Paper Group ANR 298
People Counting in Crowded and Outdoor Scenes using a Hybrid Multi-Camera Approach. A divide and conquer method for symbolic regression. Generalized maximum entropy estimation. Fast Algorithms for Learning Latent Variables in Graphical Models. One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network. …
People Counting in Crowded and Outdoor Scenes using a Hybrid Multi-Camera Approach
| Title | People Counting in Crowded and Outdoor Scenes using a Hybrid Multi-Camera Approach |
| Authors | Fabio Dittrich, Luiz E. S. de Oliveira, Alceu S. Britto Jr., Alessandro L. Koerich |
| Abstract | This paper presents two novel approaches for people counting in crowded and open environments that combine the information gathered by multiple views. Multiple camera are used to expand the field of view as well as to mitigate the problem of occlusion that commonly affects the performance of counting methods using single cameras. The first approach is regarded as a direct approach and it attempts to segment and count each individual in the crowd. For such an aim, two head detectors trained with head images are employed: one based on support vector machines and another based on Adaboost perceptron. The second approach, regarded as an indirect approach employs learning algorithms and statistical analysis on the whole crowd to achieve counting. For such an aim, corner points are extracted from groups of people in a foreground image and computed by a learning algorithm which estimates the number of people in the scene. Both approaches count the number of people on the scene and not only on a given image or video frame of the scene. The experimental results obtained on the benchmark PETS2009 video dataset show that proposed indirect method surpasses other methods with improvements of up to 46.7% and provides accurate counting results for the crowded scenes. On the other hand, the direct method shows high error rates due to the fact that the latter has much more complex problems to solve, such as segmentation of heads. |
| Tasks | |
| Published | 2017-04-02 |
| URL | http://arxiv.org/abs/1704.00326v2 |
| http://arxiv.org/pdf/1704.00326v2.pdf | |
| PWC | https://paperswithcode.com/paper/people-counting-in-crowded-and-outdoor-scenes |
| Repo | |
| Framework | |
A divide and conquer method for symbolic regression
| Title | A divide and conquer method for symbolic regression |
| Authors | Changtong Luo, Chen Chen, Zonglin Jiang |
| Abstract | Symbolic regression aims to find a function that best explains the relationship between independent variables and the objective value based on a given set of sample data. Genetic programming (GP) is usually considered as an appropriate method for the problem since it can optimize functional structure and coefficients simultaneously. However, the convergence speed of GP might be too slow for large scale problems that involve a large number of variables. Fortunately, in many applications, the target function is separable or partially separable. This feature motivated us to develop a new method, divide and conquer (D&C), for symbolic regression, in which the target function is divided into a number of sub-functions and the sub-functions are then determined by any of a GP algorithm. The separability is probed by a new proposed technique, Bi-Correlation test (BiCT). D&C powered GP has been tested on some real-world applications, and the study shows that D&C can help GP to get the target function much more rapidly. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08061v2 |
| http://arxiv.org/pdf/1705.08061v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-divide-and-conquer-method-for-symbolic |
| Repo | |
| Framework | |
Generalized maximum entropy estimation
| Title | Generalized maximum entropy estimation |
| Authors | Tobias Sutter, David Sutter, Peyman Mohajerin Esfahani, John Lygeros |
| Abstract | We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error. We further demonstrate how the presented scheme can be used for approximating the chemical master equation through the zero-information moment closure method, and for an approximate dynamic programming approach in the context of constrained Markov decision processes with uncountable state and action spaces. |
| Tasks | |
| Published | 2017-08-24 |
| URL | https://arxiv.org/abs/1708.07311v3 |
| https://arxiv.org/pdf/1708.07311v3.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-maximum-entropy-estimation |
| Repo | |
| Framework | |
Fast Algorithms for Learning Latent Variables in Graphical Models
| Title | Fast Algorithms for Learning Latent Variables in Graphical Models |
| Authors | Mohammadreza Soltani, Chinmay Hegde |
| Abstract | We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this paper, we focus on the estimation of the low-rank component, which encodes the effect of marginalization over the latent variables. We introduce fast, proper learning algorithms for this problem. In contrast with existing approaches, our algorithms are manifestly non-convex. We support their efficacy via a rigorous theoretical analysis, and show that our algorithms match the best possible in terms of sample complexity, while achieving computational speed-ups over existing methods. We complement our theory with several numerical experiments. |
