Paper Group ANR 118
Bayesian Kernel and Mutual $k$-Nearest Neighbor Regression. Geometry of Interest (GOI): Spatio-Temporal Destination Extraction and Partitioning in GPS Trajectory Data. Joint Gender Classification and Age Estimation by Nearly Orthogonalizing Their Semantic Spaces. Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Heal …
Bayesian Kernel and Mutual $k$-Nearest Neighbor Regression
| Title | Bayesian Kernel and Mutual $k$-Nearest Neighbor Regression |
| Authors | Hyun-Chul Kim |
| Abstract | We propose Bayesian extensions of two nonparametric regression methods which are kernel and mutual $k$-nearest neighbor regression methods. Derived based on Gaussian process models for regression, the extensions provide distributions for target value estimates and the framework to select the hyperparameters. It is shown that both the proposed methods asymptotically converge to kernel and mutual $k$-nearest neighbor regression methods, respectively. The simulation results show that the proposed methods can select proper hyperparameters and are better than or comparable to the former methods for an artificial data set and a real world data set. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1608.01410v1 |
| http://arxiv.org/pdf/1608.01410v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-kernel-and-mutual-k-nearest-neighbor |
| Repo | |
| Framework | |
Geometry of Interest (GOI): Spatio-Temporal Destination Extraction and Partitioning in GPS Trajectory Data
| Title | Geometry of Interest (GOI): Spatio-Temporal Destination Extraction and Partitioning in GPS Trajectory Data |
| Authors | Seyed Morteza Mousavi, Aaron Harwood, Shanika Karunasekera, Mojtaba Maghrebi |
| Abstract | Nowadays large amounts of GPS trajectory data is being continuously collected by GPS-enabled devices such as vehicles navigation systems and mobile phones. GPS trajectory data is useful for applications such as traffic management, location forecasting, and itinerary planning. Such applications often need to extract the time-stamped Sequence of Visited Locations (SVLs) of the mobile objects. The nearest neighbor query (NNQ) is the most applied method for labeling the visited locations based on the IDs of the POIs in the process of SVL generation. NNQ in some scenarios is not accurate enough. To improve the quality of the extracted SVLs, instead of using NNQ, we label the visited locations as the IDs of the POIs which geometrically intersect with the GPS observations. Intersection operator requires the accurate geometry of the points of interest which we refer to them as the Geometries of Interest (GOIs). In some application domains (e.g. movement trajectories of animals), adequate information about the POIs and their GOIs may not be available a priori, or they may not be publicly accessible and, therefore, they need to be derived from GPS trajectory data. In this paper we propose a novel method for estimating the POIs and their GOIs, which consists of three phases: (i) extracting the geometries of the stay regions; (ii) constructing the geometry of destination regions based on the extracted stay regions; and (iii) constructing the GOIs based on the geometries of the destination regions. Using the geometric similarity to known GOIs as the major evaluation criterion, the experiments we performed using long-term GPS trajectory data show that our method outperforms the existing approaches. |
| Tasks | |
| Published | 2016-03-14 |
| URL | http://arxiv.org/abs/1603.04110v2 |
| http://arxiv.org/pdf/1603.04110v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-of-interest-goi-spatio-temporal |
| Repo | |
| Framework | |
Joint Gender Classification and Age Estimation by Nearly Orthogonalizing Their Semantic Spaces
| Title | Joint Gender Classification and Age Estimation by Nearly Orthogonalizing Their Semantic Spaces |
| Authors | Qing Tian, Songcan Chen |
| Abstract | In human face-based biometrics, gender classification and age estimation are two typical learning tasks. Although a variety of approaches have been proposed to handle them, just a few of them are solved jointly, even so, these joint methods do not yet specifically concern the semantic difference between human gender and age, which is intuitively helpful for joint learning, consequently leaving us a room of further improving the performance. To this end, in this work we firstly propose a general learning framework for jointly estimating human gender and age by specially attempting to formulate such semantic relationships as a form of near-orthogonality regularization and then incorporate it into the objective of the joint learning framework. In order to evaluate the effectiveness of the proposed framework, we exemplify it by respectively taking the widely used binary-class SVM for gender classification, and two threshold-based ordinal regression methods (i.e., the discriminant learning for ordinal regression and support vector ordinal regression) for age estimation, and crucially coupling both through the proposed semantic formulation. Moreover, we develop its kernelized nonlinear counterpart by deriving a representer theorem for the joint learning strategy. Finally, through extensive experiments on three aging datasets FG-NET, Morph Album I and Morph Album II, we demonstrate the effectiveness and superiority of the proposed joint learning strategy. |
