May 5, 2019

2791 words 14 mins read

Paper Group ANR 456

Human Attention Estimation for Natural Images: An Automatic Gaze Refinement Approach. Autoregressive Moving Average Graph Filtering. Embedded Bandits for Large-Scale Black-Box Optimization. Joint Defogging and Demosaicking. Sparse Recovery from Extreme Eigenvalues Deviation Inequalities. Handwriting Profiling using Generative Adversarial Networks. …


Title	Human Attention Estimation for Natural Images: An Automatic Gaze Refinement Approach
Authors	Jinsoo Choi, Tae-Hyun Oh, In So Kweon
Abstract	Photo collections and its applications today attempt to reflect user interactions in various forms. Moreover, photo collections aim to capture the users’ intention with minimum effort through applications capturing user intentions. Human interest regions in an image carry powerful information about the user’s behavior and can be used in many photo applications. Research on human visual attention has been conducted in the form of gaze tracking and computational saliency models in the computer vision community, and has shown considerable progress. This paper presents an integration between implicit gaze estimation and computational saliency model to effectively estimate human attention regions in images on the fly. Furthermore, our method estimates human attention via implicit calibration and incremental model updating without any active participation from the user. We also present extensive analysis and possible applications for personal photo collections.
Tasks	Calibration, Gaze Estimation
Published	2016-01-12
URL	http://arxiv.org/abs/1601.02852v1
PDF	http://arxiv.org/pdf/1601.02852v1.pdf
PWC	https://paperswithcode.com/paper/human-attention-estimation-for-natural-images
Repo
Framework

Autoregressive Moving Average Graph Filtering


Title	Autoregressive Moving Average Graph Filtering
Authors	Elvin Isufi, Andreas Loukas, Andrea Simonetto, Geert Leus
Abstract	One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogues of classical filters, but intended for signals defined on graphs. This work brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which (i) are able to approximate any desired graph frequency response, and (ii) give exact solutions for tasks such as graph signal denoising and interpolation. The design philosophy, which allows us to design the ARMA coefficients independently from the underlying graph, renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph are changing over time. We show that in case of a time-varying graph signal our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domains. We also derive sufficient conditions for filter stability when the graph and signal are time-varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.
Tasks	Denoising
Published	2016-02-14
URL	http://arxiv.org/abs/1602.04436v2
PDF	http://arxiv.org/pdf/1602.04436v2.pdf
PWC	https://paperswithcode.com/paper/autoregressive-moving-average-graph-filtering
Repo
Framework

Embedded Bandits for Large-Scale Black-Box Optimization


Title	Embedded Bandits for Large-Scale Black-Box Optimization
Authors	Abdullah Al-Dujaili, S. Suresh
Abstract	Random embedding has been applied with empirical success to large-scale black-box optimization problems with low effective dimensions. This paper proposes the EmbeddedHunter algorithm, which incorporates the technique in a hierarchical stochastic bandit setting, following the optimism in the face of uncertainty principle and breaking away from the multiple-run framework in which random embedding has been conventionally applied similar to stochastic black-box optimization solvers. Our proposition is motivated by the bounded mean variation in the objective value for a low-dimensional point projected randomly into the decision space of Lipschitz-continuous problems. In essence, the EmbeddedHunter algorithm expands optimistically a partitioning tree over a low-dimensional—equal to the effective dimension of the problem—search space based on a bounded number of random embeddings of sampled points from the low-dimensional space. In contrast to the probabilistic theoretical guarantees of multiple-run random-embedding algorithms, the finite-time analysis of the proposed algorithm presents a theoretical upper bound on the regret as a function of the algorithm’s number of iterations. Furthermore, numerical experiments were conducted to validate its performance. The results show a clear performance gain over recently proposed random embedding methods for large-scale problems, provided the intrinsic dimensionality is low.
Tasks
Published	2016-11-27
URL	http://arxiv.org/abs/1611.08773v1
PDF	http://arxiv.org/pdf/1611.08773v1.pdf
PWC	https://paperswithcode.com/paper/embedded-bandits-for-large-scale-black-box
Repo
Framework

