May 6, 2019

2784 words 14 mins read

Paper Group ANR 430

Network Structure Inference, A Survey: Motivations, Methods, and Applications. Strategies for Searching Video Content with Text Queries or Video Examples. Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures. Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain …

Network Structure Inference, A Survey: Motivations, Methods, and Applications


Title	Network Structure Inference, A Survey: Motivations, Methods, and Applications
Authors	Ivan Brugere, Brian Gallagher, Tanya Y. Berger-Wolf
Abstract	Networks represent relationships between entities in many complex systems, spanning from online social interactions to biological cell development and brain connectivity. In many cases, relationships between entities are unambiguously known: are two users ‘friends’ in a social network? Do two researchers collaborate on a published paper? Do two road segments in a transportation system intersect? These are directly observable in the system in question. In most cases, relationship between nodes are not directly observable and must be inferred: does one gene regulate the expression of another? Do two animals who physically co-locate have a social bond? Who infected whom in a disease outbreak in a population? Existing approaches for inferring networks from data are found across many application domains and use specialized knowledge to infer and measure the quality of inferred network for a specific task or hypothesis. However, current research lacks a rigorous methodology which employs standard statistical validation on inferred models. In this survey, we examine (1) how network representations are constructed from underlying data, (2) the variety of questions and tasks on these representations over several domains, and (3) validation strategies for measuring the inferred network’s capability of answering questions on the system of interest.
Tasks
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00782v4
PDF	http://arxiv.org/pdf/1610.00782v4.pdf
PWC	https://paperswithcode.com/paper/network-structure-inference-a-survey
Repo
Framework

Strategies for Searching Video Content with Text Queries or Video Examples


Title	Strategies for Searching Video Content with Text Queries or Video Examples
Authors	Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang
Abstract	The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking. We present novel strategies in these topics to enhance CBVR in both accuracy and speed under different query inputs, including pure textual queries and query by video examples. Our proposed strategies have been incorporated into our submission for the TRECVID 2014 Multimedia Event Detection evaluation, where our system outperformed other submissions in both text queries and video example queries, thus demonstrating the effectiveness of our proposed approaches.
Tasks	Video Retrieval
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05705v1
PDF	http://arxiv.org/pdf/1606.05705v1.pdf
PWC	https://paperswithcode.com/paper/strategies-for-searching-video-content-with
Repo
Framework

Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures


Title	Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures
Authors	Ryo Yonetani, Kris M. Kitani, Yoichi Sato
Abstract	We envision a future time when wearable cameras are worn by the masses and recording first-person point-of-view videos of everyday life. While these cameras can enable new assistive technologies and novel research challenges, they also raise serious privacy concerns. For example, first-person videos passively recorded by wearable cameras will necessarily include anyone who comes into the view of a camera – with or without consent. Motivated by these benefits and risks, we developed a self-search technique tailored to first-person videos. The key observation of our work is that the egocentric head motion of a target person (ie, the self) is observed both in the point-of-view video of the target and observer. The motion correlation between the target person’s video and the observer’s video can then be used to identify instances of the self uniquely. We incorporate this feature into the proposed approach that computes the motion correlation over densely-sampled trajectories to search for a target individual in observer videos. Our approach significantly improves self-search performance over several well-known face detectors and recognizers. Furthermore, we show how our approach can enable several practical applications such as privacy filtering, target video retrieval, and social group clustering.
Tasks	Video Retrieval
Published	2016-06-15
URL	http://arxiv.org/abs/1606.04637v2
PDF	http://arxiv.org/pdf/1606.04637v2.pdf
PWC	https://paperswithcode.com/paper/ego-surfing-person-localization-in-first
Repo
Framework

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging


Title	Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging
Authors	Rui Liu, Hossein Nejati, Seyed Hamid Safavi, Ngai-Man Cheung
Abstract	We propose an algorithm to uncover the intrinsic low-rank component of a high-dimensional, graph-smooth and grossly-corrupted dataset, under the situations that the underlying graph is unknown. Based on a model with a low-rank component plus a sparse perturbation, and an initial graph estimation, our proposed algorithm simultaneously learns the low-rank component and refines the graph. Our evaluations using synthetic and real brain imaging data in unsupervised and supervised classification tasks demonstrate encouraging performance.
Tasks
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08221v2
PDF	http://arxiv.org/pdf/1609.08221v2.pdf
PWC	https://paperswithcode.com/paper/simultaneous-low-rank-component-and-graph
Repo
Framework

