May 7, 2019

2629 words 13 mins read

Paper Group ANR 115

Multimodal Sparse Coding for Event Detection. Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder. Mental State Recognition via Wearable EEG. Extract fetal ECG from single-lead abdominal ECG by de-shape short time Fourier transform and nonlocal median. Proof nets for the Displacement calculus. Supervis …

Multimodal Sparse Coding for Event Detection


Title	Multimodal Sparse Coding for Event Detection
Authors	Youngjune Gwon, William Campbell, Kevin Brady, Douglas Sturim, Miriam Cha, H. T. Kung
Abstract	Unsupervised feature learning methods have proven effective for classification tasks based on a single modality. We present multimodal sparse coding for learning feature representations shared across multiple modalities. The shared representations are applied to multimedia event detection (MED) and evaluated in comparison to unimodal counterparts, as well as other feature learning methods such as GMM supervectors and sparse RBM. We report the cross-validated classification accuracy and mean average precision of the MED system trained on features learned from our unimodal and multimodal settings for a subset of the TRECVID MED 2014 dataset.
Tasks
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05212v1
PDF	http://arxiv.org/pdf/1605.05212v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-sparse-coding-for-event-detection
Repo
Framework

Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder


Title	Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder
Authors	Sivanand Achanta, KNRK Raju Alluri, Suryakanth V Gangashetty
Abstract	In this paper, we describe a statistical parametric speech synthesis approach with unit-level acoustic representation. In conventional deep neural network based speech synthesis, the input text features are repeated for the entire duration of phoneme for mapping text and speech parameters. This mapping is learnt at the frame-level which is the de-facto acoustic representation. However much of this computational requirement can be drastically reduced if every unit can be represented with a fixed-dimensional representation. Using recurrent neural network based auto-encoder, we show that it is indeed possible to map units of varying duration to a single vector. We then use this acoustic representation at unit-level to synthesize speech using deep neural network based statistical parametric speech synthesis technique. Results show that the proposed approach is able to synthesize at the same quality as the conventional frame based approach at a highly reduced computational cost.
Tasks	Speech Synthesis
Published	2016-06-19
URL	http://arxiv.org/abs/1606.05844v1
PDF	http://arxiv.org/pdf/1606.05844v1.pdf
PWC	https://paperswithcode.com/paper/statistical-parametric-speech-synthesis-using-1
Repo
Framework

Mental State Recognition via Wearable EEG


Title	Mental State Recognition via Wearable EEG
Authors	Pouya Bashivan, Irina Rish, Steve Heisig
Abstract	The increasing quality and affordability of consumer electroencephalogram (EEG) headsets make them attractive for situations where medical grade devices are impractical. Predicting and tracking cognitive states is possible for tasks that were previously not conducive to EEG monitoring. For instance, monitoring operators for states inappropriate to the task (e.g. drowsy drivers), tracking mental health (e.g. anxiety) and productivity (e.g. tiredness) are among possible applications for the technology. Consumer grade EEG headsets are affordable and relatively easy to use, but they lack the resolution and quality of signal that can be achieved using medical grade EEG devices. Thus, the key questions remain: to what extent are wearable EEG devices capable of mental state recognition, and what kind of mental states can be accurately recognized with these devices? In this work, we examined responses to two different types of input: instructional (logical) versus recreational (emotional) videos, using a range of machine-learning methods. We tried SVMs, sparse logistic regression, and Deep Belief Networks, to discriminate between the states of mind induced by different types of video input, that can be roughly labeled as logical vs. emotional. Our results demonstrate a significant potential of wearable EEG devices in differentiating cognitive states between situations with large contextual but subtle apparent differences.
Tasks	EEG
Published	2016-02-02
URL	http://arxiv.org/abs/1602.00985v2
PDF	http://arxiv.org/pdf/1602.00985v2.pdf
PWC	https://paperswithcode.com/paper/mental-state-recognition-via-wearable-eeg
Repo
Framework

Extract fetal ECG from single-lead abdominal ECG by de-shape short time Fourier transform and nonlocal median


