May 7, 2019

3137 words 15 mins read

Paper Group AWR 17

Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters. TeKnowbase: Towards Construction of a Knowledge-base of Technical Concepts. This before That: Causal Precedence in the Biomedical Domain. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. Multi-Scale Convolutional Neural Networks for Time Se …

Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters


Title	Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
Authors	AJ Piergiovanni, Chenyou Fan, Michael S. Ryoo
Abstract	In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g., sub-events) with different duration/speed, and our objective is to make the model explicitly learn such temporal structure using multiple attention filters and benefit from them. Our temporal filters are designed to be fully differentiable, allowing end-of-end training of the temporal filters together with the underlying frame-based or segment-based convolutional neural network architectures. This paper presents an approach of learning a set of optimal static temporal attention filters to be shared across different videos, and extends this approach to dynamically adjust attention filters per testing video using recurrent long short-term memory networks (LSTMs). This allows our temporal attention filters to learn latent sub-events specific to each activity. We experimentally confirm that the proposed concept of temporal attention filters benefits the activity recognition, and we visualize the learned latent sub-events.
Tasks	Action Classification, Activity Recognition, Human Activity Recognition
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08140v3
PDF	http://arxiv.org/pdf/1605.08140v3.pdf
PWC	https://paperswithcode.com/paper/learning-latent-sub-events-in-activity-videos
Repo	https://github.com/piergiaj/latent-subevents
Framework	none

TeKnowbase: Towards Construction of a Knowledge-base of Technical Concepts


Title	TeKnowbase: Towards Construction of a Knowledge-base of Technical Concepts
Authors	Prajna Upadhyay, Tanuma Patra, Ashwini Purkar, Maya Ramanath
Abstract	In this paper, we describe the construction of TeKnowbase, a knowledge-base of technical concepts in computer science. Our main information sources are technical websites such as Webopedia and Techtarget as well as Wikipedia and online textbooks. We divide the knowledge-base construction problem into two parts – the acquisition of entities and the extraction of relationships among these entities. Our knowledge-base consists of approximately 100,000 triples. We conducted an evaluation on a sample of triples and report an accuracy of a little over 90%. We additionally conducted classification experiments on StackOverflow data with features from TeKnowbase and achieved improved classification accuracy.
Tasks
Published	2016-12-15
URL	http://arxiv.org/abs/1612.04988v1
PDF	http://arxiv.org/pdf/1612.04988v1.pdf
PWC	https://paperswithcode.com/paper/teknowbase-towards-construction-of-a
Repo	https://github.com/prajnaupadhyay/TeKnowbase
Framework	none

This before That: Causal Precedence in the Biomedical Domain


Title	This before That: Causal Precedence in the Biomedical Domain
Authors	Gus Hahn-Powell, Dane Bell, Marco A. Valenzuela-Escárcega, Mihai Surdeanu
Abstract	Causal precedence between biochemical interactions is crucial in the biomedical domain, because it transforms collections of individual interactions, e.g., bindings and phosphorylations, into the causal mechanisms needed to inform meaningful search and inference. Here, we analyze causal precedence in the biomedical domain as distinct from open-domain, temporal precedence. First, we describe a novel, hand-annotated text corpus of causal precedence in the biomedical domain. Second, we use this corpus to investigate a battery of models of precedence, covering rule-based, feature-based, and latent representation models. The highest-performing individual model achieved a micro F1 of 43 points, approaching the best performers on the simpler temporal-only precedence tasks. Feature-based and latent representation models each outperform the rule-based models, but their performance is complementary to one another. We apply a sieve-based architecture to capitalize on this lack of overlap, achieving a micro F1 score of 46 points.
Tasks
Published	2016-06-26
URL	http://arxiv.org/abs/1606.08089v1
PDF	http://arxiv.org/pdf/1606.08089v1.pdf
PWC	https://paperswithcode.com/paper/this-before-that-causal-precedence-in-the
Repo	https://github.com/clulab/reach
Framework	none

ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras


Title	ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
Authors	Raul Mur-Artal, Juan D. Tardos
Abstract	We present ORB-SLAM2 a complete SLAM system for monocular, stereo and RGB-D cameras, including map reuse, loop closing and relocalization capabilities. The system works in real-time on standard CPUs in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end based on bundle adjustment with monocular and stereo observations allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches to map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.
Tasks	Simultaneous Localization and Mapping, Visual Odometry
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06475v2
PDF	http://arxiv.org/pdf/1610.06475v2.pdf
PWC	https://paperswithcode.com/paper/orb-slam2-an-open-source-slam-system-for
Repo	https://github.com/m1234d/build18
Framework	none