Joint Defogging and Demosaicking


Title	Joint Defogging and Demosaicking
Authors	Y. J. Lee, K. Hirakawa, T. Q. Nguyen
Abstract	Image defogging is a technique used extensively for enhancing visual quality of images in bad weather condition. Even though defogging algorithms have been well studied, defogging performance is degraded by demosaicking artifacts and sensor noise amplification in distant scenes. In order to improve visual quality of restored images, we propose a novel approach to perform defogging and demosaicking simultaneously. We conclude that better defogging performance with fewer artifacts can be achieved when a defogging algorithm is combined with a demosaicking algorithm simultaneously. We also demonstrate that the proposed joint algorithm has the benefit of suppressing noise amplification in distant scene. In addition, we validate our theoretical analysis and observations for both synthesized datasets with ground truth fog-free images and natural scene datasets captured in a raw format.
Tasks	Demosaicking
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02885v1
PDF	http://arxiv.org/pdf/1602.02885v1.pdf
PWC	https://paperswithcode.com/paper/joint-defogging-and-demosaicking
Repo
Framework

Sparse Recovery from Extreme Eigenvalues Deviation Inequalities


Title	Sparse Recovery from Extreme Eigenvalues Deviation Inequalities
Authors	Sandrine Dallaporta, Yohann De Castro
Abstract	This article provides a new toolbox to derive sparse recovery guarantees from small deviations on extreme singular values or extreme eigenvalues obtained in Random Matrix Theory. This work is based on Restricted Isometry Constants (RICs) which are a pivotal notion in Compressed Sensing and High-Dimensional Statistics as these constants finely assess how a linear operator is conditioned on the set of sparse vectors and hence how it performs in SRSR. While it is an open problem to construct deterministic matrices with apposite RICs, one can prove that such matrices exist using random matrices models. In this paper, we show upper bounds on RICs for Gaussian and Rademacher matrices using state-of-the-art small deviation estimates on their extreme eigenvalues. This allows us to derive a lower bound on the probability of getting SRSR. One benefit of this paper is a direct and explicit derivation of upper bounds on RICs and lower bounds on SRSR from small deviations on the extreme eigenvalues given by Random Matrix theory.
Tasks
Published	2016-04-05
URL	http://arxiv.org/abs/1604.01171v4
PDF	http://arxiv.org/pdf/1604.01171v4.pdf
PWC	https://paperswithcode.com/paper/sparse-recovery-from-extreme-eigenvalues
Repo
Framework

Handwriting Profiling using Generative Adversarial Networks


Title	Handwriting Profiling using Generative Adversarial Networks
Authors	Arna Ghosh, Biswarup Bhattacharya, Somnath Basu Roy Chowdhury
Abstract	Handwriting is a skill learned by humans from a very early age. The ability to develop one’s own unique handwriting as well as mimic another person’s handwriting is a task learned by the brain with practice. This paper deals with this very problem where an intelligent system tries to learn the handwriting of an entity using Generative Adversarial Networks (GANs). We propose a modified architecture of DCGAN (Radford, Metz, and Chintala 2015) to achieve this. We also discuss about applying reinforcement learning techniques to achieve faster learning. Our algorithm hopes to give new insights in this area and its uses include identification of forged documents, signature verification, computer generated art, digitization of documents among others. Our early implementation of the algorithm illustrates a good performance with MNIST datasets.
Tasks
Published	2016-11-27
URL	http://arxiv.org/abs/1611.08789v1
PDF	http://arxiv.org/pdf/1611.08789v1.pdf
PWC	https://paperswithcode.com/paper/handwriting-profiling-using-generative
Repo
Framework

Attentional Push: Augmenting Salience with Shared Attention Modeling


Title	Attentional Push: Augmenting Salience with Shared Attention Modeling
Authors	Siavash Gorji, James J. Clark
Abstract	We present a novel visual attention tracking technique based on Shared Attention modeling. Our proposed method models the viewer as a participant in the activity occurring in the scene. We go beyond image salience and instead of only computing the power of an image region to pull attention to it, we also consider the strength with which other regions of the image push attention to the region in question. We use the term Attentional Push to refer to the power of image regions to direct and manipulate the attention allocation of the viewer. An attention model is presented that incorporates the Attentional Push cues with standard image salience-based attention modeling algorithms to improve the ability to predict where viewers will fixate. Experimental evaluation validates significant improvements in predicting viewers’ fixations using the proposed methodology in both static and dynamic imagery.
Tasks
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00072v1
PDF	http://arxiv.org/pdf/1609.00072v1.pdf
PWC	https://paperswithcode.com/paper/attentional-push-augmenting-salience-with
Repo
Framework

