May 7, 2019

3006 words 15 mins read

Paper Group ANR 40

Temporal Model Adaptation for Person Re-Identification. Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition. Correlated-PCA: Principal Components’ Analysis when Data and Noise are Correlated. Habits vs Environment: What really causes asthma?. Covariate conscious approach for G …

Temporal Model Adaptation for Person Re-Identification


Title	Temporal Model Adaptation for Person Re-Identification
Authors	Niki Martinel, Abir Das, Christian Micheloni, Amit K. Roy-Chowdhury
Abstract	Person re-identification is an open and challenging problem in computer vision. Majority of the efforts have been spent either to design the best feature representation or to learn the optimal matching metric. Most approaches have neglected the problem of adapting the selected features or the learned model over time. To address such a problem, we propose a temporal model adaptation scheme with human in the loop. We first introduce a similarity-dissimilarity learning method which can be trained in an incremental fashion by means of a stochastic alternating directions methods of multipliers optimization procedure. Then, to achieve temporal adaptation with limited human effort, we exploit a graph-based approach to present the user only the most informative probe-gallery matches that should be used to update the model. Results on three datasets have shown that our approach performs on par or even better than state-of-the-art approaches while reducing the manual pairwise labeling effort by about 80%.
Tasks	Person Re-Identification
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07216v1
PDF	http://arxiv.org/pdf/1607.07216v1.pdf
PWC	https://paperswithcode.com/paper/temporal-model-adaptation-for-person-re
Repo
Framework

Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition


Title	Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
Authors	Zecheng Xie, Zenghui Sun, Lianwen Jin, Hao Ni, Terry Lyons
Abstract	Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences. In this paper, we exploit the outstanding capability of path signature to translate online pen-tip trajectories into informative signature feature maps using a sliding window-based method, successfully capturing the analytic and geometric properties of pen strokes with strong local invariance and robustness. A multi-spatial-context fully convolutional recurrent network (MCFCRN) is proposed to exploit the multiple spatial contexts from the signature feature maps and generate a prediction sequence while completely avoiding the difficult segmentation problem. Furthermore, an implicit language model is developed to make predictions based on semantic context within a predicting feature sequence, providing a new perspective for incorporating lexicon constraints and prior knowledge about a certain language in the recognition procedure. Experiments on two standard benchmarks, Dataset-CASIA and Dataset-ICDAR, yielded outstanding results, with correct rates of 97.10% and 97.15%, respectively, which are significantly better than the best result reported thus far in the literature.
Tasks	Handwritten Chinese Text Recognition, Language Modelling
Published	2016-10-09
URL	http://arxiv.org/abs/1610.02616v2
PDF	http://arxiv.org/pdf/1610.02616v2.pdf
PWC	https://paperswithcode.com/paper/learning-spatial-semantic-context-with-fully
Repo
Framework

Correlated-PCA: Principal Components’ Analysis when Data and Noise are Correlated


Title	Correlated-PCA: Principal Components’ Analysis when Data and Noise are Correlated
Authors	Namrata Vaswani, Han Guo
Abstract	Given a matrix of observed data, Principal Components Analysis (PCA) computes a small number of orthogonal directions that contain most of its variability. Provably accurate solutions for PCA have been in use for a long time. However, to the best of our knowledge, all existing theoretical guarantees for it assume that the data and the corrupting noise are mutually independent, or at least uncorrelated. This is valid in practice often, but not always. In this paper, we study the PCA problem in the setting where the data and noise can be correlated. Such noise is often also referred to as “data-dependent noise”. We obtain a correctness result for the standard eigenvalue decomposition (EVD) based solution to PCA under simple assumptions on the data-noise correlation. We also develop and analyze a generalization of EVD, cluster-EVD, that improves upon EVD in certain regimes.
Tasks
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09307v2
PDF	http://arxiv.org/pdf/1610.09307v2.pdf
PWC	https://paperswithcode.com/paper/correlated-pca-principal-components-analysis-1
Repo
Framework

Habits vs Environment: What really causes asthma?


