estimate of the appropriate embedding dimension. We call this method CDP (change detection using Procrustes analysis). We demonstrate the performance of CDP through extensive simulation experiments and a real-world application. CDP successfully detects various types of vertex-based changes including (i) changes in vertex degree, (ii) changes in community membership of vertices, and (iii) unusual increase or decrease in edge weight between vertices. The change detection performance of CDP is compared with two other baseline methods that employ alternative spectral embedding approaches. In both cases, CDP generally shows superior performance.
Tasks	Fraud Detection, Intrusion Detection
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02301v1
PDF	https://arxiv.org/pdf/1910.02301v1.pdf
PWC	https://paperswithcode.com/paper/change-detection-in-noisy-dynamic-networks-a
Repo
Framework

Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training


Title	Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training
Authors	Tasnim Mohiuddin, Shafiq Joty
Abstract	Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoencoder for unsupervised word translation and propose two novel extensions to it that yield more stable training and improved results. Our method includes regularization terms to enforce cycle consistency and input reconstruction, and puts the target encoders as an adversary against the corresponding discriminator. Extensive experimentations with European, non-European and low-resource languages show that our method is more robust and achieves better performance than recently proposed adversarial and non-adversarial approaches.
Tasks
Published	2019-04-04
URL	http://arxiv.org/abs/1904.04116v1
PDF	http://arxiv.org/pdf/1904.04116v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-adversarial-autoencoder-for
Repo
Framework

Towards automated feature engineering for credit card fraud detection using multi-perspective HMMs


Title	Towards automated feature engineering for credit card fraud detection using multi-perspective HMMs
Authors	Yvan Lucas, Pierre-Edouard Portier, Léa Laporte, Liyun He-Guelton, Olivier Caelen, Michael Granitzer, Sylvie Calabretto
Abstract	Machine learning and data mining techniques have been used extensively in order to detect credit card frauds. However, most studies consider credit card transactions as isolated events and not as a sequence of transactions. In this framework, we model a sequence of credit card transactions from three different perspectives, namely (i) The sequence contains or doesn’t contain a fraud (ii) The sequence is obtained by fixing the card-holder or the payment terminal (iii) It is a sequence of spent amount or of elapsed time between the current and previous transactions. Combinations of the three binary perspectives give eight sets of sequences from the (training) set of transactions. Each one of these sequences is modelled with a Hidden Markov Model (HMM). Each HMM associates a likelihood to a transaction given its sequence of previous transactions. These likelihoods are used as additional features in a Random Forest classifier for fraud detection. Our multiple perspectives HMM-based approach offers automated feature engineering to model temporal correlations so as to improve the effectiveness of the classification task and allows for an increase in the detection of fraudulent transactions when combined with the state of the art expert based feature engineering strategy for credit card fraud detection. In extension to previous works, we show that this approach goes beyond ecommerce transactions and provides a robust feature engineering over different datasets, hyperparameters and classifiers. Moreover, we compare strategies to deal with structural missing values.
Tasks	Automated Feature Engineering, Feature Engineering, Fraud Detection
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01185v1
PDF	https://arxiv.org/pdf/1909.01185v1.pdf
PWC	https://paperswithcode.com/paper/towards-automated-feature-engineering-for
Repo
Framework

Watermark retrieval from 3D printed objects via synthetic data training


Title	Watermark retrieval from 3D printed objects via synthetic data training
Authors	Xin Zhang, Ning Jia, Ioannis Ivrissimtzis
Abstract	We present a deep neural network based method for the retrieval of watermarks from images of 3D printed objects. To deal with the variability of all possible 3D printing and image acquisition settings we train the network with synthetic data. The main simulator parameters such as texture, illumination and camera position are dynamically randomized in non-realistic ways, forcing the neural network to learn the intrinsic features of the 3D printed watermarks. At the end of the pipeline, the watermark, in the form of a two-dimensional bit array, is retrieved through a series of simple image processing and statistical operations applied on the confidence map generated by the neural network. The results demonstrate that the inclusion of synthetic DR data in the training set increases the generalization power of the network, which performs better on images from previously unseen 3D printed objects. We conclude that in our application domain of information retrieval from 3D printed objects, where access to the exact CAD files of the printed objects can be assumed, one can use inexpensive synthetic data to enhance neural network training, reducing the need for the labour intensive process of creating large amounts of hand labelled real data or the need to generate photorealistic synthetic data.
Tasks	Information Retrieval
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09706v1
PDF	https://arxiv.org/pdf/1905.09706v1.pdf
PWC	https://paperswithcode.com/paper/watermark-retrieval-from-3d-printed-objects-1
Repo
Framework

