May 6, 2019

2917 words 14 mins read

Paper Group ANR 251

A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation. Crowdsourcing in Computer Vision. Autonomous Ingress of a UAV through a window using Monocular Vision. The belief noisy-or model applied to network reliability analysis. Transferring Learned Microcalcification Group Detection from 2D Mammography to 3D D …

A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation


Title	A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation
Authors	Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran, Min-Yen Kan
Abstract	Word embeddings are now ubiquitous forms of word representation in natural language processing. There have been applications of word embeddings for monolingual word sense disambiguation (WSD) in English, but few comparisons have been done. This paper attempts to bridge that gap by examining popular embeddings for the task of monolingual English WSD. Our simplified method leads to comparable state-of-the-art performance without expensive retraining. Cross-Lingual WSD - where the word senses of a word in a source language e come from a separate target translation language f - can also assist in language learning; for example, when providing translations of target vocabulary for learners. Thus we have also applied word embeddings to the novel task of cross-lingual WSD for Chinese and provide a public dataset for further benchmarking. We have also experimented with using word embeddings for LSTM networks and found surprisingly that a basic LSTM network does not work well. We discuss the ramifications of this outcome.
Tasks	Word Embeddings, Word Sense Disambiguation
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02956v3
PDF	http://arxiv.org/pdf/1611.02956v3.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-word-embeddings-for-english
Repo
Framework

Crowdsourcing in Computer Vision


Title	Crowdsourcing in Computer Vision
Authors	Adriana Kovashka, Olga Russakovsky, Li Fei-Fei, Kristen Grauman
Abstract	Computer vision systems require large amounts of manually annotated data to properly learn challenging visual concepts. Crowdsourcing platforms offer an inexpensive method to capture human knowledge and understanding, for a vast number of visual perception tasks. In this survey, we describe the types of annotations computer vision researchers have collected using crowdsourcing, and how they have ensured that this data is of high quality while annotation effort is minimized. We begin by discussing data collection on both classic (e.g., object recognition) and recent (e.g., visual story-telling) vision tasks. We then summarize key design decisions for creating effective data collection interfaces and workflows, and present strategies for intelligently selecting the most important data instances to annotate. Finally, we conclude with some thoughts on the future of crowdsourcing in computer vision.
Tasks	Object Recognition
Published	2016-11-07
URL	http://arxiv.org/abs/1611.02145v1
PDF	http://arxiv.org/pdf/1611.02145v1.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-in-computer-vision
Repo
Framework

Autonomous Ingress of a UAV through a window using Monocular Vision


Title	Autonomous Ingress of a UAV through a window using Monocular Vision
Authors	Abhinav Pachauri, Vikrant More, Pradeep Gaidhani, Nitin Gupta
Abstract	The use of autonomous UAVs for surveillance purposes and other reconnaissance tasks is increasingly becoming popular and convenient.These tasks requires the ability to successfully ingress through the rectangular openings or windows of the target structure.In this paper, a method to robustly detect the window in the surrounding using basic image processing techniques and efficient distance measure, is proposed.Furthermore, a navigation scheme which incorporates this detection method for performing navigation task has also been proposed.The whole navigation task is performed and tested in the simulation environment GAZEBO.
Tasks
Published	2016-07-24
URL	http://arxiv.org/abs/1607.07006v1
PDF	http://arxiv.org/pdf/1607.07006v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-ingress-of-a-uav-through-a-window
Repo
Framework

The belief noisy-or model applied to network reliability analysis


Title	The belief noisy-or model applied to network reliability analysis
Authors	Kuang Zhou, Arnaud Martin, Quan Pan
Abstract	One difficulty faced in knowledge engineering for Bayesian Network (BN) is the quan-tification step where the Conditional Probability Tables (CPTs) are determined. The number of parameters included in CPTs increases exponentially with the number of parent variables. The most common solution is the application of the so-called canonical gates. The Noisy-OR (NOR) gate, which takes advantage of the independence of causal interactions, provides a logarithmic reduction of the number of parameters required to specify a CPT. In this paper, an extension of NOR model based on the theory of belief functions, named Belief Noisy-OR (BNOR), is proposed. BNOR is capable of dealing with both aleatory and epistemic uncertainty of the network. Compared with NOR, more rich information which is of great value for making decisions can be got when the available knowledge is uncertain. Specially, when there is no epistemic uncertainty, BNOR degrades into NOR. Additionally, different structures of BNOR are presented in this paper in order to meet various needs of engineers. The application of BNOR model on the reliability evaluation problem of networked systems demonstrates its effectiveness.
Tasks
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01116v1
PDF	http://arxiv.org/pdf/1606.01116v1.pdf
PWC	https://paperswithcode.com/paper/the-belief-noisy-or-model-applied-to-network
Repo
Framework

