May 5, 2019

3058 words 15 mins read

Paper Group ANR 548

DNA Image Pro – A Tool for Generating Pixel Patterns using DNA Tile Assembly. Projected Estimators for Robust Semi-supervised Classification. Adaptive Combination of l0 LMS Adaptive Filters for Sparse System Identification in Fluctuating Noise Power. GIFT: A Real-time and Scalable 3D Shape Search Engine. Multilingual Multiword Expressions. Machine …

DNA Image Pro – A Tool for Generating Pixel Patterns using DNA Tile Assembly


Title	DNA Image Pro – A Tool for Generating Pixel Patterns using DNA Tile Assembly
Authors	Dixita Limbachiya, Dhaval Trivedi, Manish K Gupta
Abstract	Self-assembly is a process found everywhere in the Nature. In particular, it is known that DNA self-assembly is Turing universal. Thus one can do arbitrary computations or build nano-structures using DNA self-assembly. In order to understand the DNA self-assembly process, many mathematical models have been proposed in the literature. In particular, abstract Tile Assembly Model (aTAM) received much attention. In this work, we investigate pixel pattern generation using aTAM. For a given image, a tile assembly system is given which can generate the image by self-assembly process. We also consider image blocks with specific cyclic pixel patterns (uniform shift and non uniform shift) self assembly. A software, DNA Image Pro, for generating pixel patterns using DNA tile assembly is also given.
Tasks
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03434v1
PDF	http://arxiv.org/pdf/1607.03434v1.pdf
PWC	https://paperswithcode.com/paper/dna-image-pro-a-tool-for-generating-pixel
Repo
Framework

Projected Estimators for Robust Semi-supervised Classification


Title	Projected Estimators for Robust Semi-supervised Classification
Authors	Jesse H. Krijthe, Marco Loog
Abstract	For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a projection of the supervised estimate onto a set of constraints imposed by the unlabeled data, we find we can safely improve over the supervised solution in terms of this quadratic loss. Unlike other approaches to semi-supervised learning, the procedure does not rely on assumptions that are not intrinsic to the classifier at hand. It is theoretically demonstrated that, measured on the labeled and unlabeled training data, this semi-supervised procedure never gives a lower quadratic loss than the supervised alternative. To our knowledge this is the first approach that offers such strong, albeit conservative, guarantees for improvement over the supervised solution. The characteristics of our approach are explicated using benchmark datasets to further understand the similarities and differences between the quadratic loss criterion used in the theoretical results and the classification accuracy often considered in practice.
Tasks
Published	2016-02-25
URL	http://arxiv.org/abs/1602.07865v1
PDF	http://arxiv.org/pdf/1602.07865v1.pdf
PWC	https://paperswithcode.com/paper/projected-estimators-for-robust-semi
Repo
Framework

Adaptive Combination of l0 LMS Adaptive Filters for Sparse System Identification in Fluctuating Noise Power


Title	Adaptive Combination of l0 LMS Adaptive Filters for Sparse System Identification in Fluctuating Noise Power
Authors	Bijit Kumar Das, Mrityunjoy Chakraborty
Abstract	Recently, the l0-least mean square (l0-LMS) algorithm has been proposed to identify sparse linear systems by employing a sparsity-promoting continuous function as an approximation of l0 pseudonorm penalty. However, the performance of this algorithm is sensitive to the appropriate choice of the some parameter responsible for the zero-attracting intensity. The optimum choice for this parameter depends on the signal-to-noise ratio (SNR) prevailing in the system. Thus, it becomes difficult to fix a suitable value for this parameter, particularly in a situation where SNR fluctuates over time. In this work, we propose several adaptive combinations of differently parameterized l0-LMS to get an overall satisfactory performance independent of the SNR, and discuss some issues relevant to these combination structures. We also demonstrate an efficient partial update scheme which not only reduces the number of computations per iteration, but also achieves some interesting performance gain compared with the full update case. Then, we propose a new recursive least squares (RLS)-type rule to update the combining parameter more efficiently. Finally, we extend the combination of two filters to a combination of M number adaptive filters, which manifests further improvement for M > 2.
Tasks
Published	2016-05-10
URL	http://arxiv.org/abs/1605.02878v1
PDF	http://arxiv.org/pdf/1605.02878v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-combination-of-l0-lms-adaptive
Repo
Framework