Multi-Scale Convolutional Neural Networks for Time Series Classification


Title	Multi-Scale Convolutional Neural Networks for Time Series Classification
Authors	Zhicheng Cui, Wenlin Chen, Yixin Chen
Abstract	Time series classification (TSC), the problem of predicting class labels of time series, has been around for decades within the community of data mining and machine learning, and found many important applications such as biomedical engineering and clinical prediction. However, it still remains challenging and falls short of classification accuracy and efficiency. Traditional approaches typically involve extracting discriminative features from the original time series using dynamic time warping (DTW) or shapelet transformation, based on which an off-the-shelf classifier can be applied. These methods are ad-hoc and separate the feature extraction part with the classification part, which limits their accuracy performance. Plus, most existing methods fail to take into account the fact that time series often have features at different time scales. To address these problems, we propose a novel end-to-end neural network model, Multi-Scale Convolutional Neural Networks (MCNN), which incorporates feature extraction and classification in a single framework. Leveraging a novel multi-branch layer and learnable convolutional layers, MCNN automatically extracts features at different scales and frequencies, leading to superior feature representation. MCNN is also computationally efficient, as it naturally leverages GPU computing. We conduct comprehensive empirical evaluation with various existing methods on a large number of benchmark datasets, and show that MCNN advances the state-of-the-art by achieving superior accuracy performance than other leading methods.
Tasks	Time Series, Time Series Classification
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06995v4
PDF	http://arxiv.org/pdf/1603.06995v4.pdf
PWC	https://paperswithcode.com/paper/multi-scale-convolutional-neural-networks-for
Repo	https://github.com/zdcuob/Fully-Convlutional-Neural-Networks-for-state-of-the-art-time-series-classification-
Framework	tf

Neural Network Translation Models for Grammatical Error Correction


Title	Neural Network Translation Models for Grammatical Error Correction
Authors	Shamil Chollampatt, Kaveh Taghipour, Hwee Tou Ng
Abstract	Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn text transformations from erroneous to corrected text, without explicitly modeling error types. However, phrase-based SMT systems suffer from limitations of discrete word representation, linear mapping, and lack of global context. In this paper, we address these limitations by using two different yet complementary neural network models, namely a neural network global lexicon model and a neural network joint model. These neural networks can generalize better by using continuous space representation of words and learn non-linear mappings. Moreover, they can leverage contextual information from the source sentence more effectively. By adding these two components, we achieve statistically significant improvement in accuracy for grammatical error correction over a state-of-the-art GEC system.
Tasks	Grammatical Error Correction, Machine Translation
Published	2016-06-01
URL	http://arxiv.org/abs/1606.00189v1
PDF	http://arxiv.org/pdf/1606.00189v1.pdf
PWC	https://paperswithcode.com/paper/neural-network-translation-models-for
Repo	https://github.com/seaweiqing/image2story
Framework	tf

Iterative Gaussianization: from ICA to Random Rotations


Title	Iterative Gaussianization: from ICA to Random Rotations
Authors	Valero Laparra, Gustavo Camps-Valls, Jesús Malo
Abstract	Most signal processing problems involve the challenging task of multidimensional probability density function (PDF) estimation. In this work, we propose a solution to this problem by using a family of Rotation-based Iterative Gaussianization (RBIG) transforms. The general framework consists of the sequential application of a univariate marginal Gaussianization transform followed by an orthonormal transform. The proposed procedure looks for differentiable transforms to a known PDF so that the unknown PDF can be estimated at any point of the original domain. In particular, we aim at a zero mean unit covariance Gaussian for convenience. RBIG is formally similar to classical iterative Projection Pursuit (PP) algorithms. However, we show that, unlike in PP methods, the particular class of rotations used has no special qualitative relevance in this context, since looking for interestingness is not a critical issue for PDF estimation. The key difference is that our approach focuses on the univariate part (marginal Gaussianization) of the problem rather than on the multivariate part (rotation). This difference implies that one may select the most convenient rotation suited to each practical application. The differentiability, invertibility and convergence of RBIG are theoretically and experimentally analyzed. Relation to other methods, such as Radial Gaussianization (RG), one-class support vector domain description (SVDD), and deep neural networks (DNN) is also pointed out. The practical performance of RBIG is successfully illustrated in a number of multidimensional problems such as image synthesis, classification, denoising, and multi-information estimation.
Tasks	Denoising, Image Generation
Published	2016-01-31
URL	http://arxiv.org/abs/1602.00229v1
PDF	http://arxiv.org/pdf/1602.00229v1.pdf
PWC	https://paperswithcode.com/paper/iterative-gaussianization-from-ica-to-random
Repo	https://github.com/jejjohnson/rbig
Framework	none

Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation


Title	Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
Authors	Konstantinos Kamnitsas, Christian Ledig, Virginia F. J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Daniel Rueckert, Ben Glocker
Abstract	We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation. The devised architecture is the result of an in-depth analysis of the limitations of current networks proposed for similar applications. To overcome the computational burden of processing 3D medical scans, we have devised an efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data. Further, we analyze the development of deeper, thus more discriminative 3D CNNs. In order to incorporate both local and larger contextual information, we employ a dual pathway architecture that processes the input images at multiple scales simultaneously. For post-processing of the network’s soft segmentation, we use a 3D fully connected Conditional Random Field which effectively removes false positives. Our pipeline is extensively evaluated on three challenging tasks of lesion segmentation in multi-channel MRI patient data with traumatic brain injuries, brain tumors, and ischemic stroke. We improve on the state-of-the-art for all three applications, with top ranking performance on the public benchmarks BRATS 2015 and ISLES 2015. Our method is computationally efficient, which allows its adoption in a variety of research and clinical settings. The source code of our implementation is made publicly available.
Tasks	3D Medical Imaging Segmentation, Brain Lesion Segmentation From Mri, Brain Tumor Segmentation, Lesion Segmentation, Medical Image Segmentation
Published	2016-03-18
URL	http://arxiv.org/abs/1603.05959v3
PDF	http://arxiv.org/pdf/1603.05959v3.pdf
PWC	https://paperswithcode.com/paper/efficient-multi-scale-3d-cnn-with-fully
Repo	https://github.com/etjoa003/medical_imaging
Framework	none

EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces


Title	EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces
Authors	Vernon J. Lawhern, Amelia J. Solon, Nicholas R. Waytowich, Stephen M. Gordon, Chou P. Hung, Brent J. Lance
Abstract	Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional Neural Networks (CNNs), which have been used in computer vision and speech recognition, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. In this work we introduce EEGNet, a compact convolutional network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). We show that EEGNet generalizes across paradigms better than the reference algorithms when only limited training data is available. We demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks, suggesting that the observed performances were not due to artifact or noise sources in the data.
Tasks	EEG
Published	2016-11-23
URL	http://arxiv.org/abs/1611.08024v4
PDF	http://arxiv.org/pdf/1611.08024v4.pdf
PWC	https://paperswithcode.com/paper/eegnet-a-compact-convolutional-network-for
Repo	https://github.com/aliasvishnu/EEGNet
Framework	pytorch

Inferring solutions of differential equations using noisy multi-fidelity data


Title	Inferring solutions of differential equations using noisy multi-fidelity data
Authors	Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
Abstract	For more than two centuries, solutions of differential equations have been obtained either analytically or numerically based on typically well-behaved forcing and boundary conditions for well-posed problems. We are changing this paradigm in a fundamental way by establishing an interface between probabilistic machine learning and differential equations. We develop data-driven algorithms for general linear equations using Gaussian process priors tailored to the corresponding integro-differential operators. The only observables are scarce noisy multi-fidelity data for the forcing and solution that are not required to reside on the domain boundary. The resulting predictive posterior distributions quantify uncertainty and naturally lead to adaptive solution refinement via active learning. This general framework circumvents the tyranny of numerical discretization as well as the consistency and stability issues of time-integration, and is scalable to high-dimensions.
Tasks	Active Learning
Published	2016-07-16
URL	http://arxiv.org/abs/1607.04805v1
PDF	http://arxiv.org/pdf/1607.04805v1.pdf
PWC	https://paperswithcode.com/paper/inferring-solutions-of-differential-equations
Repo	https://github.com/maziarraissi/TutorialGP
Framework	none

Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations


Title	Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
Authors	Eliyahu Kiperwasser, Yoav Goldberg
Abstract	We present a simple and effective scheme for dependency parsing which is based on bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector representing the token in its sentential context, and feature vectors are constructed by concatenating a few BiLSTM vectors. The BiLSTM is trained jointly with the parser objective, resulting in very effective feature extractors for parsing. We demonstrate the effectiveness of the approach by applying it to a greedy transition-based parser as well as to a globally optimized graph-based parser. The resulting parsers have very simple architectures, and match or surpass the state-of-the-art accuracies on English and Chinese.
Tasks	Dependency Parsing
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04351v3
PDF	http://arxiv.org/pdf/1603.04351v3.pdf
PWC	https://paperswithcode.com/paper/simple-and-accurate-dependency-parsing-using
Repo	https://github.com/ITUnlp/UniParse
Framework	none