| Tasks | Age Estimation |
| Published | 2016-09-14 |
| URL | http://arxiv.org/abs/1609.04116v1 |
| http://arxiv.org/pdf/1609.04116v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-gender-classification-and-age |
| Repo | |
| Framework | |
Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records
| Title | Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records |
| Authors | Abhyuday Jagannatha, Hong Yu |
| Abstract | Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored various recurrent neural network frameworks and show that they significantly outperformed the CRF models. |
| Tasks | |
| Published | 2016-06-25 |
| URL | http://arxiv.org/abs/1606.07953v2 |
| http://arxiv.org/pdf/1606.07953v2.pdf | |
| PWC | https://paperswithcode.com/paper/bidirectional-recurrent-neural-networks-for |
| Repo | |
| Framework | |
A Semi-Definite Programming approach to low dimensional embedding for unsupervised clustering
| Title | A Semi-Definite Programming approach to low dimensional embedding for unsupervised clustering |
| Authors | Stéphane Chrétien, Clément Dombry, Adrien Faivre |
| Abstract | This paper proposes a variant of the method of Gu'edon and Verhynin for estimating the cluster matrix in the Mixture of Gaussians framework via Semi-Definite Programming. A clustering oriented embedding is deduced from this estimate. The procedure is suitable for very high dimensional data because it is based on pairwise distances only. Theoretical garantees are provided and an eigenvalue optimisation approach is proposed for computing the embedding. The performance of the method is illustrated via Monte Carlo experiements and comparisons with other embeddings from the literature. |
| Tasks | |
| Published | 2016-06-29 |
| URL | http://arxiv.org/abs/1606.09190v1 |
| http://arxiv.org/pdf/1606.09190v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-definite-programming-approach-to-low |
| Repo | |
| Framework | |
The Life of Lazarillo de Tormes and of His Machine Learning Adversities
| Title | The Life of Lazarillo de Tormes and of His Machine Learning Adversities |
| Authors | Javier de la Rosa, Juan-Luis Suárez |
| Abstract | Summit work of the Spanish Golden Age and forefather of the so-called picaresque novel, The Life of Lazarillo de Tormes and of His Fortunes and Adversities still remains an anonymous text. Although distinguished scholars have tried to attribute it to different authors based on a variety of criteria, a consensus has yet to be reached. The list of candidates is long and not all of them enjoy the same support within the scholarly community. Analyzing their works from a data-driven perspective and applying machine learning techniques for style and text fingerprinting, we shed light on the authorship of the Lazarillo. As in a state-of-the-art survey, we discuss the methods used and how they perform in our specific case. According to our methodology, the most likely author seems to be Juan Arce de Ot'alora, closely followed by Alfonso de Vald'es. The method states that not certain attribution can be made with the given corpus. |
| Tasks | |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05360v1 |
| http://arxiv.org/pdf/1611.05360v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-life-of-lazarillo-de-tormes-and-of-his |
| Repo | |
| Framework | |
Relating Strong Spatial Cognition to Symbolic Problem Solving — An Example
| Title | Relating Strong Spatial Cognition to Symbolic Problem Solving — An Example |
| Authors | Ulrich Furbach, Florian Furbach, Christian Freksa |
| Abstract | In this note, we discuss and analyse a shortest path finding approach using strong spatial cognition. It is compared with a symbolic graph-based algorithm and it is shown that both approaches are similar with respect to structure and complexity. Nevertheless, the strong spatial cognition solution is easy to understand and even pops up immediately when one has to solve the problem. |
| Tasks | |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04397v1 |
| http://arxiv.org/pdf/1606.04397v1.pdf | |
| PWC | https://paperswithcode.com/paper/relating-strong-spatial-cognition-to-symbolic |
| Repo | |
| Framework | |
NN-grams: Unifying neural network and n-gram language models for Speech Recognition
| Title | NN-grams: Unifying neural network and n-gram language models for Speech Recognition |
| Authors | Babak Damavandi, Shankar Kumar, Noam Shazeer, Antoine Bruguier |
| Abstract | We present NN-grams, a novel, hybrid language model integrating n-grams and neural networks (NN) for speech recognition. The model takes as input both word histories as well as n-gram counts. Thus, it combines the memorization capacity and scalability of an n-gram model with the generalization ability of neural networks. We report experiments where the model is trained on 26B words. NN-grams are efficient at run-time since they do not include an output soft-max layer. The model is trained using noise contrastive estimation (NCE), an approach that transforms the estimation problem of neural networks into one of binary classification between data samples and noise samples. We present results with noise samples derived from either an n-gram distribution or from speech recognition lattices. NN-grams outperforms an n-gram model on an Italian speech recognition dictation task. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07470v1 |