| Tasks | |
| Published | 2017-06-27 |
| URL | http://arxiv.org/abs/1706.08936v2 |
| http://arxiv.org/pdf/1706.08936v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-algorithms-for-learning-latent-variables |
| Repo | |
| Framework | |
One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
| Title | One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network |
| Authors | Vedran Vukotić, Silvia-Laura Pintea, Christian Raymond, Guillaume Gravier, Jan Van Gemert |
| Abstract | There is an inherent need for autonomous cars, drones, and other robots to have a notion of how their environment behaves and to anticipate changes in the near future. In this work, we focus on anticipating future appearance given the current frame of a video. Existing work focuses on either predicting the future appearance as the next frame of a video, or predicting future motion as optical flow or motion trajectories starting from a single video frame. This work stretches the ability of CNNs (Convolutional Neural Networks) to predict an anticipation of appearance at an arbitrarily given future time, not necessarily the next video frame. We condition our predicted future appearance on a continuous time variable that allows us to anticipate future frames at a given temporal distance, directly from the input video frame. We show that CNNs can learn an intrinsic representation of typical appearance changes over time and successfully generate realistic predictions at a deliberate time difference in the near future. |
| Tasks | Optical Flow Estimation |
| Published | 2017-02-14 |
| URL | http://arxiv.org/abs/1702.04125v2 |
| http://arxiv.org/pdf/1702.04125v2.pdf | |
| PWC | https://paperswithcode.com/paper/one-step-time-dependent-future-video-frame |
| Repo | |
| Framework | |
Towards social pattern characterization in egocentric photo-streams
| Title | Towards social pattern characterization in egocentric photo-streams |
| Authors | Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer, Petia Radeva |
| Abstract | Following the increasingly popular trend of social interaction analysis in egocentric vision, this manuscript presents a comprehensive study for automatic social pattern characterization of a wearable photo-camera user, by relying on the visual analysis of egocentric photo-streams. The proposed framework consists of three major steps. The first step is to detect social interactions of the user where the impact of several social signals on the task is explored. The detected social events are inspected in the second step for categorization into different social meetings. These two steps act at event-level where each potential social event is modeled as a multi-dimensional time-series, whose dimensions correspond to a set of relevant features for each task, and LSTM is employed to classify the time-series. The last step of the framework is to characterize social patterns, which is essentially to infer the diversity and frequency of the social relations of the user through discovery of recurrences of the same people across the whole set of social events of the user. Experimental evaluation over a dataset acquired by 9 users demonstrates promising results on the task of social pattern characterization from egocentric photo-streams. |
| Tasks | Time Series |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01424v3 |
| http://arxiv.org/pdf/1709.01424v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-social-pattern-characterization-in |
| Repo | |
| Framework | |
Stochastic Divergence Minimization for Biterm Topic Model
| Title | Stochastic Divergence Minimization for Biterm Topic Model |
| Authors | Zhenghang Cui, Issei Sato, Masashi Sugiyama |
| Abstract | As the emergence and the thriving development of social networks, a huge number of short texts are accumulated and need to be processed. Inferring latent topics of collected short texts is useful for understanding its hidden structure and predicting new contents. Unlike conventional topic models such as latent Dirichlet allocation (LDA), a biterm topic model (BTM) was recently proposed for short texts to overcome the sparseness of document-level word co-occurrences by directly modeling the generation process of word pairs. Stochastic inference algorithms based on collapsed Gibbs sampling (CGS) and collapsed variational inference have been proposed for BTM. However, they either require large computational complexity, or rely on very crude estimation. In this work, we develop a stochastic divergence minimization inference algorithm for BTM to estimate latent topics more accurately in a scalable way. Experiments demonstrate the superiority of our proposed algorithm compared with existing inference algorithms. |
| Tasks | Topic Models |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00394v1 |
| http://arxiv.org/pdf/1705.00394v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-divergence-minimization-for-biterm |
| Repo | |
| Framework | |
Strongly Hierarchical Factorization Machines and ANOVA Kernel Regression
| Title | Strongly Hierarchical Factorization Machines and ANOVA Kernel Regression |
| Authors | Ruocheng Guo, Hamidreza Alvari, Paulo Shakarian |
