May 5, 2019

3334 words 16 mins read

Paper Group ANR 546

Face-space Action Recognition by Face-Object Interactions. Generating Synthetic Data for Text Recognition. Reducing training requirements through evolutionary based dimension reduction and subject transfer. Intelligent Biohybrid Neurotechnologies: Are They Really What They Claim?. Localization for Wireless Sensor Networks: A Neural Network Approach …

Face-space Action Recognition by Face-Object Interactions


Title	Face-space Action Recognition by Face-Object Interactions
Authors	Amir Rosenfeld, Shimon Ullman
Abstract	Action recognition in still images has seen major improvement in recent years due to advances in human pose estimation, object recognition and stronger feature representations. However, there are still many cases in which performance remains far from that of humans. In this paper, we approach the problem by learning explicitly, and then integrating three components of transitive actions: (1) the human body part relevant to the action (2) the object being acted upon and (3) the specific form of interaction between the person and the object. The process uses class-specific features and relations not used in the past for action recognition and which use inherently two cycles in the process unlike most standard approaches. We focus on face-related actions (FRA), a subset of actions that includes several currently challenging categories. We present an average relative improvement of 52% over state-of-the art. We also make a new benchmark publicly available.
Tasks	Action Recognition In Still Images, Object Recognition, Pose Estimation, Temporal Action Localization
Published	2016-01-17
URL	http://arxiv.org/abs/1601.04293v1
PDF	http://arxiv.org/pdf/1601.04293v1.pdf
PWC	https://paperswithcode.com/paper/face-space-action-recognition-by-face-object
Repo
Framework

Generating Synthetic Data for Text Recognition


Title	Generating Synthetic Data for Text Recognition
Authors	Praveen Krishnan, C. V. Jawahar
Abstract	Generating synthetic images is an art which emulates the natural process of image generation in a closest possible manner. In this work, we exploit such a framework for data generation in handwritten domain. We render synthetic data using open source fonts and incorporate data augmentation schemes. As part of this work, we release 9M synthetic handwritten word image corpus which could be useful for training deep network architectures and advancing the performance in handwritten word spotting and recognition tasks.
Tasks	Data Augmentation, Image Generation
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04224v1
PDF	http://arxiv.org/pdf/1608.04224v1.pdf
PWC	https://paperswithcode.com/paper/generating-synthetic-data-for-text
Repo
Framework

Reducing training requirements through evolutionary based dimension reduction and subject transfer


Title	Reducing training requirements through evolutionary based dimension reduction and subject transfer
Authors	Adham Atyabi, Martin Luerssena, Sean P. Fitzgibbon, Trent Lewis, David M. W. Powersa
Abstract	Training Brain Computer Interface (BCI) systems to understand the intention of a subject through Electroencephalogram (EEG) data currently requires multiple training sessions with a subject in order to develop the necessary expertise to distinguish signals for different tasks. Conventionally the task of training the subject is done by introducing a training and calibration stage during which some feedback is presented to the subject. This training session can take several hours which is not appropriate for on-line EEG-based BCI systems. An alternative approach is to use previous recording sessions of the same person or some other subjects that performed the same tasks (subject transfer) for training the classifiers. The main aim of this study is to generate a methodology that allows the use of data from other subjects while reducing the dimensions of the data. The study investigates several possibilities for reducing the necessary training and calibration period in subjects and the classifiers and addresses the impact of i) evolutionary subject transfer and ii) adapting previously trained methods (retraining) using other subjects data. Our results suggest reduction to 40% of target subject data is sufficient for training the classifier. Our results also indicate the superiority of the approaches that incorporated evolutionary subject transfer and highlights the feasibility of adapting a system trained on other subjects.
Tasks	Calibration, Dimensionality Reduction, EEG
Published	2016-02-06
URL	http://arxiv.org/abs/1602.02237v1
PDF	http://arxiv.org/pdf/1602.02237v1.pdf
PWC	https://paperswithcode.com/paper/reducing-training-requirements-through
Repo
Framework

Intelligent Biohybrid Neurotechnologies: Are They Really What They Claim?


Title	Intelligent Biohybrid Neurotechnologies: Are They Really What They Claim?
Authors	Gabriella Panuccio, Marianna Semprini, Lorenzo Natale, Michela Chiappalone
Abstract	In the era of intelligent biohybrid neurotechnologies for brain repair, new fanciful terms are appearing in the scientific dictionary to define what has so far been unimaginable. As the emerging neurotechnologies are becoming increasingly polyhedral and sophisticated, should we talk about evolution and rank the intelligence of these devices?
Tasks
Published	2016-07-18
URL	http://arxiv.org/abs/1607.05023v1
PDF	http://arxiv.org/pdf/1607.05023v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-biohybrid-neurotechnologies-are
Repo
Framework