GIFT: A Real-time and Scalable 3D Shape Search Engine


Title	GIFT: A Real-time and Scalable 3D Shape Search Engine
Authors	Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, Longin Jan Latecki
Abstract	Projective analysis is an important solution for 3D shape retrieval, since human visual perceptions of 3D shapes rely on various 2D observations from different view points. Although multiple informative and discriminative views are utilized, most projection-based retrieval systems suffer from heavy computational cost, thus cannot satisfy the basic requirement of scalability for search engines. In this paper, we present a real-time 3D shape search engine based on the projective images of 3D shapes. The real-time property of our search engine results from the following aspects: (1) efficient projection and view feature extraction using GPU acceleration; (2) the first inverted file, referred as F-IF, is utilized to speed up the procedure of multi-view matching; (3) the second inverted file (S-IF), which captures a local distribution of 3D shapes in the feature manifold, is adopted for efficient context-based re-ranking. As a result, for each query the retrieval task can be finished within one second despite the necessary cost of IO overhead. We name the proposed 3D shape search engine, which combines GPU acceleration and Inverted File Twice, as GIFT. Besides its high efficiency, GIFT also outperforms the state-of-the-art methods significantly in retrieval accuracy on various shape benchmarks and competitions.
Tasks	3D Shape Retrieval
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01879v2
PDF	http://arxiv.org/pdf/1604.01879v2.pdf
PWC	https://paperswithcode.com/paper/gift-a-real-time-and-scalable-3d-shape-search
Repo
Framework

Multilingual Multiword Expressions


Title	Multilingual Multiword Expressions
Authors	Lahari Poddar
Abstract	The project aims to provide a semi-supervised approach to identify Multiword Expressions in a multilingual context consisting of English and most of the major Indian languages. Multiword expressions are a group of words which refers to some conventional or regional way of saying things. If they are literally translated from one language to another the expression will lose its inherent meaning. To automatically extract multiword expressions from a corpus, an extraction pipeline have been constructed which consist of a combination of rule based and statistical approaches. There are several types of multiword expressions which differ from each other widely by construction. We employ different methods to detect different types of multiword expressions. Given a POS tagged corpus in English or any Indian language the system initially applies some regular expression filters to narrow down the search space to certain patterns (like, reduplication, partial reduplication, compound nouns, compound verbs, conjunct verbs etc.). The word sequences matching the required pattern are subjected to a series of linguistic tests which include verb filtering, named entity filtering and hyphenation filtering test to exclude false positives. The candidates are then checked for semantic relationships among themselves (using Wordnet). In order to detect partial reduplication we make use of Wordnet as a lexical database as well as a tool for lemmatising. We detect complex predicates by investigating the features of the constituent words. Statistical methods are applied to detect collocations. Finally, lexicographers examine the list of automatically extracted candidates to validate whether they are true multiword expressions or not and add them to the multiword dictionary accordingly.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00246v1
PDF	http://arxiv.org/pdf/1612.00246v1.pdf
PWC	https://paperswithcode.com/paper/multilingual-multiword-expressions
Repo
Framework

Machine Learning Across Cultures: Modeling the Adoption of Financial Services for the Poor


Title	Machine Learning Across Cultures: Modeling the Adoption of Financial Services for the Poor
Authors	Muhammad Raza Khan, Joshua E. Blumenstock
Abstract	Recently, mobile operators in many developing economies have launched “Mobile Money” platforms that deliver basic financial services over the mobile phone network. While many believe that these services can improve the lives of the poor, a consistent difficulty has been identifying individuals most likely to benefit from access to the new technology. Here, we combine terabyte-scale data from three different mobile phone operators from Ghana, Pakistan, and Zambia, to better understand the behavioral determinants of mobile money adoption. Our supervised learning models provide insight into the best predictors of adoption in three very distinct cultures. We find that models fit on one population fail to generalize to another, and in general are highly context-dependent. These findings highlight the need for a nuanced approach to understanding the role and potential of financial services for the poor.
Tasks
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05105v1
PDF	http://arxiv.org/pdf/1606.05105v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-across-cultures-modeling-the
Repo
Framework

Digits that are not: Generating new types through deep neural nets


Title	Digits that are not: Generating new types through deep neural nets
Authors	Akın Kazakçıand Mehdi Cherti, Balázs Kégl
Abstract	For an artificial creative agent, an essential driver of the search for novelty is a value function which is often provided by the system designer or users. We argue that an important barrier for progress in creativity research is the inability of these systems to develop their own notion of value for novelty. We propose a notion of knowledge-driven creativity that circumvent the need for an externally imposed value function, allowing the system to explore based on what it has learned from a set of referential objects. The concept is illustrated by a specific knowledge model provided by a deep generative autoencoder. Using the described system, we train a knowledge model on a set of digit images and we use the same model to build coherent sets of new digits that do not belong to known digit types.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04345v1
PDF	http://arxiv.org/pdf/1606.04345v1.pdf
PWC	https://paperswithcode.com/paper/digits-that-are-not-generating-new-types
Repo
Framework