Title	Habits vs Environment: What really causes asthma?
Authors	Mengfan Tang, Pranav Agrawal, Ramesh Jain
Abstract	Despite considerable number of studies on risk factors for asthma onset, very little is known about their relative importance. To have a full picture of these factors, both categories, personal and environmental data, have to be taken into account simultaneously, which is missing in previous studies. We propose a framework to rank the risk factors from heterogeneous data sources of the two categories. Established on top of EventShop and Personal EventShop, this framework extracts about 400 features, and analyzes them by employing a gradient boosting tree. The features come from sources including personal profile and life-event data, and environmental data on air pollution, weather and PM2.5 emission sources. The top ranked risk factors derived from our framework agree well with the general medical consensus. Thus, our framework is a reliable approach, and the discovered rankings of relative importance of risk factors can provide insights for the prevention of asthma.
Tasks
Published	2016-01-20
URL	http://arxiv.org/abs/1601.05141v1
PDF	http://arxiv.org/pdf/1601.05141v1.pdf
PWC	https://paperswithcode.com/paper/habits-vs-environment-what-really-causes
Repo
Framework

Covariate conscious approach for Gait recognition based upon Zernike moment invariants


Title	Covariate conscious approach for Gait recognition based upon Zernike moment invariants
Authors	Himanshu Aggarwal, Dinesh K. Vishwakarma
Abstract	Gait recognition i.e. identification of an individual from his/her walking pattern is an emerging field. While existing gait recognition techniques perform satisfactorily in normal walking conditions, there performance tend to suffer drastically with variations in clothing and carrying conditions. In this work, we propose a novel covariate cognizant framework to deal with the presence of such covariates. We describe gait motion by forming a single 2D spatio-temporal template from video sequence, called Average Energy Silhouette image (AESI). Zernike moment invariants (ZMIs) are then computed to screen the parts of AESI infected with covariates. Following this, features are extracted from Spatial Distribution of Oriented Gradients (SDOGs) and novel Mean of Directional Pixels (MDPs) methods. The obtained features are fused together to form the final well-endowed feature set. Experimental evaluation of the proposed framework on three publicly available datasets i.e. CASIA dataset B, OU-ISIR Treadmill dataset B and USF Human-ID challenge dataset with recently published gait recognition approaches, prove its superior performance.
Tasks	Gait Recognition
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06683v1
PDF	http://arxiv.org/pdf/1611.06683v1.pdf
PWC	https://paperswithcode.com/paper/covariate-conscious-approach-for-gait
Repo
Framework

Walker-Independent Features for Gait Recognition from Motion Capture Data


Title	Walker-Independent Features for Gait Recognition from Motion Capture Data
Authors	Michal Balazia, Petr Sojka
Abstract	MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach. Yet in some applications such as video surveillance new identities can appear on the fly and labeled data for all encountered people may not always be available. This work introduces the concept of learning walker-independent gait features directly from raw joint coordinates by a modification of the Fisher Linear Discriminant Analysis with Maximum Margin Criterion. Our new approach shows not only that these features can discriminate different people than who they are learned on, but also that the number of learning identities can be much smaller than the number of walkers encountered in the real operation.
Tasks	Gait Recognition, Motion Capture
Published	2016-09-22
URL	http://arxiv.org/abs/1609.06936v4
PDF	http://arxiv.org/pdf/1609.06936v4.pdf
PWC	https://paperswithcode.com/paper/walker-independent-features-for-gait
Repo
Framework