Localization for Wireless Sensor Networks: A Neural Network Approach


Title	Localization for Wireless Sensor Networks: A Neural Network Approach
Authors	Shiu Kumar, Ronesh Sharma, Edwin Vans
Abstract	As Wireless Sensor Networks are penetrating into the industrial domain, many research opportunities are emerging. One such essential and challenging application is that of node localization. A feed-forward neural network based methodology is adopted in this paper. The Received Signal Strength Indicator (RSSI) values of the anchor node beacons are used. The number of anchor nodes and their configurations has an impact on the accuracy of the localization system, which is also addressed in this paper. Five different training algorithms are evaluated to find the training algorithm that gives the best result. The multi-layer Perceptron (MLP) neural network model was trained using Matlab. In order to evaluate the performance of the proposed method in real time, the model obtained was then implemented on the Arduino microcontroller. With four anchor nodes, an average 2D localization error of 0.2953 m has been achieved with a 12-12-2 neural network structure. The proposed method can also be implemented on any other embedded microcontroller system.
Tasks
Published	2016-02-07
URL	http://arxiv.org/abs/1610.04494v1
PDF	http://arxiv.org/pdf/1610.04494v1.pdf
PWC	https://paperswithcode.com/paper/localization-for-wireless-sensor-networks-a
Repo
Framework

Algebraic foundations for qualitative calculi and networks


Title	Algebraic foundations for qualitative calculi and networks
Authors	Robin Hirsch, Marcel Jackson, Tomasz Kowalski
Abstract	A qualitative representation $\phi$ is like an ordinary representation of a relation algebra, but instead of requiring $(a; b)^\phi = a^\phi b^\phi$, as we do for ordinary representations, we only require that $c^\phi\supseteq a^\phi b^\phi \iff c\geq a ; b$, for each $c$ in the algebra. A constraint network is qualitatively satisfiable if its nodes can be mapped to elements of a qualitative representation, preserving the constraints. If a constraint network is satisfiable then it is clearly qualitatively satisfiable, but the converse can fail. However, for a wide range of relation algebras including the point algebra, the Allen Interval Algebra, RCC8 and many others, a network is satisfiable if and only if it is qualitatively satisfiable. Unlike ordinary composition, the weak composition arising from qualitative representations need not be associative, so we can generalise by considering network satisfaction problems over non-associative algebras. We prove that computationally, qualitative representations have many advantages over ordinary representations: whereas many finite relation algebras have only infinite representations, every finite qualitatively representable algebra has a finite qualitative representation; the representability problem for (the atom structures of) finite non-associative algebras is NP-complete; the network satisfaction problem over a finite qualitatively representable algebra is always in NP; the validity of equations over qualitative representations is co-NP-complete. On the other hand we prove that there is no finite axiomatisation of the class of qualitatively representable algebras.
Tasks
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09140v3
PDF	http://arxiv.org/pdf/1606.09140v3.pdf
PWC	https://paperswithcode.com/paper/algebraic-foundations-for-qualitative-calculi
Repo
Framework

Evolving the Structure of Evolution Strategies


Title	Evolving the Structure of Evolution Strategies
Authors	Sander van Rijn, Hao Wang, Matthijs van Leeuwen, Thomas Bäck
Abstract	Various variants of the well known Covariance Matrix Adaptation Evolution Strategy (CMA-ES) have been proposed recently, which improve the empirical performance of the original algorithm by structural modifications. However, in practice it is often unclear which variation is best suited to the specific optimization problem at hand. As one approach to tackle this issue, algorithmic mechanisms attached to CMA-ES variants are considered and extracted as functional \emph{modules}, allowing for combinations of them. This leads to a configuration space over ES structures, which enables the exploration of algorithm structures and paves the way toward novel algorithm generation. Specifically, eleven modules are incorporated in this framework with two or three alternative configurations for each module, resulting in $4,608$ algorithms. A self-adaptive Genetic Algorithm (GA) is used to efficiently evolve effective ES-structures for given classes of optimization problems, outperforming any classical CMA-ES variants from literature. The proposed approach is evaluated on noiseless functions from BBOB suite. Furthermore, such an observation is again confirmed on different function groups and dimensionality, indicating the feasibility of ES configuration on real-world problem classes.
Tasks
Published	2016-10-17
URL	http://arxiv.org/abs/1610.05231v1
PDF	http://arxiv.org/pdf/1610.05231v1.pdf
PWC	https://paperswithcode.com/paper/evolving-the-structure-of-evolution
Repo
Framework