| Abstract | High-order parametric models that include terms for feature interactions are applied to various data mining tasks, where ground truth depends on interactions of features. However, with sparse data, the high- dimensional parameters for feature interactions often face three issues: expensive computation, difficulty in parameter estimation and lack of structure. Previous work has proposed approaches which can partially re- solve the three issues. In particular, models with factorized parameters (e.g. Factorization Machines) and sparse learning algorithms (e.g. FTRL-Proximal) can tackle the first two issues but fail to address the third. Regarding to unstructured parameters, constraints or complicated regularization terms are applied such that hierarchical structures can be imposed. However, these methods make the optimization problem more challenging. In this work, we propose Strongly Hierarchical Factorization Machines and ANOVA kernel regression where all the three issues can be addressed without making the optimization problem more difficult. Experimental results show the proposed models significantly outperform the state-of-the-art in two data mining tasks: cold-start user response time prediction and stock volatility prediction. |
| Tasks | Sparse Learning |
| Published | 2017-12-25 |
| URL | http://arxiv.org/abs/1712.09133v2 |
| http://arxiv.org/pdf/1712.09133v2.pdf | |
| PWC | https://paperswithcode.com/paper/strongly-hierarchical-factorization-machines |
| Repo | |
| Framework | |
Unsure When to Stop? Ask Your Semantic Neighbors
| Title | Unsure When to Stop? Ask Your Semantic Neighbors |
| Authors | Ivo Gonçalves, Sara Silva, Carlos M. Fonseca, Mauro Castelli |
| Abstract | In iterative supervised learning algorithms it is common to reach a point in the search where no further induction seems to be possible with the available data. If the search is continued beyond this point, the risk of overfitting increases significantly. Following the recent developments in inductive semantic stochastic methods, this paper studies the feasibility of using information gathered from the semantic neighborhood to decide when to stop the search. Two semantic stopping criteria are proposed and experimentally assessed in Geometric Semantic Genetic Programming (GSGP) and in the Semantic Learning Machine (SLM) algorithm (the equivalent algorithm for neural networks). The experiments are performed on real-world high-dimensional regression datasets. The results show that the proposed semantic stopping criteria are able to detect stopping points that result in a competitive generalization for both GSGP and SLM. This approach also yields computationally efficient algorithms as it allows the evolution of neural networks in less than 3 seconds on average, and of GP trees in at most 10 seconds. The usage of the proposed semantic stopping criteria in conjunction with the computation of optimal mutation/learning steps also results in small trees and neural networks. |
| Tasks | |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.06195v1 |
| http://arxiv.org/pdf/1706.06195v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsure-when-to-stop-ask-your-semantic |
| Repo | |
| Framework | |
Accelerated Sparse Subspace Clustering
| Title | Accelerated Sparse Subspace Clustering |
| Authors | Abolfazl Hashemi, Haris Vikalo |
| Abstract | State-of-the-art algorithms for sparse subspace clustering perform spectral clustering on a similarity matrix typically obtained by representing each data point as a sparse combination of other points using either basis pursuit (BP) or orthogonal matching pursuit (OMP). BP-based methods are often prohibitive in practice while the performance of OMP-based schemes are unsatisfactory, especially in settings where data points are highly similar. In this paper, we propose a novel algorithm that exploits an accelerated variant of orthogonal least-squares to efficiently find the underlying subspaces. We show that under certain conditions the proposed algorithm returns a subspace-preserving solution. Simulation results illustrate that the proposed method compares favorably with BP-based method in terms of running time while being significantly more accurate than OMP-based schemes. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00126v1 |
| http://arxiv.org/pdf/1711.00126v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-sparse-subspace-clustering |
| Repo | |
| Framework | |
Individual Recognition in Schizophrenia using Deep Learning Methods with Random Forest and Voting Classifiers: Insights from Resting State EEG Streams
| Title | Individual Recognition in Schizophrenia using Deep Learning Methods with Random Forest and Voting Classifiers: Insights from Resting State EEG Streams |
| Authors | Lei Chu, Robert Qiu, Haichun Liu, Zenan Ling, Tianhong Zhang, Jijun Wang |