How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes


Title	How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes
Authors	Ziad Al-Halah, Rainer Stiefelhagen
Abstract	Attribute based knowledge transfer has proven very successful in visual object analysis and learning previously unseen classes. However, the common approach learns and transfers attributes without taking into consideration the embedded structure between the categories in the source set. Such information provides important cues on the intra-attribute variations. We propose to capture these variations in a hierarchical model that expands the knowledge source with additional abstraction levels of attributes. We also provide a novel transfer approach that can choose the appropriate attributes to be shared with an unseen class. We evaluate our approach on three public datasets: aPascal, Animals with Attributes and CUB-200-2011 Birds. The experiments demonstrate the effectiveness of our model with significant improvement over state-of-the-art.
Tasks	Object Recognition, Transfer Learning
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00326v1
PDF	http://arxiv.org/pdf/1604.00326v1.pdf
PWC	https://paperswithcode.com/paper/how-to-transfer-zero-shot-object-recognition
Repo
Framework

Deep, Dense, and Low-Rank Gaussian Conditional Random Fields


Title	Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
Authors	Siddhartha Chandra, Iasonas Kokkinos
Abstract	In this work we introduce a fully-connected graph structure in the Deep Gaussian Conditional Random Field (G-CRF) model. For this we express the pairwise interactions between pixels as the inner-products of low-dimensional embeddings, delivered by a new subnetwork of a deep architecture. We efficiently minimize the resulting energy by solving the resulting low-rank linear system with conjugate gradients, and derive an analytic expression for the gradient of our embeddings which allows us to train them end-to-end with backpropagation. We demonstrate the merit of our approach by achieving state of the art results on three challenging Computer Vision benchmarks, namely semantic segmentation, human parts segmentation, and saliency estimation. Our implementation is fully GPU based, built on top of the Caffe library, and will be made publicly available.
Tasks	Saliency Prediction, Semantic Segmentation
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09051v1
PDF	http://arxiv.org/pdf/1611.09051v1.pdf
PWC	https://paperswithcode.com/paper/deep-dense-and-low-rank-gaussian-conditional
Repo
Framework

Robust cDNA microarray image segmentation and analysis technique based on Hough circle transform


Title	Robust cDNA microarray image segmentation and analysis technique based on Hough circle transform
Authors	R. M. Farouk, M. A. SayedElahl
Abstract	One of the most challenging tasks in microarray image analysis is spot segmentation. A solution to this problem is to provide an algorithm than can be used to find any spot within the microarray image. Circular Hough Transformation (CHT) is a powerful feature extraction technique used in image analysis, computer vision, and digital image processing. CHT algorithm is applied on the cDNA microarray images to develop the accuracy and the efficiency of the spots localization, addressing and segmentation process. The purpose of the applied technique is to find imperfect instances of spots within a certain class of circles by applying a voting procedure on the cDNA microarray images for spots localization, addressing and characterizing the pixels of each spot into foreground pixels and background simultaneously. Intensive experiments on the University of North Carolina (UNC) microarray database indicate that the proposed method is superior to the K-means method and the Support vector machine (SVM). Keywords: Hough circle transformation, cDNA microarray image analysis, cDNA microarray image segmentation, spots localization and addressing, spots segmentation
Tasks	Semantic Segmentation
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07123v1
PDF	http://arxiv.org/pdf/1603.07123v1.pdf
PWC	https://paperswithcode.com/paper/robust-cdna-microarray-image-segmentation-and
Repo
Framework

A Multi-Scale Cascade Fully Convolutional Network Face Detector


Title	A Multi-Scale Cascade Fully Convolutional Network Face Detector
Authors	Zhenheng Yang, Ram Nevatia
Abstract	Face detection is challenging as faces in images could be present at arbitrary locations and in different scales. We propose a three-stage cascade structure based on fully convolutional neural networks (FCNs). It first proposes the approximate locations where the faces may be, then aims to find the accurate location by zooming on to the faces. Each level of the FCN cascade is a multi-scale fully-convolutional network, which generates scores at different locations and in different scales. A score map is generated after each FCN stage. Probable regions of face are selected and fed to the next stage. The number of proposals is decreased after each level, and the areas of regions are decreased to more precisely fit the face. Compared to passing proposals directly between stages, passing probable regions can decrease the number of proposals and reduce the cases where first stage doesn’t propose good bounding boxes. We show that by using FCN and score map, the FCN cascade face detector can achieve strong performance on public datasets.
Tasks	Face Detection
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03536v1
PDF	http://arxiv.org/pdf/1609.03536v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-scale-cascade-fully-convolutional
Repo
Framework

