May 6, 2019

3173 words 15 mins read

Paper Group ANR 290

Occurrence Statistics of Entities, Relations and Types on the Web. Active Learning for Online Recognition of Human Activities from Streaming Videos. Robust Gait Recognition by Integrating Inertial and RGBD Sensors. We Can “See” You via Wi-Fi - WiFi Action Recognition via Vision-based Methods. Semi-supervised learning of deep metrics for stereo reco …

Occurrence Statistics of Entities, Relations and Types on the Web


Title	Occurrence Statistics of Entities, Relations and Types on the Web
Authors	Aman Madaan, Sunita Sarawagi
Abstract	The problem of collecting reliable estimates of occurrence of entities on the open web forms the premise for this report. The models learned for tagging entities cannot be expected to perform well when deployed on the web. This is owing to the severe mismatch in the distributions of such entities on the web and in the relatively diminutive training data. In this report, we build up the case for maximum mean discrepancy for estimation of occurrence statistics of entities on the web, taking a review of named entity disambiguation techniques and related concepts along the way.
Tasks	Entity Disambiguation
Published	2016-05-14
URL	http://arxiv.org/abs/1605.04359v1
PDF	http://arxiv.org/pdf/1605.04359v1.pdf
PWC	https://paperswithcode.com/paper/occurrence-statistics-of-entities-relations
Repo
Framework

Active Learning for Online Recognition of Human Activities from Streaming Videos


Title	Active Learning for Online Recognition of Human Activities from Streaming Videos
Authors	Rocco De Rosa, Ilaria Gori, Fabio Cuzzolin, Barbara Caputo, Nicolò Cesa-Bianchi
Abstract	Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptively covers the feature space with simple local classifiers; (2) employing an active learning strategy to reduce annotation requests; (3) achieving promising accuracy within a fixed model size. Extensive experiments on standard benchmarks show that our approach is competitive with state-of-the-art non-incremental methods, and outperforms the existing active incremental baselines.
Tasks	Active Learning
Published	2016-04-11
URL	http://arxiv.org/abs/1604.02855v1
PDF	http://arxiv.org/pdf/1604.02855v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-online-recognition-of
Repo
Framework

Robust Gait Recognition by Integrating Inertial and RGBD Sensors


Title	Robust Gait Recognition by Integrating Inertial and RGBD Sensors
Authors	Qin Zou, Lihao Ni, Qian Wang, Qingquan Li, Song Wang
Abstract	Gait has been considered as a promising and unique biometric for person identification. Traditionally, gait data are collected using either color sensors, such as a CCD camera, depth sensors, such as a Microsoft Kinect, or inertial sensors, such as an accelerometer. However, a single type of sensors may only capture part of the dynamic gait features and make the gait recognition sensitive to complex covariate conditions, leading to fragile gait-based person identification systems. In this paper, we propose to combine all three types of sensors for gait data collection and gait recognition, which can be used for important identification applications, such as identity recognition to access a restricted building or area. We propose two new algorithms, namely EigenGait and TrajGait, to extract gait features from the inertial data and the RGBD (color and depth) data, respectively. Specifically, EigenGait extracts general gait dynamics from the accelerometer readings in the eigenspace and TrajGait extracts more detailed sub-dynamics by analyzing 3D dense trajectories. Finally, both extracted features are fed into a supervised classifier for gait recognition and person identification. Experiments on 50 subjects, with comparisons to several other state-of-the-art gait-recognition approaches, show that the proposed approach can achieve higher recognition accuracy and robustness.
Tasks	Gait Recognition, Person Identification
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09816v1
PDF	http://arxiv.org/pdf/1610.09816v1.pdf
PWC	https://paperswithcode.com/paper/robust-gait-recognition-by-integrating
Repo
Framework