| http://arxiv.org/pdf/1606.07470v1.pdf | |
| PWC | https://paperswithcode.com/paper/nn-grams-unifying-neural-network-and-n-gram |
| Repo | |
| Framework | |
The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM
| Title | The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM |
| Authors | Ardavan Saeedi, Matthew Hoffman, Matthew Johnson, Ryan Adams |
| Abstract | We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme. The siHMM is well suited to segmentation problems, where the goal is to identify points at which a time series transitions from one relatively stable regime to a new regime. Conventional iHMMs often struggle with such problems, since they have no mechanism for distinguishing between high- and low-level dynamics. Hierarchical HMMs (HHMMs) can do better, but they require much more complex and expensive inference algorithms. The siHMM retains the simplicity and efficiency of the iHMM, but outperforms it on a variety of segmentation problems, achieving performance that matches or exceeds that of a more complicated HHMM. |
| Tasks | Time Series |
| Published | 2016-02-20 |
| URL | http://arxiv.org/abs/1602.06349v1 |
| http://arxiv.org/pdf/1602.06349v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-segmented-ihmm-a-simple-efficient |
| Repo | |
| Framework | |
Crafting a multi-task CNN for viewpoint estimation
| Title | Crafting a multi-task CNN for viewpoint estimation |
| Authors | Francisco Massa, Renaud Marlet, Mathieu Aubry |
| Abstract | Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a unified setting as well as a detailed analysis of the key factors that impact performance. Followingly, we present a new joint training method with the detection task and demonstrate its benefit. We also highlight the superiority of classification approaches over regression approaches, quantify the benefits of deeper architectures and extended training data, and demonstrate that synthetic data is beneficial even when using ImageNet training data. By combining all these elements, we demonstrate an improvement of approximately 5% mAVP over previous state-of-the-art results on the Pascal3D+ dataset. In particular for their most challenging 24 view classification task we improve the results from 31.1% to 36.1% mAVP. |
| Tasks | Viewpoint Estimation |
| Published | 2016-09-13 |
| URL | http://arxiv.org/abs/1609.03894v1 |
| http://arxiv.org/pdf/1609.03894v1.pdf | |
| PWC | https://paperswithcode.com/paper/crafting-a-multi-task-cnn-for-viewpoint |
| Repo | |
| Framework | |
A Riemannian Network for SPD Matrix Learning
| Title | A Riemannian Network for SPD Matrix Learning |
| Authors | Zhiwu Huang, Luc Van Gool |
| Abstract | Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of underlying SPD manifolds. In this paper we build a Riemannian network architecture to open up a new direction of SPD matrix non-linear learning in a deep model. In particular, we devise bilinear mapping layers to transform input SPD matrices to more desirable SPD matrices, exploit eigenvalue rectification layers to apply a non-linear activation function to the new SPD matrices, and design an eigenvalue logarithm layer to perform Riemannian computing on the resulting SPD matrices for regular output layers. For training the proposed deep network, we exploit a new backpropagation with a variant of stochastic gradient descent on Stiefel manifolds to update the structured connection weights and the involved SPD matrix data. We show through experiments that the proposed SPD matrix network can be simply trained and outperform existing SPD matrix learning and state-of-the-art methods in three typical visual classification tasks. |
| Tasks | |
| Published | 2016-08-15 |
| URL | http://arxiv.org/abs/1608.04233v2 |
| http://arxiv.org/pdf/1608.04233v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-riemannian-network-for-spd-matrix-learning |
| Repo | |
| Framework | |
Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks
| Title | Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks |
| Authors | Noah J. Apthorpe, Alexander J. Riordan, Rob E. Aguilar, Jan Homann, Yi Gu, David W. Tank, H. Sebastian Seung |
| Abstract | Calcium imaging is an important technique for monitoring the activity of thousands of neurons simultaneously. As calcium imaging datasets grow in size, automated detection of individual neurons is becoming important. Here we apply a supervised learning approach to this problem and show that convolutional networks can achieve near-human accuracy and superhuman speed. Accuracy is superior to the popular PCA/ICA method based on precision and recall relative to ground truth annotation by a human expert. These results suggest that convolutional networks are an efficient and flexible tool for the analysis of large-scale calcium imaging data. |
| Tasks | |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07372v2 |