IDNet: Smartphone-based Gait Recognition with Convolutional Neural Networks


Title	IDNet: Smartphone-based Gait Recognition with Convolutional Neural Networks
Authors	Matteo Gadaleta, Michele Rossi
Abstract	Here, we present IDNet, a user authentication framework from smartphone-acquired motion signals. Its goal is to recognize a target user from their way of walking, using the accelerometer and gyroscope (inertial) signals provided by a commercial smartphone worn in the front pocket of the user’s trousers. IDNet features several innovations including: i) a robust and smartphone-orientation-independent walking cycle extraction block, ii) a novel feature extractor based on convolutional neural networks, iii) a one-class support vector machine to classify walking cycles, and the coherent integration of these into iv) a multi-stage authentication technique. IDNet is the first system that exploits a deep learning approach as universal feature extractors for gait recognition, and that combines classification results from subsequent walking cycles into a multi-stage decision making framework. Experimental results show the superiority of our approach against state-of-the-art techniques, leading to misclassification rates (either false negatives or positives) smaller than 0.15% with fewer than five walking cycles. Design choices are discussed and motivated throughout, assessing their impact on the user authentication performance.
Tasks	Decision Making, Gait Recognition
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03238v3
PDF	http://arxiv.org/pdf/1606.03238v3.pdf
PWC	https://paperswithcode.com/paper/idnet-smartphone-based-gait-recognition-with
Repo
Framework

Fisher Motion Descriptor for Multiview Gait Recognition


Title	Fisher Motion Descriptor for Multiview Gait Recognition
Authors	F. M. Castro, M. J. Marín-Jiménez, N. Guil, R. Muñoz-Salinas
Abstract	The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art people detectors to define custom spatial configurations of the descriptors around the target person, obtaining a rich representation of the gait motion. The local motion features (described by the Divergence-Curl-Shear descriptor) extracted on the different spatial areas of the person are combined into a single high-level gait descriptor by using the Fisher Vector encoding. The proposed approach, coined Pyramidal Fisher Motion, is experimentally validated on `CASIA' dataset (parts B and C),` TUM GAID’ dataset, `CMU MoBo' dataset and the recent` AVA Multiview Gait’ dataset. The results show that this new approach achieves state-of-the-art results in the problem of gait recognition, allowing to recognize walking people from diverse viewpoints on single and multiple camera setups, wearing different clothes, carrying bags, walking at diverse speeds and not limited to straight walking paths.
Tasks	Gait Recognition, Multiview Gait Recognition
Published	2016-01-26
URL	http://arxiv.org/abs/1601.06931v1
PDF	http://arxiv.org/pdf/1601.06931v1.pdf
PWC	https://paperswithcode.com/paper/fisher-motion-descriptor-for-multiview-gait
Repo
Framework

Person Re-Identification by Discriminative Selection in Video Ranking


Title	Person Re-Identification by Discriminative Selection in Video Ranking
Authors	Taiqing Wang, Shaogang Gong, Xiatian Zhu, Shengjin Wang
Abstract	Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios. Single-frame (single-shot) based visual appearance matching is inherently limited for person ReID in public spaces due to the challenging visual ambiguity and uncertainty arising from non-overlapping camera views where viewing condition changes can cause significant people appearance variations. In this work, we present a novel model to automatically select the most discriminative video fragments from noisy/incomplete image sequences of people from which reliable space-time and appearance features can be computed, whilst simultaneously learning a video ranking function for person ReID. Using the PRID$2011$, iLIDS-VID, and HDA+ image sequence datasets, we extensively conducted comparative evaluations to demonstrate the advantages of the proposed model over contemporary gait recognition, holistic image sequence matching and state-of-the-art single-/multi-shot ReID methods.
Tasks	Gait Recognition, Person Re-Identification
Published	2016-01-23
URL	http://arxiv.org/abs/1601.06260v1
PDF	http://arxiv.org/pdf/1601.06260v1.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-by-discriminative
Repo
Framework