Learning Robust Representations of Text


Title	Learning Robust Representations of Text
Authors	Yitong Li, Trevor Cohn, Timothy Baldwin
Abstract	Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network sensitivity to its inputs, inspired by ideas from computer vision, thus learning models that are more robust. Empirical evaluation over a range of sentiment datasets with a convolutional neural network shows that, compared to a baseline model and the dropout method, our method achieves superior performance over noisy inputs and out-of-domain data.
Tasks
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06082v1
PDF	http://arxiv.org/pdf/1609.06082v1.pdf
PWC	https://paperswithcode.com/paper/learning-robust-representations-of-text
Repo
Framework

On the Iteration Complexity of Oblivious First-Order Optimization Algorithms


Title	On the Iteration Complexity of Oblivious First-Order Optimization Algorithms
Authors	Yossi Arjevani, Ohad Shamir
Abstract	We consider a broad class of first-order optimization algorithms which are \emph{oblivious}, in the sense that their step sizes are scheduled regardless of the function under consideration, except for limited side-information such as smoothness or strong convexity parameters. With the knowledge of these two parameters, we show that any such algorithm attains an iteration complexity lower bound of $\Omega(\sqrt{L/\epsilon})$ for $L$-smooth convex functions, and $\tilde{\Omega}(\sqrt{L/\mu}\ln(1/\epsilon))$ for $L$-smooth $\mu$-strongly convex functions. These lower bounds are stronger than those in the traditional oracle model, as they hold independently of the dimension. To attain these, we abandon the oracle model in favor of a structure-based approach which builds upon a framework recently proposed in (Arjevani et al., 2015). We further show that without knowing the strong convexity parameter, it is impossible to attain an iteration complexity better than $\tilde{\Omega}\left((L/\mu)\ln(1/\epsilon)\right)$. This result is then used to formalize an observation regarding $L$-smooth convex functions, namely, that the iteration complexity of algorithms employing time-invariant step sizes must be at least $\Omega(L/\epsilon)$.
Tasks
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03529v1
PDF	http://arxiv.org/pdf/1605.03529v1.pdf
PWC	https://paperswithcode.com/paper/on-the-iteration-complexity-of-oblivious
Repo
Framework

Weighted Positive Binary Decision Diagrams for Exact Probabilistic Inference


Title	Weighted Positive Binary Decision Diagrams for Exact Probabilistic Inference
Authors	Giso H. Dal, Peter J. F. Lucas
Abstract	Recent work on weighted model counting has been very successfully applied to the problem of probabilistic inference in Bayesian networks. The probability distribution is encoded into a Boolean normal form and compiled to a target language, in order to represent local structure expressed among conditional probabilities more efficiently. We show that further improvements are possible, by exploiting the knowledge that is lost during the encoding phase and incorporating it into a compiler inspired by Satisfiability Modulo Theories. Constraints among variables are used as a background theory, which allows us to optimize the Shannon decomposition. We propose a new language, called Weighted Positive Binary Decision Diagrams, that reduces the cost of probabilistic inference by using this decomposition variant to induce an arithmetic circuit of reduced size.
Tasks
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05551v1
PDF	http://arxiv.org/pdf/1610.05551v1.pdf
PWC	https://paperswithcode.com/paper/weighted-positive-binary-decision-diagrams
Repo
Framework

SeDMiD for Confusion Detection: Uncovering Mind State from Time Series Brain Wave Data


Title	SeDMiD for Confusion Detection: Uncovering Mind State from Time Series Brain Wave Data
Authors	Jingkang Yang, Haohan Wang, Jun Zhu, Eric P. Xing
Abstract	Understanding how brain functions has been an intriguing topic for years. With the recent progress on collecting massive data and developing advanced technology, people have become interested in addressing the challenge of decoding brain wave data into meaningful mind states, with many machine learning models and algorithms being revisited and developed, especially the ones that handle time series data because of the nature of brain waves. However, many of these time series models, like HMM with hidden state in discrete space or State Space Model with hidden state in continuous space, only work with one source of data and cannot handle different sources of information simultaneously. In this paper, we propose an extension of State Space Model to work with different sources of information together with its learning and inference algorithms. We apply this model to decode the mind state of students during lectures based on their brain waves and reach a significant better results compared to traditional methods.
Tasks	Time Series
Published	2016-11-29
URL	http://arxiv.org/abs/1611.10252v1
PDF	http://arxiv.org/pdf/1611.10252v1.pdf
PWC	https://paperswithcode.com/paper/sedmid-for-confusion-detection-uncovering
Repo
Framework