Multispectral Deep Neural Networks for Pedestrian Detection


Title	Multispectral Deep Neural Networks for Pedestrian Detection
Authors	Jingjing Liu, Shaoting Zhang, Shu Wang, Dimitris N. Metaxas
Abstract	Multispectral pedestrian detection is essential for around-the-clock applications, e.g., surveillance and autonomous driving. We deeply analyze Faster R-CNN for multispectral pedestrian detection task and then model it into a convolutional network (ConvNet) fusion problem. Further, we discover that ConvNet-based pedestrian detectors trained by color or thermal images separately provide complementary information in discriminating human instances. Thus there is a large potential to improve pedestrian detection by using color and thermal images in DNNs simultaneously. We carefully design four ConvNet fusion architectures that integrate two-branch ConvNets on different DNNs stages, all of which yield better performance compared with the baseline detector. Our experimental results on KAIST pedestrian benchmark show that the Halfway Fusion model that performs fusion on the middle-level convolutional features outperforms the baseline method by 11% and yields a missing rate 3.5% lower than the other proposed architectures.
Tasks	Autonomous Driving, Pedestrian Detection
Published	2016-11-08
URL	http://arxiv.org/abs/1611.02644v1
PDF	http://arxiv.org/pdf/1611.02644v1.pdf
PWC	https://paperswithcode.com/paper/multispectral-deep-neural-networks-for
Repo	https://github.com/SoonminHwang/rgbt-ped-detection
Framework	none

Distraction-Based Neural Networks for Document Summarization


Title	Distraction-Based Neural Networks for Document Summarization
Authors	Qian Chen, Xiaodan Zhu, Zhenhua Ling, Si Wei, Hui Jiang
Abstract	Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to help model larger spans of text, e.g., documents, is intriguing, and further investigation would still be desirable. This paper aims to enhance neural network models for such a purpose. A typical problem of document-level modeling is automatic summarization, which aims to model documents in order to generate summaries. In this paper, we propose neural models to train computers not just to pay attention to specific regions and content of input documents with attention models, but also distract them to traverse between different content of a document so as to better grasp the overall meaning for summarization. Without engineering any features, we train the models on two large datasets. The models achieve the state-of-the-art performance, and they significantly benefit from the distraction modeling, particularly when input documents are long.
Tasks	Document Summarization
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08462v1
PDF	http://arxiv.org/pdf/1610.08462v1.pdf
PWC	https://paperswithcode.com/paper/distraction-based-neural-networks-for
Repo	https://github.com/lukecq1231/nats
Framework	none

Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees


Title	Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees
Authors	Ehsan Shareghi, Matthias Petri, Gholamreza Haffari, Trevor Cohn
Abstract	Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art KenLM package. It imposes much lower memory requirements, often by orders of magnitude, and has runtimes that are either similar (for training) or comparable (for querying).
Tasks	Language Modelling
Published	2016-08-16
URL	http://arxiv.org/abs/1608.04465v1
PDF	http://arxiv.org/pdf/1608.04465v1.pdf
PWC	https://paperswithcode.com/paper/fast-small-and-exact-infinite-order-language
Repo	https://github.com/eehsan/cstlm
Framework	none

An argumentative agent-based model of scientific inquiry


Title	An argumentative agent-based model of scientific inquiry
Authors	Annemarie Borg, Daniel Frey, Dunja Šešelja, Christian Straßer
Abstract	In this paper we present an agent-based model (ABM) of scientific inquiry aimed at investigating how different social networks impact the efficiency of scientists in acquiring knowledge. As such, the ABM is a computational tool for tackling issues in the domain of scientific methodology and science policy. In contrast to existing ABMs of science, our model aims to represent the argumentative dynamics that underlies scientific practice. To this end we employ abstract argumentation theory as the core design feature of the model. This helps to avoid a number of problematic idealizations which are present in other ABMs of science and which impede their relevance for actual scientific practice.
Tasks	Abstract Argumentation
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04432v1
PDF	http://arxiv.org/pdf/1612.04432v1.pdf
PWC	https://paperswithcode.com/paper/an-argumentative-agent-based-model-of
Repo	https://github.com/g4v4g4i/ArgABM
Framework	none