We Can “See” You via Wi-Fi - WiFi Action Recognition via Vision-based Methods


Title	We Can “See” You via Wi-Fi - WiFi Action Recognition via Vision-based Methods
Authors	Jen-Yin Chang, Kuan-Ying Lee, Yu-Lin Wei, Kate Ching-Ju Lin, Winston Hsu
Abstract	Recently, Wi-Fi has caught tremendous attention for its ubiquity, and, motivated by Wi-Fi’s low cost and privacy preservation, researchers have been putting lots of investigation into its potential on action recognition and even person identification. In this paper, we offer an comprehensive overview on these two topics in Wi-Fi. Also, through looking at these two topics from an unprecedented perspective, we could achieve generality instead of designing specific ad-hoc features for each scenario. Observing the great resemblance of Channel State Information (CSI, a fine-grained information captured from the received Wi-Fi signal) to texture, we proposed a brand-new framework based on computer vision methods. To minimize the effect of location dependency embedded in CSI, we propose a novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies. From the experiments conducted, we demonstrate the feasibility and efficacy of the proposed methods. Also, we conclude factors that would affect the performance and highlight a few promising issues that require further deliberation.
Tasks	Person Identification, Temporal Action Localization
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05461v2
PDF	http://arxiv.org/pdf/1608.05461v2.pdf
PWC	https://paperswithcode.com/paper/we-can-see-you-via-wi-fi-wifi-action
Repo
Framework

Semi-supervised learning of deep metrics for stereo reconstruction


Title	Semi-supervised learning of deep metrics for stereo reconstruction
Authors	Stepan Tulyakov, Anton Ivanov, Francois Fleuret
Abstract	Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to collect for certain applications. The main contribution of our work is a new semi-supervised method for learning deep metrics from unlabeled stereo images, given coarse information about the scenes and the optical system. Our method alternatively optimizes the metric with a standard stochastic gradient descent, and applies stereo constraints to regularize its prediction. Experiments on reference data-sets show that, for a given network architecture, training with this new method without ground-truth produces a metric with performance as good as state-of-the-art baselines trained with the said ground-truth. This work has three practical implications. Firstly, it helps to overcome limitations of training sets, in particular noisy ground truth. Secondly it allows to use much more training data during learning. Thirdly, it allows to tune deep metric for a particular stereo system, even if ground truth is not available.
Tasks
Published	2016-12-03
URL	http://arxiv.org/abs/1612.00979v1
PDF	http://arxiv.org/pdf/1612.00979v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-of-deep-metrics-for
Repo
Framework

Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection


Title	Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection
Authors	Abir Das, Rameswar Panda, Amit K. Roy-Chowdhury
Abstract	The problem of image-base person identification/recognition is to provide an identity to the image of an individual based on learned models that describe his/her appearance. Most traditional person identification systems rely on learning a static model on tediously labeled training data. Though labeling manually is an indispensable part of a supervised framework, for a large scale identification system labeling huge amount of data is a significant overhead. For large multi-sensor data as typically encountered in camera networks, labeling a lot of samples does not always mean more information, as redundant images are labeled several times. In this work, we propose a convex optimization based iterative framework that progressively and judiciously chooses a sparse but informative set of samples for labeling, with minimal overlap with previously labeled images. We also use a structure preserving sparse reconstruction based classifier to reduce the training burden typically seen in discriminative classifiers. The two stage approach leads to a novel framework for online update of the classifiers involving only the incorporation of new labeled data rather than any expensive training phase. We demonstrate the effectiveness of our approach on multi-camera person re-identification datasets, to demonstrate the feasibility of learning online classification models in multi-camera big data applications. Using three benchmark datasets, we validate our approach and demonstrate that our framework achieves superior performance with significantly less amount of manual labeling.
Tasks	Person Identification, Person Re-Identification
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00417v1
PDF	http://arxiv.org/pdf/1607.00417v1.pdf
PWC	https://paperswithcode.com/paper/continuous-adaptation-of-multi-camera-person
Repo
Framework