The empirical size of trained neural networks


Title	The empirical size of trained neural networks
Authors	Kevin K. Chen, Anthony Gamst, Alden Walker
Abstract	ReLU neural networks define piecewise linear functions of their inputs. However, initializing and training a neural network is very different from fitting a linear spline. In this paper, we expand empirically upon previous theoretical work to demonstrate features of trained neural networks. Standard network initialization and training produce networks vastly simpler than a naive parameter count would suggest and can impart odd features to the trained network. However, we also show the forced simplicity is beneficial and, indeed, critical for the wide success of these networks.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09444v1
PDF	http://arxiv.org/pdf/1611.09444v1.pdf
PWC	https://paperswithcode.com/paper/the-empirical-size-of-trained-neural-networks
Repo
Framework

Robust and Scalable Column/Row Sampling from Corrupted Big Data


Title	Robust and Scalable Column/Row Sampling from Corrupted Big Data
Authors	Mostafa Rahmani, George Atia
Abstract	Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily. In this paper, we present new sampling algorithms which can locate the informative columns in presence of severe data corruptions. In addition, we develop new scalable randomized designs of the proposed algorithms. The proposed approach is simultaneously robust to sparse corruption and outliers and substantially outperforms the state-of-the-art robust sampling algorithms as demonstrated by experiments conducted using both real and synthetic data.
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.05977v1
PDF	http://arxiv.org/pdf/1611.05977v1.pdf
PWC	https://paperswithcode.com/paper/robust-and-scalable-columnrow-sampling-from
Repo
Framework

Audio Visual Speech Recognition using Deep Recurrent Neural Networks


Title	Audio Visual Speech Recognition using Deep Recurrent Neural Networks
Authors	Abhinav Thanda, Shankar M Venkatesan
Abstract	In this work, we propose a training algorithm for an audio-visual automatic speech recognition (AV-ASR) system using deep recurrent neural network (RNN).First, we train a deep RNN acoustic model with a Connectionist Temporal Classification (CTC) objective function. The frame labels obtained from the acoustic model are then used to perform a non-linear dimensionality reduction of the visual features using a deep bottleneck network. Audio and visual features are fused and used to train a fusion RNN. The use of bottleneck features for visual modality helps the model to converge properly during training. Our system is evaluated on GRID corpus. Our results show that presence of visual modality gives significant improvement in character error rate (CER) at various levels of noise even when the model is trained without noisy data. We also provide a comparison of two fusion methods: feature fusion and decision fusion.
Tasks	Audio-Visual Speech Recognition, Dimensionality Reduction, Speech Recognition, Visual Speech Recognition
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02879v1
PDF	http://arxiv.org/pdf/1611.02879v1.pdf
PWC	https://paperswithcode.com/paper/audio-visual-speech-recognition-using-deep
Repo
Framework

Input Switched Affine Networks: An RNN Architecture Designed for Interpretability


Title	Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
Authors	Jakob N. Foerster, Justin Gilmer, Jan Chorowski, Jascha Sohl-Dickstein, David Sussillo
Abstract	There exist many problem domains where the interpretability of neural network models is essential for deployment. Here we introduce a recurrent architecture composed of input-switched affine transformations - in other words an RNN without any explicit nonlinearities, but with input-dependent recurrent weights. This simple form allows the RNN to be analyzed via straightforward linear methods: we can exactly characterize the linear contribution of each input to the model predictions; we can use a change-of-basis to disentangle input, output, and computational hidden unit subspaces; we can fully reverse-engineer the architecture’s solution to a simple task. Despite this ease of interpretation, the input switched affine network achieves reasonable performance on a text modeling tasks, and allows greater computational efficiency than networks with standard nonlinearities.
Tasks
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09434v2
PDF	http://arxiv.org/pdf/1611.09434v2.pdf
PWC	https://paperswithcode.com/paper/input-switched-affine-networks-an-rnn
Repo
Framework