Transferring Learned Microcalcification Group Detection from 2D Mammography to 3D Digital Breast Tomosynthesis Using a Hierarchical Model and Scope-based Normalization Features


Title	Transferring Learned Microcalcification Group Detection from 2D Mammography to 3D Digital Breast Tomosynthesis Using a Hierarchical Model and Scope-based Normalization Features
Authors	Yin Yin, Sergei V. Fotin, Hrishikesh Haldankar, Jeffrey W. Hoffmeister, Senthil Periaswamy
Abstract	A novel hierarchical model is introduced to solve a general problem of detecting groups of similar objects. Under this model, detection of groups is performed in hierarchically organized layers while each layer represents a scope for target objects. The processing of these layers involves sequential extraction of appearance features for an individual object, consistency measurement features for nearby objects, and finally the distribution features for all objects within the group. Using the concept of scope-based normalization, the extracted features not only enhance local contrast of an individual object, but also provide consistent characterization for all related objects. As an example, a microcalcification group detection system for 2D mammography was developed, and then the learned model was transferred to 3D digital breast tomosynthesis without any retraining or fine-tuning. The detection system demonstrated state-of-the-art performance and detected 96% of cancerous lesions at the rate of 1.2 false positives per volume as measured on an independent tomosynthesis test set.
Tasks
Published	2016-03-18
URL	http://arxiv.org/abs/1603.05955v1
PDF	http://arxiv.org/pdf/1603.05955v1.pdf
PWC	https://paperswithcode.com/paper/transferring-learned-microcalcification-group
Repo
Framework

A Quasi-Bayesian Perspective to Online Clustering


Title	A Quasi-Bayesian Perspective to Online Clustering
Authors	Le Li, Benjamin Guedj, Sébastien Loustau
Abstract	When faced with high frequency streams of data, clustering raises theoretical and algorithmic pitfalls. We introduce a new and adaptive online clustering algorithm relying on a quasi-Bayesian approach, with a dynamic (i.e., time-dependent) estimation of the (unknown and changing) number of clusters. We prove that our approach is supported by minimax regret bounds. We also provide an RJMCMC-flavored implementation (called PACBO, see https://cran.r-project.org/web/packages/PACBO/index.html) for which we give a convergence guarantee. Finally, numerical experiments illustrate the potential of our procedure.
Tasks
Published	2016-02-01
URL	http://arxiv.org/abs/1602.00522v3
PDF	http://arxiv.org/pdf/1602.00522v3.pdf
PWC	https://paperswithcode.com/paper/a-quasi-bayesian-perspective-to-online
Repo
Framework

Structured Prediction by Conditional Risk Minimization


Title	Structured Prediction by Conditional Risk Minimization
Authors	Chong Yang Goh, Patrick Jaillet
Abstract	We propose a general approach for supervised learning with structured output spaces, such as combinatorial and polyhedral sets, that is based on minimizing estimated conditional risk functions. Given a loss function defined over pairs of output labels, we first estimate the conditional risk function by solving a (possibly infinite) collection of regularized least squares problems. A prediction is made by solving an inference problem that minimizes the estimated conditional risk function over the output space. We show that this approach enables, in some cases, efficient training and inference without explicitly introducing a convex surrogate for the original loss function, even when it is discontinuous. Empirical evaluations on real-world and synthetic data sets demonstrate the effectiveness of our method in adapting to a variety of loss functions.
Tasks	Structured Prediction
Published	2016-11-21
URL	http://arxiv.org/abs/1611.07096v2
PDF	http://arxiv.org/pdf/1611.07096v2.pdf
PWC	https://paperswithcode.com/paper/structured-prediction-by-conditional-risk
Repo
Framework

TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency


Title	TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
Authors	Adji B. Dieng, Chong Wang, Jianfeng Gao, John Paisley
Abstract	In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are good at capturing the local structure of a word sequence - both semantic and syntactic - but might face difficulty remembering long-range dependencies. Intuitively, these long-range dependencies are of semantic nature. In contrast, latent topic models are able to capture the global underlying semantic structure of a document but do not account for word ordering. The proposed TopicRNN model integrates the merits of RNNs and latent topic models: it captures local (syntactic) dependencies using an RNN and global (semantic) dependencies using latent topics. Unlike previous work on contextual RNN language modeling, our model is learned end-to-end. Empirical results on word prediction show that TopicRNN outperforms existing contextual RNN baselines. In addition, TopicRNN can be used as an unsupervised feature extractor for documents. We do this for sentiment analysis on the IMDB movie review dataset and report an error rate of $6.28%$. This is comparable to the state-of-the-art $5.91%$ resulting from a semi-supervised approach. Finally, TopicRNN also yields sensible topics, making it a useful alternative to document models such as latent Dirichlet allocation.
Tasks	Language Modelling, Sentiment Analysis, Topic Models
Published	2016-11-05
URL	http://arxiv.org/abs/1611.01702v2
PDF	http://arxiv.org/pdf/1611.01702v2.pdf
PWC	https://paperswithcode.com/paper/topicrnn-a-recurrent-neural-network-with-long
Repo
Framework