Row-less Universal Schema


Title	Row-less Universal Schema
Authors	Patrick Verga, Andrew McCallum
Abstract	Universal schema jointly embeds knowledge bases and textual patterns to reason about entities and relations for automatic knowledge base construction and information extraction. In the past, entity pairs and relations were represented as learned vectors with compatibility determined by a scoring function, limiting generalization to unseen text patterns and entities. Recently, ‘column-less’ versions of Universal Schema have used compositional pattern encoders to generalize to all text patterns. In this work we take the next step and propose a ‘row-less’ model of universal schema, removing explicit entity pair representations. Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. In experimental results on the FB15k-237 benchmark we demonstrate that we can match the performance of a comparable model with explicit entity pair representations using a model of attention over relation types. We further demonstrate that the model per- forms with nearly the same accuracy on entity pairs never seen during training.
Tasks
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06361v1
PDF	http://arxiv.org/pdf/1604.06361v1.pdf
PWC	https://paperswithcode.com/paper/row-less-universal-schema
Repo
Framework

Harmonic Grammar in a DisCo Model of Meaning


Title	Harmonic Grammar in a DisCo Model of Meaning
Authors	Martha Lewis, Bob Coecke
Abstract	The model of cognition developed in (Smolensky and Legendre, 2006) seeks to unify two levels of description of the cognitive process: the connectionist and the symbolic. The theory developed brings together these two levels into the Integrated Connectionist/Symbolic Cognitive architecture (ICS). Clark and Pulman (2007) draw a parallel with semantics where meaning may be modelled on both distributional and symbolic levels, developed by Coecke et al, 2010 into the Distributional Compositional (DisCo) model of meaning. In the current work, we revisit Smolensky and Legendre (S&L)‘s model. We describe the DisCo framework, summarise the key ideas in S&L’s architecture, and describe how their description of harmony as a graded measure of grammaticality may be applied in the DisCo model.
Tasks
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02089v1
PDF	http://arxiv.org/pdf/1602.02089v1.pdf
PWC	https://paperswithcode.com/paper/harmonic-grammar-in-a-disco-model-of-meaning
Repo
Framework

Spectral M-estimation with Applications to Hidden Markov Models


Title	Spectral M-estimation with Applications to Hidden Markov Models
Authors	Dustin Tran, Minjae Kim, Finale Doshi-Velez
Abstract	Method of moment estimators exhibit appealing statistical properties, such as asymptotic unbiasedness, for nonconvex problems. However, they typically require a large number of samples and are extremely sensitive to model misspecification. In this paper, we apply the framework of M-estimation to develop both a generalized method of moments procedure and a principled method for regularization. Our proposed M-estimator obtains optimal sample efficiency rates (in the class of moment-based estimators) and the same well-known rates on prediction accuracy as other spectral estimators. It also makes it straightforward to incorporate regularization into the sample moment conditions. We demonstrate empirically the gains in sample efficiency from our approach on hidden Markov models.
Tasks
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08815v1
PDF	http://arxiv.org/pdf/1603.08815v1.pdf
PWC	https://paperswithcode.com/paper/spectral-m-estimation-with-applications-to
Repo
Framework

Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling


Title	Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling
Authors	Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
Abstract	The “interpretation through synthesis” approach to analyze face images, particularly Active Appearance Models (AAMs) method, has become one of the most successful face modeling approaches over the last two decades. AAM models have ability to represent face images through synthesis using a controllable parameterized Principal Component Analysis (PCA) model. However, the accuracy and robustness of the synthesized faces of AAM are highly depended on the training sets and inherently on the generalizability of PCA subspaces. This paper presents a novel Deep Appearance Models (DAMs) approach, an efficient replacement for AAMs, to accurately capture both shape and texture of face images under large variations. In this approach, three crucial components represented in hierarchical layers are modeled using the Deep Boltzmann Machines (DBM) to robustly capture the variations of facial shapes and appearances. DAMs are therefore superior to AAMs in inferencing a representation for new face images under various challenging conditions. The proposed approach is evaluated in various applications to demonstrate its robustness and capabilities, i.e. facial super-resolution reconstruction, facial off-angle reconstruction or face frontalization, facial occlusion removal and age estimation using challenging face databases, i.e. Labeled Face Parts in the Wild (LFPW), Helen and FG-NET. Comparing to AAMs and other deep learning based approaches, the proposed DAMs achieve competitive results in those applications, thus this showed their advantages in handling occlusions, facial representation, and reconstruction.
Tasks	Age Estimation, Super-Resolution
Published	2016-07-23
URL	http://arxiv.org/abs/1607.06871v3
PDF	http://arxiv.org/pdf/1607.06871v3.pdf
PWC	https://paperswithcode.com/paper/deep-appearance-models-a-deep-boltzmann
Repo
Framework