A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements


Title	A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements
Authors	Daniel Durstewitz
Abstract	The computational properties of neural systems are often thought to be implemented in terms of their network dynamics. Hence, recovering the system dynamics from experimentally observed neuronal time series, like multiple single-unit (MSU) recordings or neuroimaging data, is an important step toward understanding its computations. Ideally, one would not only seek a state space representation of the dynamics, but would wish to have access to its governing equations for in-depth analysis. Recurrent neural networks (RNNs) are a computationally powerful and dynamically universal formal framework which has been extensively studied from both the computational and the dynamical systems perspective. Here we develop a semi-analytical maximum-likelihood estimation scheme for piecewise-linear RNNs (PLRNNs) within the statistical framework of state space models, which accounts for noise in both the underlying latent dynamics and the observation process. The Expectation-Maximization algorithm is used to infer the latent state distribution, through a global Laplace approximation, and the PLRNN parameters iteratively. After validating the procedure on toy examples, the approach is applied to MSU recordings from the rodent anterior cingulate cortex obtained during performance of a classical working memory task, delayed alternation. A model with 5 states turned out to be sufficient to capture the essential computational dynamics underlying task performance, including stimulus-selective delay activity. The estimated models were rarely multi-stable, but rather were tuned to exhibit slow dynamics in the vicinity of a bifurcation point. In summary, the present work advances a semi-analytical (thus reasonably fast) maximum-likelihood estimation framework for PLRNNs that may enable to recover the relevant dynamics underlying observed neuronal time series, and directly link them to computational properties.
Tasks	Time Series
Published	2016-12-23
URL	http://arxiv.org/abs/1612.07846v1
PDF	http://arxiv.org/pdf/1612.07846v1.pdf
PWC	https://paperswithcode.com/paper/a-state-space-approach-for-piecewise-linear
Repo
Framework

Learning A Deep $\ell_\infty$ Encoder for Hashing


Title	Learning A Deep $\ell_\infty$ Encoder for Hashing
Authors	Zhangyang Wang, Yingzhen Yang, Shiyu Chang, Qing Ling, Thomas S. Huang
Abstract	We investigate the $\ell_\infty$-constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning. Based on the Alternating Direction Method of Multipliers (ADMM), we formulate the original convex minimization problem as a feed-forward neural network, named \textit{Deep $\ell_\infty$ Encoder}, by introducing the novel Bounded Linear Unit (BLU) neuron and modeling the Lagrange multipliers as network biases. Such a structural prior acts as an effective network regularization, and facilitates the model initialization. We then investigate the effective use of the proposed model in the application of hashing, by coupling the proposed encoders under a supervised pairwise loss, to develop a \textit{Deep Siamese $\ell_\infty$ Network}, which can be optimized from end to end. Extensive experiments demonstrate the impressive performances of the proposed model. We also provide an in-depth analysis of its behaviors against the competitors.
Tasks	Quantization
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01475v1
PDF	http://arxiv.org/pdf/1604.01475v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-deep-ell_infty-encoder-for-hashing
Repo
Framework

Conversational Recommendation System with Unsupervised Learning


Title	Conversational Recommendation System with Unsupervised Learning
Authors	Yueming Sun, Yi Zhang, Yunfei Chen, Roger Jin
Abstract	We will demonstrate a conversational products recommendation agent. This system shows how we combine research in personalized recommendation systems with research in dialogue systems to build a virtual sales agent. Based on new deep learning technologies we developed, the virtual agent is capable of learning how to interact with users, how to answer user questions, what is the next question to ask, and what to recommend when chatting with a human user. Normally a descent conversational agent for a particular domain requires tens of thousands of hand labeled conversational data or hand written rules. This is a major barrier when launching a conversation agent for a new domain. We will explore and demonstrate the effectiveness of the learning solution even when there is no hand written rules or hand labeled training data.
Tasks	Recommendation Systems
Published	2016-09-22
URL	http://arxiv.org/abs/1610.01546v1
PDF	http://arxiv.org/pdf/1610.01546v1.pdf
PWC	https://paperswithcode.com/paper/conversational-recommendation-system-with
Repo
Framework