An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data


Title	An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
Authors	Rémi Viola, Rémi Emonet, Amaury Habrard, Guillaume Metzler, Sébastien Riou, Marc Sebban
Abstract	In this paper, we address the challenging problem of learning from imbalanced data using a Nearest-Neighbor (NN) algorithm. In this setting, the minority examples typically belong to the class of interest requiring the optimization of specific criteria, like the F-Measure. Based on simple geometrical ideas, we introduce an algorithm that reweights the distance between a query sample and any positive training example. This leads to a modification of the Voronoi regions and thus of the decision boundaries of the NN algorithm. We provide a theoretical justification about the weighting scheme needed to reduce the False Negative rate while controlling the number of False Positives. We perform an extensive experimental study on many public imbalanced datasets, but also on large scale non public data from the French Ministry of Economy and Finance on a tax fraud detection task, showing that our method is very effective and, interestingly, yields the best performance when combined with state of the art sampling methods.
Tasks	Fraud Detection
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00693v2
PDF	https://arxiv.org/pdf/1909.00693v2.pdf
PWC	https://paperswithcode.com/paper/an-adjusted-nearest-neighbor-algorithm
Repo
Framework

CAMR: Coded Aggregated MapReduce


Title	CAMR: Coded Aggregated MapReduce
Authors	Konstantinos Konstantinidis, Aditya Ramamoorthy
Abstract	Many big data algorithms executed on MapReduce-like systems have a shuffle phase that often dominates the overall job execution time. Recent work has demonstrated schemes where the communication load in the shuffle phase can be traded off for the computation load in the map phase. In this work, we focus on a class of distributed algorithms, broadly used in deep learning, where intermediate computations of the same task can be combined. Even though prior techniques reduce the communication load significantly, they require a number of jobs that grows exponentially in the system parameters. This limitation is crucial and may diminish the load gains as the algorithm scales. We propose a new scheme which achieves the same load as the state-of-the-art while ensuring that the number of jobs as well as the number of subfiles that the data set needs to be split into remain small.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07418v2
PDF	http://arxiv.org/pdf/1901.07418v2.pdf
PWC	https://paperswithcode.com/paper/camr-coded-aggregated-mapreduce
Repo
Framework

Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues


Title	Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues
Authors	Shanu Kumar, Shubham Atreja, Anjali Singh, Mohit Jain
Abstract	Citizen engagement and technology usage are two emerging trends driven by smart city initiatives. Governments around the world are adopting technology for faster resolution of civic issues. Typically, citizens report issues, such as broken roads, garbage dumps, etc. through web portals and mobile apps, in order for the government authorities to take appropriate actions. Several mediums – text, image, audio, video – are used to report these issues. Through a user study with 13 citizens and 3 authorities, we found that image is the most preferred medium to report civic issues. However, analyzing civic issue related images is challenging for the authorities as it requires manual effort. Moreover, previous works have been limited to identifying a specific set of issues from images. In this work, given an image, we propose to generate a Civic Issue Graph consisting of a set of objects and the semantic relations between them, which are representative of the underlying civic issue. We also release two multi-modal (text and images) datasets, that can help in further analysis of civic issues from images. We present a novel approach for adversarial training of existing scene graph models that enables the use of scene graphs for new applications in the absence of any labelled training data. We conduct several experiments to analyze the efficacy of our approach, and using human evaluation, we establish the appropriateness of our model at representing different civic issues.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10124v1
PDF	http://arxiv.org/pdf/1901.10124v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-adaptation-of-scene-graph-models
Repo
Framework

Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video


Title	Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video
Authors	Alisha Sharma, Jonathan Ventura
Abstract	We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We also introduce Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting.
Tasks	Depth Estimation, Motion Estimation
Published	2019-01-04
URL	https://arxiv.org/abs/1901.00979v2
PDF	https://arxiv.org/pdf/1901.00979v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-of-depth-and-ego-motion
Repo
Framework

Robust One-Class Kernel Spectral Regression


Title	Robust One-Class Kernel Spectral Regression
Authors	Shervin Rahimzadeh Arashloo, Josef Kittler
Abstract	The kernel null-space technique and its regression-based formulation (called one-class kernel spectral regression, a.k.a. OC-KSR) is known to be an effective and computationally attractive one-class classification framework. Despite its outstanding performance, the applicability of kernel null-space method is limited due to its susceptibility to possible training data corruptions and inability to rank training observations according to their conformity with the model. This work addresses these shortcomings by studying the effect of regularising the solution of the null-space kernel Fisher methodology in the context of its regression-based formulation (OC-KSR). In this respect, first, the effect of a Tikhonov regularisation in the Hilbert space is analysed where the one-class learning problem in presence of contaminations in the training set is posed as a sensitivity analysis problem. Next, driven by the success of the sparse representation methodology, the effect of a sparsity regularisation on the solution is studied. For both alternative regularisation schemes, iterative algorithms are proposed which recursively update label confidences and rank training observations based on their fit with the model. Through extensive experiments conducted on different data sets, the proposed methodology is found to enhance robustness against contamination in the training set as compared with the baseline kernel null-space technique as well as other existing approaches in a one-class classification paradigm while providing the functionality to rank training samples effectively.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02208v1
PDF	http://arxiv.org/pdf/1902.02208v1.pdf
PWC	https://paperswithcode.com/paper/robust-one-class-kernel-spectral-regression
Repo
Framework

Generalizing Graph Convolutional Neural Networks with Edge-Variant Recursions on Graphs


Title	Generalizing Graph Convolutional Neural Networks with Edge-Variant Recursions on Graphs
Authors	Elvin Isufi, Fernando Gama, Alejandro Ribeiro
Abstract	This paper reviews graph convolutional neural networks (GCNNs) through the lens of edge-variant graph filters. The edge-variant graph filter is a finite order, linear, and local recursion that allows each node, in each iteration, to weigh differently the information of its neighbors. By exploiting this recursion, we formulate a general framework for GCNNs which considers state-of-the-art solutions as particular cases. This framework results useful to i) understand the tradeoff between local detail and the number of parameters of each solution and ii) provide guidelines for developing a myriad of novel approaches that can be implemented locally in the vertex domain. One of such approaches is presented here showing superior performance w.r.t. current alternatives in graph signal classification problems.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01298v1
PDF	http://arxiv.org/pdf/1903.01298v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-graph-convolutional-neural
Repo
Framework

Multi-Person tracking by multi-scale detection in Basketball scenarios


Title	Multi-Person tracking by multi-scale detection in Basketball scenarios
Authors	Adrià Arbués-Sangüesa, Gloria Haro, Coloma Ballester
Abstract	Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results both in terms of detection (F1-score) and tracking (MOTA). The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.
Tasks
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04637v1
PDF	https://arxiv.org/pdf/1907.04637v1.pdf
PWC	https://paperswithcode.com/paper/multi-person-tracking-by-multi-scale
Repo
Framework

On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes


Title	On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes
Authors	Pravesh K. Kothari, Roi Livni
Abstract	We study the expressive power of kernel methods and the algorithmic feasibility of multiple kernel learning for a special rich class of kernels. Specifically, we define \emph{Euclidean kernels}, a diverse class that includes most, if not all, families of kernels studied in literature such as polynomial kernels and radial basis functions. We then describe the geometric and spectral structure of this family of kernels over the hypercube (and to some extent for any compact domain). Our structural results allow us to prove meaningful limitations on the expressive power of the class as well as derive several efficient algorithms for learning kernels over different domains.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04782v1
PDF	http://arxiv.org/pdf/1902.04782v1.pdf
PWC	https://paperswithcode.com/paper/on-the-expressive-power-of-kernel-methods-and
Repo
Framework