On the Place of Text Data in Lifelogs, and Text Analysis via Semantic Facets


Title	On the Place of Text Data in Lifelogs, and Text Analysis via Semantic Facets
Authors	Gregory Grefenstette, Lawrence Muchemi
Abstract	Current research in lifelog data has not paid enough attention to analysis of cognitive activities in comparison to physical activities. We argue that as we look into the future, wearable devices are going to be cheaper and more prevalent and textual data will play a more significant role. Data captured by lifelogging devices will increasingly include speech and text, potentially useful in analysis of intellectual activities. Analyzing what a person hears, reads, and sees, we should be able to measure the extent of cognitive activity devoted to a certain topic or subject by a learner. Test-based lifelog records can benefit from semantic analysis tools developed for natural language processing. We show how semantic analysis of such text data can be achieved through the use of taxonomic subject facets and how these facets might be useful in quantifying cognitive activity devoted to various topics in a person’s day. We are currently developing a method to automatically create taxonomic topic vocabularies that can be applied to this detection of intellectual activity.
Tasks
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02440v1
PDF	http://arxiv.org/pdf/1606.02440v1.pdf
PWC	https://paperswithcode.com/paper/on-the-place-of-text-data-in-lifelogs-and
Repo
Framework

3-D Convolutional Neural Networks for Glioblastoma Segmentation


Title	3-D Convolutional Neural Networks for Glioblastoma Segmentation
Authors	Darvin Yi, Mu Zhou, Zhao Chen, Olivier Gevaert
Abstract	Convolutional Neural Networks (CNN) have emerged as powerful tools for learning discriminative image features. In this paper, we propose a framework of 3-D fully CNN models for Glioblastoma segmentation from multi-modality MRI data. By generalizing CNN models to true 3-D convolutions in learning 3-D tumor MRI data, the proposed approach utilizes a unique network architecture to decouple image pixels. Specifically, we design a convolutional layer with pre-defined Difference- of-Gaussian (DoG) filters to perform true 3-D convolution incorporating local neighborhood information at each pixel. We then use three trained convolutional layers that act to decouple voxels from the initial 3-D convolution. The proposed framework allows identification of high-level tumor structures on MRI. We evaluate segmentation performance on the BRATS segmentation dataset with 274 tumor samples. Extensive experimental results demonstrate encouraging performance of the proposed approach comparing to the state-of-the-art methods. Our data-driven approach achieves a median Dice score accuracy of 89% in whole tumor glioblastoma segmentation, revealing a generalized low-bias possibility to learn from medium-size MRI datasets.
Tasks
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04534v1
PDF	http://arxiv.org/pdf/1611.04534v1.pdf
PWC	https://paperswithcode.com/paper/3-d-convolutional-neural-networks-for
Repo
Framework


Title	Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks
Authors	Dat Tien Nguyen, Kamela Ali Al Mannai, Shafiq Joty, Hassan Sajjad, Muhammad Imran, Prasenjit Mitra
Abstract	The role of social media, in particular microblogging platforms such as Twitter, as a conduit for actionable and tactical information during disasters is increasingly acknowledged. However, time-critical analysis of big crisis data on social media streams brings challenges to machine learning techniques, especially the ones that use supervised learning. The Scarcity of labeled data, particularly in the early hours of a crisis, delays the machine learning process. The current state-of-the-art classification methods require a significant amount of labeled data specific to a particular event for training plus a lot of feature engineering to achieve best results. In this work, we introduce neural network based classification methods for binary and multi-class tweet classification task. We show that neural network based models do not require any feature engineering and perform better than state-of-the-art methods. In the early hours of a disaster when no labeled data is available, our proposed method makes the best use of the out-of-event data and achieves good results.
Tasks	Feature Engineering
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03902v1
PDF	http://arxiv.org/pdf/1608.03902v1.pdf
PWC	https://paperswithcode.com/paper/rapid-classification-of-crisis-related-data
Repo
Framework

Intra-day Activity Better Predicts Chronic Conditions


Title	Intra-day Activity Better Predicts Chronic Conditions
Authors	Tom Quisel, David C. Kale, Luca Foschini
Abstract	In this work we investigate intra-day patterns of activity on a population of 7,261 users of mobile health wearable devices and apps. We show that: (1) using intra-day step and sleep data recorded from passive trackers significantly improves classification performance on self-reported chronic conditions related to mental health and nervous system disorders, (2) Convolutional Neural Networks achieve top classification performance vs. baseline models when trained directly on multivariate time series of activity data, and (3) jointly predicting all condition classes via multi-task learning can be leveraged to extract features that generalize across data sets and achieve the highest classification performance.
Tasks	Multi-Task Learning, Time Series
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01200v1
PDF	http://arxiv.org/pdf/1612.01200v1.pdf
PWC	https://paperswithcode.com/paper/intra-day-activity-better-predicts-chronic
Repo
Framework