Word Embeddings to Enhance Twitter Gang Member Profile Identification


Title	Word Embeddings to Enhance Twitter Gang Member Profile Identification
Authors	Sanjaya Wijeratne, Lakshika Balasuriya, Derek Doran, Amit Sheth
Abstract	Gang affiliates have joined the masses who use social media to share thoughts and actions publicly. Interestingly, they use this public medium to express recent illegal actions, to intimidate others, and to share outrageous images and statements. Agencies able to unearth these profiles may thus be able to anticipate, stop, or hasten the investigation of gang-related crimes. This paper investigates the use of word embeddings to help identify gang members on Twitter. Building on our previous work, we generate word embeddings that translate what Twitter users post in their profile descriptions, tweets, profile images, and linked YouTube content to a real vector format amenable for machine learning classification. Our experimental results show that pre-trained word embeddings can boost the accuracy of supervised learning algorithms trained over gang members social media posts.
Tasks	Word Embeddings
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08597v1
PDF	http://arxiv.org/pdf/1610.08597v1.pdf
PWC	https://paperswithcode.com/paper/word-embeddings-to-enhance-twitter-gang
Repo
Framework

Nazr-CNN: Fine-Grained Classification of UAV Imagery for Damage Assessment


Title	Nazr-CNN: Fine-Grained Classification of UAV Imagery for Damage Assessment
Authors	N. Attari, F. Ofli, M. Awad, J. Lucas, S. Chawla
Abstract	We propose Nazr-CNN1, a deep learning pipeline for object detection and fine-grained classification in images acquired from Unmanned Aerial Vehicles (UAVs) for damage assessment and monitoring. Nazr-CNN consists of two components. The function of the first component is to localize objects (e.g. houses or infrastructure) in an image by carrying out a pixel-level classification. In the second component, a hidden layer of a Convolutional Neural Network (CNN) is used to encode Fisher Vectors (FV) of the segments generated from the first component in order to help discriminate between different levels of damage. To showcase our approach we use data from UAVs that were deployed to assess the level of damage in the aftermath of a devastating cyclone that hit the island of Vanuatu in 2015. The collected images were labeled by a crowdsourcing effort and the labeling categories consisted of fine-grained levels of damage to built structures. Since our data set is relatively small, a pre- trained network for pixel-level classification and FV encoding was used. Nazr-CNN attains promising results both for object detection and damage assessment suggesting that the integrated pipeline is robust in the face of small data sets and labeling errors by annotators. While the focus of Nazr-CNN is on assessment of UAV images in a post-disaster scenario, our solution is general and can be applied in many diverse settings. We show one such case of transfer learning to assess the level of damage in aerial images collected after a typhoon in Philippines.
Tasks	Object Detection, Transfer Learning
Published	2016-11-20
URL	http://arxiv.org/abs/1611.06474v2
PDF	http://arxiv.org/pdf/1611.06474v2.pdf
PWC	https://paperswithcode.com/paper/nazr-cnn-fine-grained-classification-of-uav
Repo
Framework

Deep Multi-scale Location-aware 3D Convolutional Neural Networks for Automated Detection of Lacunes of Presumed Vascular Origin


Title	Deep Multi-scale Location-aware 3D Convolutional Neural Networks for Automated Detection of Lacunes of Presumed Vascular Origin
Authors	Mohsen Ghafoorian, Nico Karssemeijer, Tom Heskes, Mayra Bergkamp, Joost Wissink, Jiri Obels, Karlijn Keizer, Frank-Erik de Leeuw, Bram van Ginneken, Elena Marchiori, Bram Platel
Abstract	Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines. In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.
Tasks
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07442v2
PDF	http://arxiv.org/pdf/1610.07442v2.pdf
PWC	https://paperswithcode.com/paper/deep-multi-scale-location-aware-3d
Repo
Framework

Texture Synthesis Using Shallow Convolutional Networks with Random Filters


Title	Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Authors	Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge
Abstract	Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images. Our finding suggests that such optimized multi-layer feature spaces are not imperative for texture modeling. Instead, much simpler shallow and convolutional networks can serve as the basis for novel texture synthesis algorithms.
Tasks	Texture Synthesis
Published	2016-05-31
URL	http://arxiv.org/abs/1606.00021v1
PDF	http://arxiv.org/pdf/1606.00021v1.pdf
PWC	https://paperswithcode.com/paper/texture-synthesis-using-shallow-convolutional
Repo
Framework

CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews


Title	CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews
Authors	Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
Abstract	Product reviews contain a lot of useful information about product features and customer opinions. One important product feature is the complementary entity (products) that may potentially work together with the reviewed product. Knowing complementary entities of the reviewed product is very important because customers want to buy compatible products and avoid incompatible ones. In this paper, we address the problem of Complementary Entity Recognition (CER). Since no existing method can solve this problem, we first propose a novel unsupervised method to utilize syntactic dependency paths to recognize complementary entities. Then we expand category-level domain knowledge about complementary entities using only a few general seed verbs on a large amount of unlabeled reviews. The domain knowledge helps the unsupervised method to adapt to different products and greatly improves the precision of the CER task. The advantage of the proposed method is that it does not require any labeled data for training. We conducted experiments on 7 popular products with about 1200 reviews in total to demonstrate that the proposed approach is effective.
Tasks
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01039v1
PDF	http://arxiv.org/pdf/1612.01039v1.pdf
PWC	https://paperswithcode.com/paper/cer-complementary-entity-recognition-via
Repo
Framework