Human Action Attribute Learning From Video Data Using Low-Rank Representations


Title	Human Action Attribute Learning From Video Data Using Low-Rank Representations
Authors	Tong Wu, Prudhvi Gurram, Raghuveer M. Rao, Waheed U. Bajwa
Abstract	Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR) model, termed the clustering-aware structure-constrained low-rank representation (CS-LRR) model, for unsupervised learning of human action attributes from video data. Our model is based on the union-of-subspaces (UoS) framework, and integrates spectral clustering into the LRR optimization problem for better subspace clustering results. We lay out an efficient linear alternating direction method to solve the CS-LRR optimization problem. We also introduce a hierarchical subspace clustering approach, termed hierarchical CS-LRR, to learn the attributes without the need for a priori specification of their number. By visualizing and labeling these action attributes, the hierarchical model can be used to semantically summarize long video sequences of human actions at multiple resolutions. A human action or activity can also be uniquely represented as a sequence of transitions from one action attribute to another, which can then be used for human action recognition. We demonstrate the effectiveness of the proposed model for semantic summarization and action recognition through comprehensive experiments on five real-world human action datasets.
Tasks	Activity Recognition, Human Activity Recognition, Temporal Action Localization
Published	2016-12-23
URL	http://arxiv.org/abs/1612.07857v1
PDF	http://arxiv.org/pdf/1612.07857v1.pdf
PWC	https://paperswithcode.com/paper/human-action-attribute-learning-from-video
Repo
Framework

RetiNet: Automatic AMD identification in OCT volumetric data


Title	RetiNet: Automatic AMD identification in OCT volumetric data
Authors	Stefanos Apostolopoulos, Carlos Ciller, Sandro I. De Zanet, Sebastian Wolf, Raphael Sznitman
Abstract	Optical Coherence Tomography (OCT) provides a unique ability to image the eye retina in 3D at micrometer resolution and gives ophthalmologist the ability to visualize retinal diseases such as Age-Related Macular Degeneration (AMD). While visual inspection of OCT volumes remains the main method for AMD identification, doing so is time consuming as each cross-section within the volume must be inspected individually by the clinician. In much the same way, acquiring ground truth information for each cross-section is expensive and time consuming. This fact heavily limits the ability to acquire large amounts of ground truth, which subsequently impacts the performance of learning-based methods geared at automatic pathology identification. To avoid this burden, we propose a novel strategy for automatic analysis of OCT volumes where only volume labels are needed. That is, we train a classifier in a semi-supervised manner to conduct this task. Our approach uses a novel Convolutional Neural Network (CNN) architecture, that only needs volume-level labels to be trained to automatically asses whether an OCT volume is healthy or contains AMD. Our architecture involves first learning a cross-section pathology classifier using pseudo-labels that could be corrupted and then leverage these towards a more accurate volume-level classification. We then show that our approach provides excellent performances on a publicly available dataset and outperforms a number of existing automatic techniques.
Tasks
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03628v1
PDF	http://arxiv.org/pdf/1610.03628v1.pdf
PWC	https://paperswithcode.com/paper/retinet-automatic-amd-identification-in-oct
Repo
Framework

An optimal algorithm for bandit convex optimization


Title	An optimal algorithm for bandit convex optimization
Authors	Elad Hazan, Yuanzhi Li
Abstract	We consider the problem of online convex optimization against an arbitrary adversary with bandit feedback, known as bandit convex optimization. We give the first $\tilde{O}(\sqrt{T})$-regret algorithm for this setting based on a novel application of the ellipsoid method to online learning. This bound is known to be tight up to logarithmic factors. Our analysis introduces new tools in discrete convex geometry.
Tasks
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04350v2
PDF	http://arxiv.org/pdf/1603.04350v2.pdf
PWC	https://paperswithcode.com/paper/an-optimal-algorithm-for-bandit-convex
Repo
Framework