Title	Extract fetal ECG from single-lead abdominal ECG by de-shape short time Fourier transform and nonlocal median
Authors	Su Li, Hau-tieng Wu
Abstract	The multiple fundamental frequency detection problem and the source separation problem from a single-channel signal containing multiple oscillatory components and a nonstationary noise are both challenging tasks. To extract the fetal electrocardiogram (ECG) from a single-lead maternal abdominal ECG, we face both challenges. In this paper, we propose a novel method to extract the fetal ECG signal from the single channel maternal abdominal ECG signal, without any additional measurement. The algorithm is composed of three main ingredients. First, the maternal and fetal heart rates are estimated by the de-shape short time Fourier transform, which is a recently proposed nonlinear time-frequency analysis technique; second, the beat tracking technique is applied to accurately obtain the maternal and fetal R peaks; third, the maternal and fetal ECG waveforms are established by the nonlocal median. The algorithm is evaluated on a simulated fetal ECG signal database ({\em fecgsyn} database), and tested on two real databases with the annotation provided by experts ({\em adfecgdb} database and {\em CinC2013} database). In general, the algorithm could be applied to solve other detection and source separation problems, and reconstruct the time-varying wave-shape function of each oscillatory component.
Tasks
Published	2016-09-09
URL	http://arxiv.org/abs/1609.02938v1
PDF	http://arxiv.org/pdf/1609.02938v1.pdf
PWC	https://paperswithcode.com/paper/extract-fetal-ecg-from-single-lead-abdominal
Repo
Framework

Proof nets for the Displacement calculus


Title	Proof nets for the Displacement calculus
Authors	Richard Moot
Abstract	We present a proof net calculus for the Displacement calculus and show its correctness. This is the first proof net calculus which models the Displacement calculus directly and not by some sort of translation into another formalism. The proof net calculus opens up new possibilities for parsing and proof search with the Displacement calculus.
Tasks
Published	2016-06-06
URL	http://arxiv.org/abs/1606.01720v1
PDF	http://arxiv.org/pdf/1606.01720v1.pdf
PWC	https://paperswithcode.com/paper/proof-nets-for-the-displacement-calculus
Repo
Framework

Supervisory Control for Behavior Composition


Title	Supervisory Control for Behavior Composition
Authors	Paolo Felli, Nitin Yadav, Sebastian Sardina
Abstract	We relate behavior composition, a synthesis task studied in AI, to supervisory control theory from the discrete event systems field. In particular, we show that realizing (i.e., implementing) a target behavior module (e.g., a house surveillance system) by suitably coordinating a collection of available behaviors (e.g., automatic blinds, doors, lights, cameras, etc.) amounts to imposing a supervisor onto a special discrete event system. Such a link allows us to leverage on the solid foundations and extensive work on discrete event systems, including borrowing tools and ideas from that field. As evidence of that we show how simple it is to introduce preferences in the mapped framework.
Tasks
Published	2016-04-29
URL	http://arxiv.org/abs/1604.08768v1
PDF	http://arxiv.org/pdf/1604.08768v1.pdf
PWC	https://paperswithcode.com/paper/supervisory-control-for-behavior-composition
Repo
Framework

Crowdsourcing with Unsure Option


Title	Crowdsourcing with Unsure Option
Authors	Yao-Xiang Ding, Zhi-Hua Zhou
Abstract	One of the fundamental problems in crowdsourcing is the trade-off between the number of the workers needed for high-accuracy aggregation and the budget to pay. For saving budget, it is important to ensure high quality of the crowd-sourced labels, hence the total cost on label collection will be reduced. Since the self-confidence of the workers often has a close relationship with their abilities, a possible way for quality control is to request the workers to return the labels only when they feel confident, by means of providing unsure option to them. On the other hand, allowing workers to choose unsure option also leads to the potential danger of budget waste. In this work, we propose the analysis towards understanding when providing the unsure option indeed leads to significant cost reduction, as well as how the confidence threshold is set. We also propose an online mechanism, which is alternative for threshold selection when the estimation of the crowd ability distribution is difficult.
Tasks
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00292v2
PDF	http://arxiv.org/pdf/1609.00292v2.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-with-unsure-option
Repo
Framework