Title	On Generation of Time-based Label Refinements
Authors	Niek Tax, Emin Alasgarov, Natalia Sidorova, Reinder Haakma
Abstract	Process mining is a research field focused on the analysis of event data with the aim of extracting insights in processes. Applying process mining techniques on data from smart home environments has the potential to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions. Finding the right event labels to enable application of process mining techniques is however far from trivial, as simply using the triggering sensor as the label for sensor events results in uninformative models that allow for too much behavior (overgeneralizing). Refinements of sensor level event labels suggested by domain experts have shown to enable discovery of more precise and insightful process models. However, there exist no automated approach to generate refinements of event labels in the context of process mining. In this paper we propose a framework for automated generation of label refinements based on the time attribute of events. We show on a case study with real life smart home event data that behaviorally more specific, and therefore more insightful, process models can be found by using automatically generated refined labels in process discovery.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03333v1
PDF	http://arxiv.org/pdf/1609.03333v1.pdf
PWC	https://paperswithcode.com/paper/on-generation-of-time-based-label-refinements
Repo
Framework

Brain Emotional Learning-Based Prediction Model (For Long-Term Chaotic Prediction Applications)


Title	Brain Emotional Learning-Based Prediction Model (For Long-Term Chaotic Prediction Applications)
Authors	Mahboobeh Parsapoor
Abstract	This study suggests a new prediction model for chaotic time series inspired by the brain emotional learning of mammals. We describe the structure and function of this model, which is referred to as BELPM (Brain Emotional Learning-Based Prediction Model). Structurally, the model mimics the connection between the regions of the limbic system, and functionally it uses weighted k nearest neighbors to imitate the roles of those regions. The learning algorithm of BELPM is defined using steepest descent (SD) and the least square estimator (LSE). Two benchmark chaotic time series, Lorenz and Henon, have been used to evaluate the performance of BELPM. The obtained results have been compared with those of other prediction methods. The results show that BELPM has the capability to achieve a reasonable accuracy for long-term prediction of chaotic time series, using a limited amount of training data and a reasonably low computational time.
Tasks	Time Series
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01681v1
PDF	http://arxiv.org/pdf/1605.01681v1.pdf
PWC	https://paperswithcode.com/paper/brain-emotional-learning-based-prediction
Repo
Framework

OCR Error Correction Using Character Correction and Feature-Based Word Classification


Title	OCR Error Correction Using Character Correction and Feature-Based Word Classification
Authors	Ido Kissos, Nachum Dershowitz
Abstract	This paper explores the use of a learned classifier for post-OCR text correction. Experiments with the Arabic language show that this approach, which integrates a weighted confusion matrix and a shallow language model, improves the vast majority of segmentation and recognition errors, the most frequent types of error on our dataset.
Tasks	Language Modelling, Optical Character Recognition
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06225v1
PDF	http://arxiv.org/pdf/1604.06225v1.pdf
PWC	https://paperswithcode.com/paper/ocr-error-correction-using-character
Repo
Framework