| Abstract | Recently, there has been a growing interest in monitoring brain activity for individual recognition system. So far these works are mainly focussing on single channel data or fragment data collected by some advanced brain monitoring modalities. In this study we propose new individual recognition schemes based on spatio-temporal resting state Electroencephalography (EEG) data. Besides, instead of using features derived from artificially-designed procedures, modified deep learning architectures which aim to automatically extract an individual’s unique features are developed to conduct classification. Our designed deep learning frameworks are proved of a small but consistent advantage of replacing the $softmax$ layer with Random Forest. Additionally, a voting layer is added at the top of designed neural networks in order to tackle the classification problem arisen from EEG streams. Lastly, various experiments are implemented to evaluate the performance of the designed deep learning architectures; Results indicate that the proposed EEG-based individual recognition scheme yields a high degree of classification accuracy: $81.6%$ for characteristics in high risk (CHR) individuals, $96.7%$ for clinically stable first episode patients with schizophrenia (FES) and $99.2%$ for healthy controls (HC). |
| Tasks | EEG |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1707.03467v2 |
| http://arxiv.org/pdf/1707.03467v2.pdf | |
| PWC | https://paperswithcode.com/paper/individual-recognition-in-schizophrenia-using |
| Repo | |
| Framework | |
Convolutional neural networks for segmentation and object detection of human semen
| Title | Convolutional neural networks for segmentation and object detection of human semen |
| Authors | Malte Stær Nissen, Oswin Krause, Kristian Almstrup, Søren Kjærulff, Torben Trindkær Nielsen, Mads Nielsen |
| Abstract | We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due to clutter. Our results indicate that training on full images is superior to training on patches when class-skew is properly handled. Full image training including up-sampling during training proves to be beneficial in deep CNNs for pixel wise accuracy and detection performance. Predicted sperm cells are found by using connected components on the CNN predictions. We investigate optimization of a threshold parameter on the size of detected components. Our best network achieves 93.87% precision and 91.89% recall on our test dataset after thresholding outperforming a classical mage analysis approach. |
| Tasks | Object Detection |
| Published | 2017-04-03 |
| URL | http://arxiv.org/abs/1704.00498v1 |
| http://arxiv.org/pdf/1704.00498v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for |
| Repo | |
| Framework | |
Computational Eco-Systems for Handwritten Digits Recognition
| Title | Computational Eco-Systems for Handwritten Digits Recognition |
| Authors | Antonio Loquercio, Francesca Della Torre, Massimo Buscema |
| Abstract | Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convolutional Neural Networks, currently the state-of-the-art technique for this task, among with other traditional and innovative machine learning techniques. Then, we optimally combine them through Meta-Nets, a family of recently developed and performing ensemble methods. |
| Tasks | |
| Published | 2017-03-06 |
| URL | http://arxiv.org/abs/1703.01872v2 |
| http://arxiv.org/pdf/1703.01872v2.pdf | |
| PWC | https://paperswithcode.com/paper/computational-eco-systems-for-handwritten |
| Repo | |
| Framework | |
A Dependency-Based Neural Reordering Model for Statistical Machine Translation
| Title | A Dependency-Based Neural Reordering Model for Statistical Machine Translation |
| Authors | Christian Hadiwinoto, Hwee Tou Ng |
| Abstract | In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network and dependency-based embeddings to predict whether the translations of two source words linked by a dependency relation should remain in the same order or should be swapped in the translated sentence. Experiments on Chinese-to-English translation show that our approach yields a statistically significant improvement of 0.57 BLEU point on benchmark NIST test sets, compared to our prior state-of-the-art statistical MT system that uses sparse dependency-based reordering features. |
| Tasks | Machine Translation |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04510v1 |
| http://arxiv.org/pdf/1702.04510v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dependency-based-neural-reordering-model |
| Repo | |
| Framework | |
Genetic Algorithm with Optimal Recombination for the Asymmetric Travelling Salesman Problem
| Title | Genetic Algorithm with Optimal Recombination for the Asymmetric Travelling Salesman Problem |
| Authors | A. V. Eremeev, Yu. V. Kovalenko |
| Abstract | We propose a new genetic algorithm with optimal recombination for the asymmetric instances of travelling salesman problem. The algorithm incorporates several new features that contribute to its effectiveness: (i) Optimal recombination problem is solved within crossover operator. (ii) A new mutation operator performs a random jump within 3-opt or 4-opt neighborhood. (iii) Greedy constructive heuristic of W.Zhang and 3-opt local search heuristic are used to generate the initial population. A computational experiment on TSPLIB instances shows that the proposed algorithm yields competitive results to other well-known memetic algorithms for asymmetric travelling salesman problem. |
| Tasks | |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06920v2 |
| http://arxiv.org/pdf/1706.06920v2.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-algorithm-with-optimal-recombination |
| Repo | |
| Framework | |