Correlation-based Intrinsic Evaluation of Word Vector Representations


Title	Correlation-based Intrinsic Evaluation of Word Vector Representations
Authors	Yulia Tsvetkov, Manaal Faruqui, Chris Dyer
Abstract	We introduce QVEC-CCA–an intrinsic evaluation metric for word vector representations based on correlations of learned vectors with features extracted from linguistic resources. We show that QVEC-CCA scores are an effective proxy for a range of extrinsic semantic and syntactic tasks. We also show that the proposed evaluation obtains higher and more consistent correlations with downstream tasks, compared to existing approaches to intrinsic evaluation of word vectors that are based on word similarity.
Tasks
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06710v1
PDF	http://arxiv.org/pdf/1606.06710v1.pdf
PWC	https://paperswithcode.com/paper/correlation-based-intrinsic-evaluation-of
Repo
Framework

Orthogonal Echo State Networks and stochastic evaluations of likelihoods


Title	Orthogonal Echo State Networks and stochastic evaluations of likelihoods
Authors	Norbert Michael Mayer, Ying-Hao Yu
Abstract	We report about probabilistic likelihood estimates that are performed on time series using an echo state network with orthogonal recurrent connectivity. The results from tests using synthetic stochastic input time series with temporal inference indicate that the capability of the network to infer depends on the balance between input strength and recurrent activity. This balance has an influence on the network with regard to the quality of inference from the short term input history versus inference that accounts for influences that date back a long time. Sensitivity of such networks against noise and the finite accuracy of network states in the recurrent layer are investigated. In addition, a measure based on mutual information between the output time series and the reservoir is introduced. Finally, different types of recurrent connectivity are evaluated. Orthogonal matrices show the best results of all investigated connectivity types overall, but also in the way how the network performance scales with the size of the recurrent layer.
Tasks	Time Series
Published	2016-01-22
URL	http://arxiv.org/abs/1601.05911v5
PDF	http://arxiv.org/pdf/1601.05911v5.pdf
PWC	https://paperswithcode.com/paper/orthogonal-echo-state-networks-and-stochastic
Repo
Framework

A Survey on Object Detection in Optical Remote Sensing Images


Title	A Survey on Object Detection in Optical Remote Sensing Images
Authors	Gong Cheng, Junwei Han
Abstract	Object detection in optical remote sensing images, being a fundamental but challenging problem in the field of aerial and satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. While enormous methods exist, a deep review of the literature concerning generic object detection is still lacking. This paper aims to provide a review of the recent progress in this field. Different from several previously published surveys that focus on a specific object class such as building and road, we concentrate on more generic object categories including, but are not limited to, road, building, tree, vehicle, ship, airport, urban-area. Covering about 270 publications we survey 1) template matching-based object detection methods, 2) knowledge-based object detection methods, 3) object-based image analysis (OBIA)-based object detection methods, 4) machine learning-based object detection methods, and 5) five publicly available datasets and three standard evaluation metrics. We also discuss the challenges of current studies and propose two promising research directions, namely deep learning-based feature representation and weakly supervised learning-based geospatial object detection. It is our hope that this survey will be beneficial for the researchers to have better understanding of this research field.
Tasks	Object Detection
Published	2016-03-20
URL	http://arxiv.org/abs/1603.06201v2
PDF	http://arxiv.org/pdf/1603.06201v2.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-object-detection-in-optical
Repo
Framework

Variational reaction-diffusion systems for semantic segmentation


Title	Variational reaction-diffusion systems for semantic segmentation
Authors	Paul Vernaza
Abstract	A novel global energy model for multi-class semantic image segmentation is proposed that admits very efficient exact inference and derivative calculations for learning. Inference in this model is equivalent to MAP inference in a particular kind of vector-valued Gaussian Markov random field, and ultimately reduces to solving a linear system of linear PDEs known as a reaction-diffusion system. Solving this system can be achieved in time scaling near-linearly in the number of image pixels by reducing it to sequential FFTs, after a linear change of basis. The efficiency and differentiability of the model make it especially well-suited for integration with convolutional neural networks, even allowing it to be used in interior, feature-generating layers and stacked multiple times. Experimental results are shown demonstrating that the model can be employed profitably in conjunction with different convolutional net architectures, and that doing so compares favorably to joint training of a fully-connected CRF with a convolutional net.
Tasks	Semantic Segmentation
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00092v1
PDF	http://arxiv.org/pdf/1604.00092v1.pdf
PWC	https://paperswithcode.com/paper/variational-reaction-diffusion-systems-for
Repo
Framework