| http://arxiv.org/pdf/1606.07372v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-neuron-detection-in-calcium-imaging |
| Repo | |
| Framework | |
Automatic Discrimination of Color Retinal Images using the Bag of Words Approach
| Title | Automatic Discrimination of Color Retinal Images using the Bag of Words Approach |
| Authors | Ibrahim Sadek |
| Abstract | Diabetic retinopathy (DR) and age related macular degeneration (ARMD) are among the major causes of visual impairment worldwide. DR is mainly characterized by red spots, namely microaneurysms and bright lesions, specifically exudates whereas ARMD is mainly identified by tiny yellow or white deposits called drusen. Since exudates might be the only manifestation of the early diabetic retinopathy, there is an increase demand for automatic retinopathy diagnosis. Exudates and drusen may share similar appearances, thus discriminating between them is of interest to enhance screening performance. In this research, we investigative the role of bag of words approach in the automatic diagnosis of retinopathy diabetes. We proposed to use a single based and multiple based methods for the construction of the visual dictionary by combining the histogram of word occurrences from each dictionary and building a single histogram. The introduced approach is evaluated for automatic diagnosis of normal and abnormal color fundus images with bright lesions. This approach has been implemented on 430 fundus images, including six publicly available datasets, in addition to one local dataset. The mean accuracies reported are 97.2% and 99.77% for single based and multiple based dictionaries respectively. |
| Tasks | |
| Published | 2016-03-14 |
| URL | http://arxiv.org/abs/1603.04327v1 |
| http://arxiv.org/pdf/1603.04327v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-discrimination-of-color-retinal |
| Repo | |
| Framework | |
Destination Prediction by Trajectory Distribution Based Model
| Title | Destination Prediction by Trajectory Distribution Based Model |
| Authors | Philippe C. Besse, Brendan Guillouet, Jean-Michel Loubes, Francois Royer |
| Abstract | In this paper we propose a new method to predict the final destination of vehicle trips based on their initial partial trajectories. We first review how we obtained clustering of trajectories that describes user behaviour. Then, we explain how we model main traffic flow patterns by a mixture of 2d Gaussian distributions. This yielded a density based clustering of locations, which produces a data driven grid of similar points within each pattern. We present how this model can be used to predict the final destination of a new trajectory based on their first locations using a two step procedure: We first assign the new trajectory to the clusters it mot likely belongs. Secondly, we use characteristics from trajectories inside these clusters to predict the final destination. Finally, we present experimental results of our methods for classification of trajectories and final destination prediction on datasets of timestamped GPS-Location of taxi trips. We test our methods on two different datasets, to assess the capacity of our method to adapt automatically to different subsets. |
| Tasks | |
| Published | 2016-05-10 |
| URL | http://arxiv.org/abs/1605.03027v1 |
| http://arxiv.org/pdf/1605.03027v1.pdf | |
| PWC | https://paperswithcode.com/paper/destination-prediction-by-trajectory |
| Repo | |
| Framework | |
Structure vs. Language: Investigating the Multi-factors of Asymmetric Opinions on Online Social Interrelationship with a Case Study
| Title | Structure vs. Language: Investigating the Multi-factors of Asymmetric Opinions on Online Social Interrelationship with a Case Study |
| Authors | Bo Wang, Yingjun Sun, Yuan Wang |
| Abstract | Though current researches often study the properties of online social relationship from an objective view, we also need to understand individuals’ subjective opinions on their interrelationships in social computing studies. Inspired by the theories from sociolinguistics, the latest work indicates that interactive language can reveal individuals’ asymmetric opinions on their interrelationship. In this work, in order to explain the opinions’ asymmetry on interrelationship with more latent factors, we extend the investigation from single relationship to the structural context in online social network. We analyze the correlation between interactive language features and the structural context of interrelationships. The structural context of vertex, edges and triangles in social network are considered. With statistical analysis on Enron email dataset, we find that individuals’ opinions (measured by interactive language features) on their interrelationship are related to some of their important structural context in social network. This result can help us to understand and measure the individuals’ opinions on their interrelationship with more intrinsic information. |
| Tasks | |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00457v1 |
| http://arxiv.org/pdf/1611.00457v1.pdf | |
| PWC | https://paperswithcode.com/paper/structure-vs-language-investigating-the-multi |
| Repo | |
| Framework | |