Fractal Descriptors of Texture Images Based on the Triangular Prism Dimension


Title	Fractal Descriptors of Texture Images Based on the Triangular Prism Dimension
Authors	João B. Florindo, Odemir M. Bruno
Abstract	This work presents a novel descriptor for texture images based on fractal geometry and its application to image analysis. The descriptors are provided by estimating the triangular prism fractal dimension under different scales with a weight exponential parameter, followed by dimensionality reduction using Karhunen-Lo`{e}ve transform. The efficiency of the proposed descriptors is tested on two well-known texture data sets, that is, Brodatz and Vistex, both for classification and image retrieval. The novel method is also tested concerning invariances in situations when the textures are rotated or affected by Gaussian noise. The obtained results outperform other classical and state-of-the-art descriptors in the literature and demonstrate the power of the triangular descriptors in these tasks, suggesting their use in practical applications of image analysis based on texture features.
Tasks	Dimensionality Reduction, Image Retrieval
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06435v1
PDF	http://arxiv.org/pdf/1612.06435v1.pdf
PWC	https://paperswithcode.com/paper/fractal-descriptors-of-texture-images-based
Repo
Framework

Determination of the edge of criticality in echo state networks through Fisher information maximization


Title	Determination of the edge of criticality in echo state networks through Fisher information maximization
Authors	Lorenzo Livi, Filippo Maria Bianchi, Cesare Alippi
Abstract	It is a widely accepted fact that the computational capability of recurrent neural networks is maximized on the so-called “edge of criticality”. Once the network operates in this configuration, it performs efficiently on a specific application both in terms of (i) low prediction error and (ii) high short-term memory capacity. Since the behavior of recurrent networks is strongly influenced by the particular input signal driving the dynamics, a universal, application-independent method for determining the edge of criticality is still missing. In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in recurrent neural networks. It is proven that Fisher information is maximized for (finite-size) systems operating in such critical regions. However, Fisher information is notoriously difficult to compute and either requires the probability density function or the conditional dependence of the system states with respect to the model parameters. The paper takes advantage of a recently-developed non-parametric estimator of the Fisher information matrix and provides a method to determine the critical region of echo state networks, a particular class of recurrent networks. The considered control parameters, which indirectly affect the echo state network performance, are explored to identify those configurations lying on the edge of criticality and, as such, maximizing Fisher information and computational performance. Experimental results on benchmarks and real-world data demonstrate the effectiveness of the proposed method.
Tasks
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03685v2
PDF	http://arxiv.org/pdf/1603.03685v2.pdf
PWC	https://paperswithcode.com/paper/determination-of-the-edge-of-criticality-in
Repo
Framework

Causality on Longitudinal Data: Stable Specification Search in Constrained Structural Equation Modeling


Title	Causality on Longitudinal Data: Stable Specification Search in Constrained Structural Equation Modeling
Authors	Ridho Rahmadi, Perry Groot, Marieke HC van Rijn, Jan AJG van den Brand, Marianne Heins, Hans Knoop, Tom Heskes
Abstract	A typical problem in causal modeling is the instability of model structure learning, i.e., small changes in finite data can result in completely different optimal models. The present work introduces a novel causal modeling algorithm for longitudinal data, that is robust for finite samples based on recent advances in stability selection using subsampling and selection algorithms. Our approach uses exploratory search but allows incorporation of prior knowledge, e.g., the absence of a particular causal relationship between two specific variables. We represent causal relationships using structural equation models. Models are scored along two objectives: the model fit and the model complexity. Since both objectives are often conflicting we apply a multi-objective evolutionary algorithm to search for Pareto optimal models. To handle the instability of small finite data samples, we repeatedly subsample the data and select those substructures (from the optimal models) that are both stable and parsimonious. These substructures can be visualized through a causal graph. Our more exploratory approach achieves at least comparable performance as, but often a significant improvement over state-of-the-art alternative approaches on a simulated data set with a known ground truth. We also present the results of our method on three real-world longitudinal data sets on chronic fatigue syndrome, Alzheimer disease, and chronic kidney disease. The findings obtained with our approach are generally in line with results from more hypothesis-driven analyses in earlier studies and suggest some novel relationships that deserve further research.
Tasks
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06838v3
PDF	http://arxiv.org/pdf/1605.06838v3.pdf
PWC	https://paperswithcode.com/paper/causality-on-longitudinal-data-stable
Repo
Framework