A Strongly Quasiconvex PAC-Bayesian Bound


Title	A Strongly Quasiconvex PAC-Bayesian Bound
Authors	Niklas Thiemann, Christian Igel, Olivier Wintenberger, Yevgeny Seldin
Abstract	We propose a new PAC-Bayesian bound and a way of constructing a hypothesis space, so that the bound is convex in the posterior distribution and also convex in a trade-off parameter between empirical performance of the posterior distribution and its complexity. The complexity is measured by the Kullback-Leibler divergence to a prior. We derive an alternating procedure for minimizing the bound. We show that the bound can be rewritten as a one-dimensional function of the trade-off parameter and provide sufficient conditions under which the function has a single global minimum. When the conditions are satisfied the alternating minimization is guaranteed to converge to the global minimum of the bound. We provide experimental results demonstrating that rigorous minimization of the bound is competitive with cross-validation in tuning the trade-off between complexity and empirical performance. In all our experiments the trade-off turned to be quasiconvex even when the sufficient conditions were violated.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05610v2
PDF	http://arxiv.org/pdf/1608.05610v2.pdf
PWC	https://paperswithcode.com/paper/a-strongly-quasiconvex-pac-bayesian-bound
Repo
Framework

Formulating Semantics of Probabilistic Argumentation by Characterizing Subgraphs: Theory and Empirical Results


Title	Formulating Semantics of Probabilistic Argumentation by Characterizing Subgraphs: Theory and Empirical Results
Authors	Beishui Liao, Kang Xu, Huaxin Huang
Abstract	In existing literature, while approximate approaches based on Monte-Carlo simulation technique have been proposed to compute the semantics of probabilistic argumentation, how to improve the efficiency of computation without using simulation technique is still an open problem. In this paper, we address this problem from the following two perspectives. First, conceptually, we define specific properties to characterize the subgraphs of a PrAG with respect to a given extension, such that the probability of a set of arguments E being an extension can be defined in terms of these properties, without (or with less) construction of subgraphs. Second, computationally, we take preferred semantics as an example, and develop algorithms to evaluate the efficiency of our approach. The results show that our approach not only dramatically decreases the time for computing p(E^\sigma), but also has an attractive property, which is contrary to that of existing approaches: the denser the edges of a PrAG are or the bigger the size of a given extension E is, the more efficient our approach computes p(E^\sigma). Meanwhile, it is shown that under complete and preferred semantics, the problems of determining p(E^\sigma) are fixed-parameter tractable.
Tasks
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00302v2
PDF	http://arxiv.org/pdf/1608.00302v2.pdf
PWC	https://paperswithcode.com/paper/formulating-semantics-of-probabilistic
Repo
Framework

Generic 3D Convolutional Fusion for image restoration


Title	Generic 3D Convolutional Fusion for image restoration
Authors	Jiqing Wu, Radu Timofte, Luc Van Gool
Abstract	Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations and assumptions, so even if their average performance may be similar, some work better on certain image types and image regions than others. This complementarity motivated us to propose a novel 3D convolutional fusion (3DCF) method. Unlike other methods adapted to different tasks, our method uses the exact same convolutional network architecture to address both image denois- ing and single image super-resolution. As a result, our 3DCF method achieves substantial improvements (0.1dB-0.4dB PSNR) over the state-of-the-art methods that it fuses, and this on standard benchmarks for both tasks. At the same time, the method still is computationally efficient.
Tasks	Denoising, Image Denoising, Image Restoration, Image Super-Resolution, Super-Resolution
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07561v1
PDF	http://arxiv.org/pdf/1607.07561v1.pdf
PWC	https://paperswithcode.com/paper/generic-3d-convolutional-fusion-for-image
Repo
Framework