deepMiRGene: Deep Neural Network based Precursor microRNA Prediction


Title	deepMiRGene: Deep Neural Network based Precursor microRNA Prediction
Authors	Seunghyun Park, Seonwoo Min, Hyunsoo Choi, Sungroh Yoon
Abstract	Since microRNAs (miRNAs) play a crucial role in post-transcriptional gene regulation, miRNA identification is one of the most essential problems in computational biology. miRNAs are usually short in length ranging between 20 and 23 base pairs. It is thus often difficult to distinguish miRNA-encoding sequences from other non-coding RNAs and pseudo miRNAs that have a similar length, and most previous studies have recommended using precursor miRNAs instead of mature miRNAs for robust detection. A great number of conventional machine-learning-based classification methods have been proposed, but they often have the serious disadvantage of requiring manual feature engineering, and their performance is limited as well. In this paper, we propose a novel miRNA precursor prediction algorithm, deepMiRGene, based on recurrent neural networks, specifically long short-term memory networks. deepMiRGene automatically learns suitable features from the data themselves without manual feature engineering and constructs a model that can successfully reflect structural characteristics of precursor miRNAs. For the performance evaluation of our approach, we have employed several widely used evaluation metrics on three recent benchmark datasets and verified that deepMiRGene delivered comparable performance among the current state-of-the-art tools.
Tasks	Feature Engineering
Published	2016-04-29
URL	http://arxiv.org/abs/1605.00017v1
PDF	http://arxiv.org/pdf/1605.00017v1.pdf
PWC	https://paperswithcode.com/paper/deepmirgene-deep-neural-network-based
Repo
Framework

Using real-time cluster configurations of streaming asynchronous features as online state descriptors in financial markets


Title	Using real-time cluster configurations of streaming asynchronous features as online state descriptors in financial markets
Authors	Dieter Hendricks
Abstract	We present a scheme for online, unsupervised state discovery and detection from streaming, multi-featured, asynchronous data in high-frequency financial markets. Online feature correlations are computed using an unbiased, lossless Fourier estimator. A high-speed maximum likelihood clustering algorithm is then used to find the feature cluster configuration which best explains the structure in the correlation matrix. We conjecture that this feature configuration is a candidate descriptor for the temporal state of the system. Using a simple cluster configuration similarity metric, we are able to enumerate the state space based on prevailing feature configurations. The proposed state representation removes the need for human-driven data pre-processing for state attribute specification, allowing a learning agent to find structure in streaming data, discern changes in the system, enumerate its perceived state space and learn suitable action-selection policies.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06805v2
PDF	http://arxiv.org/pdf/1603.06805v2.pdf
PWC	https://paperswithcode.com/paper/using-real-time-cluster-configurations-of
Repo
Framework

On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization


Title	On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
Authors	Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, Mingyi Hong
Abstract	The cyclic block coordinate descent-type (CBCD-type) methods, which performs iterative updates for a few coordinates (a block) simultaneously throughout the procedure, have shown remarkable computational performance for solving strongly convex minimization problems. Typical applications include many popular statistical machine learning methods such as elastic-net regression, ridge penalized logistic regression, and sparse additive regression. Existing optimization literature has shown that for strongly convex minimization, the CBCD-type methods attain iteration complexity of $\mathcal{O}(p\log(1/\epsilon))$, where $\epsilon$ is a pre-specified accuracy of the objective value, and $p$ is the number of blocks. However, such iteration complexity explicitly depends on $p$, and therefore is at least $p$ times worse than the complexity $\mathcal{O}(\log(1/\epsilon))$ of gradient descent (GD) methods. To bridge this theoretical gap, we propose an improved convergence analysis for the CBCD-type methods. In particular, we first show that for a family of quadratic minimization problems, the iteration complexity $\mathcal{O}(\log^2(p)\cdot\log(1/\epsilon))$ of the CBCD-type methods matches that of the GD methods in term of dependency on $p$, up to a $\log^2 p$ factor. Thus our complexity bounds are sharper than the existing bounds by at least a factor of $p/\log^2(p)$. We also provide a lower bound to confirm that our improved complexity bounds are tight (up to a $\log^2 (p)$ factor), under the assumption that the largest and smallest eigenvalues of the Hessian matrix do not scale with $p$. Finally, we generalize our analysis to other strongly convex minimization problems beyond quadratic ones.
Tasks
Published	2016-07-10
URL	http://arxiv.org/abs/1607.02793v3
PDF	http://arxiv.org/pdf/1607.02793v3.pdf
PWC	https://paperswithcode.com/paper/on-faster-convergence-of-cyclic-block
Repo
Framework