Submodular Optimization under Noise


Title	Submodular Optimization under Noise
Authors	Avinatan Hassidim, Yaron Singer
Abstract	We consider the problem of maximizing a monotone submodular function under noise. There has been a great deal of work on optimization of submodular functions under various constraints, resulting in algorithms that provide desirable approximation guarantees. In many applications, however, we do not have access to the submodular function we aim to optimize, but rather to some erroneous or noisy version of it. This raises the question of whether provable guarantees are obtainable in presence of error and noise. We provide initial answers, by focusing on the question of maximizing a monotone submodular function under a cardinality constraint when given access to a noisy oracle of the function. We show that: - For a cardinality constraint $k \geq 2$, there is an approximation algorithm whose approximation ratio is arbitrarily close to $1-1/e$; - For $k=1$ there is an algorithm whose approximation ratio is arbitrarily close to $1/2$. No randomized algorithm can obtain an approximation ratio better than $1/2+o(1)$; -If the noise is adversarial, no non-trivial approximation guarantee can be obtained.
Tasks
Published	2016-01-12
URL	http://arxiv.org/abs/1601.03095v3
PDF	http://arxiv.org/pdf/1601.03095v3.pdf
PWC	https://paperswithcode.com/paper/submodular-optimization-under-noise
Repo
Framework

Multilevel Monte Carlo for Scalable Bayesian Computations


Title	Multilevel Monte Carlo for Scalable Bayesian Computations
Authors	Mike Giles, Tigran Nagapetyan, Lukasz Szpruch, Sebastian Vollmer, Konstantinos Zygalakis
Abstract	Markov chain Monte Carlo (MCMC) algorithms are ubiquitous in Bayesian computations. However, they need to access the full data set in order to evaluate the posterior density at every step of the algorithm. This results in a great computational burden in big data applications. In contrast to MCMC methods, Stochastic Gradient MCMC (SGMCMC) algorithms such as the Stochastic Gradient Langevin Dynamics (SGLD) only require access to a batch of the data set at every step. This drastically improves the computational performance and scales well to large data sets. However, the difficulty with SGMCMC algorithms comes from the sensitivity to its parameters which are notoriously difficult to tune. Moreover, the Root Mean Square Error (RMSE) scales as $\mathcal{O}(c^{-\frac{1}{3}})$ as opposed to standard MCMC $\mathcal{O}(c^{-\frac{1}{2}})$ where $c$ is the computational cost. We introduce a new class of Multilevel Stochastic Gradient Markov chain Monte Carlo algorithms that are able to mitigate the problem of tuning the step size and more importantly of recovering the $\mathcal{O}(c^{-\frac{1}{2}})$ convergence of standard Markov Chain Monte Carlo methods without the need to introduce Metropolis-Hasting steps. A further advantage of this new class of algorithms is that it can easily be parallelised over a heterogeneous computer architecture. We illustrate our methodology using Bayesian logistic regression and provide numerical evidence that for a prescribed relative RMSE the computational cost is sublinear in the number of data items.
Tasks
Published	2016-09-15
URL	http://arxiv.org/abs/1609.06144v1
PDF	http://arxiv.org/pdf/1609.06144v1.pdf
PWC	https://paperswithcode.com/paper/multilevel-monte-carlo-for-scalable-bayesian
Repo
Framework