Stochastic Games for Smart Grid Energy Management with Prospect Prosumers


Title	Stochastic Games for Smart Grid Energy Management with Prospect Prosumers
Authors	Seyed Rasoul Etesami, Walid Saad, Narayan Mandayam, H. Vincent Poor
Abstract	In this paper, the problem of smart grid energy management under stochastic dynamics is investigated. In the considered model, at the demand side, it is assumed that customers can act as prosumers who own renewable energy sources and can both produce and consume energy. Due to the coupling between the prosumers’ decisions and the stochastic nature of renewable energy, the interaction among prosumers is formulated as a stochastic game, in which each prosumer seeks to maximize its payoff, in terms of revenues, by controlling its energy consumption and demand. In particular, the subjective behavior of prosumers is explicitly reflected into their payoff functions using prospect theory, a powerful framework that allows modeling real-life human choices. For this prospect-based stochastic game, it is shown that there always exists a stationary Nash equilibrium where the prosumers’ trading policies in the equilibrium are independent of the time and their histories of the play. Moreover, a novel distributed algorithm with no information sharing among prosumers is proposed and shown to converge to an $\epsilon$-Nash equilibrium. On the other hand, at the supply side, the interaction between the utility company and the prosumers is formulated as an online optimization problem in which the utility company’s goal is to learn its optimal energy allocation rules. For this case, it is shown that such an optimization problem admits a no-regret algorithm meaning that regardless of the actual outcome of the game among the prosumers, the utility company can follow a strategy that mitigates its allocation costs as if it knew the entire demand market a priori. Simulation results show the convergence of the proposed algorithms to their predicted outcomes and present new insights resulting from prospect theory that contribute toward more efficient energy management in the smart grids.
Tasks
Published	2016-10-06
URL	http://arxiv.org/abs/1610.02067v2
PDF	http://arxiv.org/pdf/1610.02067v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-games-for-smart-grid-energy
Repo
Framework

Personalized Emphasis Framing for Persuasive Message Generation


Title	Personalized Emphasis Framing for Persuasive Message Generation
Authors	Tao Ding, Shimei Pan
Abstract	In this paper, we present a study on personalized emphasis framing which can be used to tailor the content of a message to enhance its appeal to different individuals. With this framework, we directly model content selection decisions based on a set of psychologically-motivated domain-independent personal traits including personality (e.g., extraversion and conscientiousness) and basic human values (e.g., self-transcendence and hedonism). We also demonstrate how the analysis results can be used in automated personalized content selection for persuasive message generation.
Tasks
Published	2016-07-29
URL	http://arxiv.org/abs/1607.08898v1
PDF	http://arxiv.org/pdf/1607.08898v1.pdf
PWC	https://paperswithcode.com/paper/personalized-emphasis-framing-for-persuasive
Repo
Framework

Toward Automatic Understanding of the Function of Affective Language in Support Groups


Title	Toward Automatic Understanding of the Function of Affective Language in Support Groups
Authors	Amit Navindgi, Caroline Brun, Cécile Boulard Masson, Scott Nowson
Abstract	Understanding expressions of emotions in support forums has considerable value and NLP methods are key to automating this. Many approaches understandably use subjective categories which are more fine-grained than a straightforward polarity-based spectrum. However, the definition of such categories is non-trivial and, in fact, we argue for a need to incorporate communicative elements even beyond subjectivity. To support our position, we report experiments on a sentiment-labelled corpus of posts taken from a medical support forum. We argue that not only is a more fine-grained approach to text analysis important, but simultaneously recognising the social function behind affective expressions enable a more accurate and valuable level of understanding.
Tasks
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01910v1
PDF	http://arxiv.org/pdf/1610.01910v1.pdf
PWC	https://paperswithcode.com/paper/toward-automatic-understanding-of-the
Repo
Framework

Active Learning and Proofreading for Delineation of Curvilinear Structures


Title	Active Learning and Proofreading for Delineation of Curvilinear Structures
Authors	Agata Mosinska, Jakub Tarnawski, Pascal Fua
Abstract	Many state-of-the-art delineation methods rely on supervised machine learning algorithms. As a result, they require manually annotated training data, which is tedious to obtain. Furthermore, even minor classification errors may significantly affect the topology of the final result. In this paper we propose a generic approach to addressing both of these problems by taking into account the influence of a potential misclassification on the resulting delineation. In an Active Learning context, we identify parts of linear structures that should be annotated first in order to train a classifier effectively. In a proofreading context, we similarly find regions of the resulting reconstruction that should be verified in priority to obtain a nearly-perfect result. In both cases, by focusing the attention of the human expert on potential classification mistakes which are the most critical parts of the delineation, we reduce the amount of required supervision. We demonstrate the effectiveness of our approach on microscopy images depicting blood vessels and neurons.
Tasks	Active Learning
Published	2016-12-23
URL	http://arxiv.org/abs/1612.08036v2
PDF	http://arxiv.org/pdf/1612.08036v2.pdf
PWC	https://paperswithcode.com/paper/active-learning-and-proofreading-for
Repo
Framework