Title	Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
Authors	Guanqun Cao, Alexandros Iosifidis, Ke Chen, Moncef Gabbouj
Abstract	In this paper, the problem of multi-view embedding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Sqaure regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and (deep) neural networks are derived, achieving better performance than the linear ones. Moreover, a novel Multi-view Modular Discriminant Analysis (MvMDA) is proposed by taking the view difference into consideration. We demonstrate the effectiveness of the proposed multi-view embedding methods on visual object recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.
Tasks	Cross-Modal Retrieval, Image Retrieval, Object Recognition
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09696v3
PDF	http://arxiv.org/pdf/1605.09696v3.pdf
PWC	https://paperswithcode.com/paper/generalized-multi-view-embedding-for-visual
Repo
Framework

Generating Natural Language Inference Chains


Title	Generating Natural Language Inference Chains
Authors	Vladyslav Kolesnyk, Tim Rocktäschel, Sebastian Riedel
Abstract	The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can recognize textual entailment, i.e., whether one sentence can be inferred from another one. However, in most NLP applications only single source sentences instead of sentence pairs are available. Hence, we propose a new task that measures how well a model can generate an entailed sentence from a source sentence. We take entailment-pairs of the Stanford Natural Language Inference corpus and train an LSTM with attention. On a manually annotated test set we found that 82% of generated sentences are correct, an improvement of 10.3% over an LSTM baseline. A qualitative analysis shows that this model is not only capable of shortening input sentences, but also inferring new statements via paraphrasing and phrase entailment. We then apply this model recursively to input-output pairs, thereby generating natural language inference chains that can be used to automatically construct an entailment graph from source sentences. Finally, by swapping source and target sentences we can also train a model that given an input sentence invents additional information to generate a new sentence.
Tasks	Machine Translation, Natural Language Inference, Question Answering
Published	2016-06-04
URL	http://arxiv.org/abs/1606.01404v1
PDF	http://arxiv.org/pdf/1606.01404v1.pdf
PWC	https://paperswithcode.com/paper/generating-natural-language-inference-chains
Repo
Framework

ResearchDoom and CocoDoom: Learning Computer Vision with Games


Title	ResearchDoom and CocoDoom: Learning Computer Vision with Games
Authors	A. Mahendran, H. Bilen, J. F. Henriques, A. Vedaldi
Abstract	In this short note we introduce ResearchDoom, an implementation of the Doom first-person shooter that can extract detailed metadata from the game. We also introduce the CocoDoom dataset, a collection of pre-recorded data extracted from Doom gaming sessions along with annotations in the MS Coco format. ResearchDoom and CocoDoom can be used to train and evaluate a variety of computer vision methods such as object recognition, detection and segmentation at the level of instances and categories, tracking, ego-motion estimation, monocular depth estimation and scene segmentation. The code and data are available at http://www.robots.ox.ac.uk/~vgg/research/researchdoom.
Tasks	Depth Estimation, Monocular Depth Estimation, Motion Estimation, Object Recognition, Scene Segmentation
Published	2016-10-07
URL	http://arxiv.org/abs/1610.02431v1
PDF	http://arxiv.org/pdf/1610.02431v1.pdf
PWC	https://paperswithcode.com/paper/researchdoom-and-cocodoom-learning-computer
Repo
Framework

Quantifying Urban Traffic Anomalies


Title	Quantifying Urban Traffic Anomalies
Authors	Zhengyi Zhou, Philipp Meerkamp, Chris Volinsky
Abstract	Detecting and quantifying anomalies in urban traffic is critical for real-time alerting or re-routing in the short run and urban planning in the long run. We describe a two-step framework that achieves these two goals in a robust, fast, online, and unsupervised manner. First, we adapt stable principal component pursuit to detect anomalies for each road segment. This allows us to pinpoint traffic anomalies early and precisely in space. Then we group the road-level anomalies across time and space into meaningful anomaly events using a simple graph expansion procedure. These events can be easily clustered, visualized, and analyzed by urban planners. We demonstrate the effectiveness of our system using 7 weeks of anonymized and aggregated cellular location data in Dallas-Fort Worth. We suggest potential opportunities for urban planners and policy makers to use our methodology to make informed changes. These applications include real-time re-routing of traffic in response to abnormally high traffic, or identifying candidates for high-impact infrastructure projects.
Tasks
Published	2016-09-30
URL	http://arxiv.org/abs/1610.00579v1
PDF	http://arxiv.org/pdf/1610.00579v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-urban-traffic-anomalies
Repo
Framework