Tracking Algorithm for Microscopic Flow Data Collection


Title	Tracking Algorithm for Microscopic Flow Data Collection
Authors	Kardi Teknomo, Yasushi Takeyama, Hajime Inamura
Abstract	Various methods to automate traffic data collection have recently been developed by many researchers. A macroscopic data collection through image processing has been proposed. For microscopic traffic flow data, such as individual speed and time or distance headway, tracking of individual movement is needed. The tracking algorithms for pedestrian or vehicle have been developed to trace the movement of one or two pedestrians based on sign pattern, and feature detection. No research has been done to track many pedestrians or vehicles at once. This paper describes a new and fast algorithm to track the movement of many individual vehicles or pedestrians
Tasks
Published	2016-09-07
URL	http://arxiv.org/abs/1609.02137v1
PDF	http://arxiv.org/pdf/1609.02137v1.pdf
PWC	https://paperswithcode.com/paper/tracking-algorithm-for-microscopic-flow-data
Repo
Framework

Super-resolution estimation of cyclic arrival rates


Title	Super-resolution estimation of cyclic arrival rates
Authors	Ningyuan Chen, Donald K. K. Lee, Sahand Negahban
Abstract	Exploiting the fact that most arrival processes exhibit cyclic behaviour, we propose a simple procedure for estimating the intensity of a nonhomogeneous Poisson process. The estimator is the super-resolution analogue to Shao 2010 and Shao & Lii 2011, which is a sum of $p$ sinusoids where $p$ and the frequency, amplitude, and phase of each wave are not known and need to be estimated. This results in an interpretable yet flexible specification that is suitable for use in modelling as well as in high resolution simulations. Our estimation procedure sits in between classic periodogram methods and atomic/total variation norm thresholding. Through a novel use of window functions in the point process domain, our approach attains super-resolution without semidefinite programming. Under suitable conditions, finite sample guarantees can be derived for our procedure. These resolve some open questions and expand existing results in spectral estimation literature.
Tasks	Super-Resolution
Published	2016-10-30
URL	http://arxiv.org/abs/1610.09600v7
PDF	http://arxiv.org/pdf/1610.09600v7.pdf
PWC	https://paperswithcode.com/paper/super-resolution-estimation-of-cyclic-arrival
Repo
Framework

Short-term prediction of localized cloud motion using ground-based sky imagers


Title	Short-term prediction of localized cloud motion using ground-based sky imagers
Authors	Soumyabrata Dev, Florian M. Savoy, Yee Hui Lee, Stefan Winkler
Abstract	Fine-scale short-term cloud motion prediction is needed for several applications, including solar energy generation and satellite communications. In tropical regions such as Singapore, clouds are mostly formed by convection; they are very localized, and evolve quickly. We capture hemispherical images of the sky at regular intervals of time using ground-based cameras. They provide a high resolution and localized cloud images. We use two successive frames to compute optical flow and predict the future location of clouds. We achieve good prediction accuracy for a lead time of up to 5 minutes.
Tasks	motion prediction, Optical Flow Estimation
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06666v1
PDF	http://arxiv.org/pdf/1610.06666v1.pdf
PWC	https://paperswithcode.com/paper/short-term-prediction-of-localized-cloud
Repo
Framework

Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models


Title	Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models
Authors	Daniel P. Robinson, Suchi Saria
Abstract	Predictive models are finding an increasing number of applications in many industries. As a result, a practical means for trading-off the cost of deploying a model versus its effectiveness is needed. Our work is motivated by risk prediction problems in healthcare. Cost-structures in domains such as healthcare are quite complex, posing a significant challenge to existing approaches. We propose a novel framework for designing cost-sensitive structured regularizers that is suitable for problems with complex cost dependencies. We draw upon a surprising connection to boolean circuits. In particular, we represent the problem costs as a multi-layer boolean circuit, and then use properties of boolean circuits to define an extended feature vector and a group regularizer that exactly captures the underlying cost structure. The resulting regularizer may then be combined with a fidelity function to perform model prediction, for example. For the challenging real-world application of risk prediction for sepsis in intensive care units, the use of our regularizer leads to models that are in harmony with the underlying cost structure and thus provide an excellent prediction accuracy versus cost tradeoff.
Tasks
Published	2016-04-20
URL	http://arxiv.org/abs/1604.05819v1
PDF	http://arxiv.org/pdf/1604.05819v1.pdf
PWC	https://paperswithcode.com/paper/trading-off-cost-of-deployment-versus
Repo
Framework

Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation


Title	Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation
Authors	Taehwan Kim, Weiran Wang, Hao Tang, Karen Livescu
Abstract	We study the problem of recognition of fingerspelled letter sequences in American Sign Language in a signer-independent setting. Fingerspelled sequences are both challenging and important to recognize, as they are used for many content words such as proper nouns and technical terms. Previous work has shown that it is possible to achieve almost 90% accuracies on fingerspelling recognition in a signer-dependent setting. However, the more realistic signer-independent setting presents challenges due to significant variations among signers, coupled with the dearth of available training data. We investigate this problem with approaches inspired by automatic speech recognition. We start with the best-performing approaches from prior work, based on tandem models and segmental conditional random fields (SCRFs), with features based on deep neural network (DNN) classifiers of letters and phonological features. Using DNN adaptation, we find that it is possible to bridge a large part of the gap between signer-dependent and signer-independent performance. Using only about 115 transcribed words for adaptation from the target signer, we obtain letter accuracies of up to 82.7% with frame-level adaptation labels and 69.7% with only word labels.
Tasks	Speech Recognition
Published	2016-02-13
URL	http://arxiv.org/abs/1602.04278v1
PDF	http://arxiv.org/pdf/1602.04278v1.pdf
PWC	https://paperswithcode.com/paper/signer-independent-fingerspelling-recognition
Repo
Framework

Decision Tree Classification with Differential Privacy: A Survey


Title	Decision Tree Classification with Differential Privacy: A Survey
Authors	Sam Fletcher, Md Zahidul Islam
Abstract	Data mining information about people is becoming increasingly important in the data-driven society of the 21st century. Unfortunately, sometimes there are real-world considerations that conflict with the goals of data mining; sometimes the privacy of the people being data mined needs to be considered. This necessitates that the output of data mining algorithms be modified to preserve privacy while simultaneously not ruining the predictive power of the outputted model. Differential privacy is a strong, enforceable definition of privacy that can be used in data mining algorithms, guaranteeing that nothing will be learned about the people in the data that could not already be discovered without their participation. In this survey, we focus on one particular data mining algorithm – decision trees – and how differential privacy interacts with each of the components that constitute decision tree algorithms. We analyze both greedy and random decision trees, and the conflicts that arise when trying to balance privacy requirements with the accuracy of the model.
Tasks
Published	2016-11-07
URL	https://arxiv.org/abs/1611.01919v2
PDF	https://arxiv.org/pdf/1611.01919v2.pdf
PWC	https://paperswithcode.com/paper/decision-tree-classification-with
Repo
Framework

Rapid building detection using machine learning


Title	Rapid building detection using machine learning
Authors	Joseph Paul Cohen, Wei Ding, Caitlin Kuhlman, Aijun Chen, Liping Di
Abstract	This work describes algorithms for performing discrete object detection, specifically in the case of buildings, where usually only low quality RGB-only geospatial reflective imagery is available. We utilize new candidate search and feature extraction techniques to reduce the problem to a machine learning (ML) classification task. Here we can harness the complex patterns of contrast features contained in training data to establish a model of buildings. We avoid costly sliding windows to generate candidates; instead we innovatively stitch together well known image processing techniques to produce candidates for building detection that cover 80-85% of buildings. Reducing the number of possible candidates is important due to the scale of the problem. Each candidate is subjected to classification which, although linear, costs time and prohibits large scale evaluation. We propose a candidate alignment algorithm to boost classification performance to 80-90% precision with a linear time algorithm and show it has negligible cost. Also, we propose a new concept called a Permutable Haar Mesh (PHM) which we use to form and traverse a search space to recover candidate buildings which were lost in the initial preprocessing phase.
Tasks	Object Detection
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04392v1
PDF	http://arxiv.org/pdf/1603.04392v1.pdf
PWC	https://paperswithcode.com/paper/rapid-building-detection-using-machine
Repo
Framework

Negative Learning Rates and P-Learning


Title	Negative Learning Rates and P-Learning
Authors	Devon Merrill
Abstract	We present a method of training a differentiable function approximator for a regression task using negative examples. We effect this training using negative learning rates. We also show how this method can be used to perform direct policy learning in a reinforcement learning setting.
Tasks
Published	2016-03-27
URL	http://arxiv.org/abs/1603.08253v3
PDF	http://arxiv.org/pdf/1603.08253v3.pdf
PWC	https://paperswithcode.com/paper/negative-learning-rates-and-p-learning
Repo
Framework