Paper Group ANR 728
Sequence to Sequence Learning for Event Prediction. Solving differential equations with unknown constitutive relations as recurrent neural networks. Structured Black Box Variational Inference for Latent Time Series Models. Single-trial P300 Classification using PCA with LDA, QDA and Neural Networks. Rotational Subgroup Voting and Pose Clustering fo …
Sequence to Sequence Learning for Event Prediction
| Title | Sequence to Sequence Learning for Event Prediction |
| Authors | Dai Quoc Nguyen, Dat Quoc Nguyen, Cuong Xuan Chu, Stefan Thater, Manfred Pinkal |
| Abstract | This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively. Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events. |
| Tasks | |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.06033v1 |
| http://arxiv.org/pdf/1709.06033v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-to-sequence-learning-for-event |
| Repo | |
| Framework | |
Solving differential equations with unknown constitutive relations as recurrent neural networks
| Title | Solving differential equations with unknown constitutive relations as recurrent neural networks |
| Authors | Tobias Hagge, Panos Stinis, Enoch Yeung, Alexandre M. Tartakovsky |
| Abstract | We solve a system of ordinary differential equations with an unknown functional form of a sink (reaction rate) term. We assume that the measurements (time series) of state variables are partially available, and we use recurrent neural network to “learn” the reaction rate from this data. This is achieved by including a discretized ordinary differential equations as part of a recurrent neural network training problem. We extend TensorFlow’s recurrent neural network architecture to create a simple but scalable and effective solver for the unknown functions, and apply it to a fedbatch bioreactor simulation problem. Use of techniques from recent deep learning literature enables training of functions with behavior manifesting over thousands of time steps. Our networks are structurally similar to recurrent neural networks, but differences in design and function require modifications to the conventional wisdom about training such networks. |
| Tasks | Time Series |
| Published | 2017-10-06 |
| URL | http://arxiv.org/abs/1710.02242v1 |
| http://arxiv.org/pdf/1710.02242v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-differential-equations-with-unknown |
| Repo | |
| Framework | |
Structured Black Box Variational Inference for Latent Time Series Models
| Title | Structured Black Box Variational Inference for Latent Time Series Models |
| Authors | Robert Bamler, Stephan Mandt |
| Abstract | Continuous latent time series models are prevalent in Bayesian modeling; examples include the Kalman filter, dynamic collaborative filtering, or dynamic topic models. These models often benefit from structured, non mean field variational approximations that capture correlations between time steps. Black box variational inference with reparameterization gradients (BBVI) allows us to explore a rich new class of Bayesian non-conjugate latent time series models; however, a naive application of BBVI to such structured variational models would scale quadratically in the number of time steps. We describe a BBVI algorithm analogous to the forward-backward algorithm which instead scales linearly in time. It allows us to efficiently sample from the variational distribution and estimate the gradients of the ELBO. Finally, we show results on the recently proposed dynamic word embedding model, which was trained using our method. |
| Tasks | Time Series, Topic Models |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.01069v1 |
| http://arxiv.org/pdf/1707.01069v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-black-box-variational-inference |
| Repo | |
| Framework | |
Single-trial P300 Classification using PCA with LDA, QDA and Neural Networks
| Title | Single-trial P300 Classification using PCA with LDA, QDA and Neural Networks |
| Authors | Nand Sharma |
| Abstract | The P300 event-related potential (ERP), evoked in scalp-recorded electroencephalography (EEG) by external stimuli, has proven to be a reliable response for controlling a BCI. The P300 component of an event related potential is thus widely used in brain-computer interfaces to translate the subjects’ intent by mere thoughts into commands to control artificial devices. The main challenge in the classification of P300 trials in electroencephalographic (EEG) data is the low signal-to-noise ratio (SNR) of the P300 response. To overcome the low SNR of individual trials, it is common practice to average together many consecutive trials, which effectively diminishes the random noise. Unfortunately, when more repeated trials are required for applications such as the P300 speller, the communication rate is greatly reduced. This has resulted in a need for better methods to improve single-trial classification accuracy of P300 response. In this work, we use Principal Component Analysis (PCA) as a preprocessing method and use Linear Discriminant Analysis (LDA)and neural networks for classification. The results show that a combination of PCA with these methods provided as high as 13% accuracy gain for single-trial classification while using only 3 to 4 principal components. |
| Tasks | EEG |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.01977v1 |
| http://arxiv.org/pdf/1712.01977v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-trial-p300-classification-using-pca |
| Repo | |
| Framework | |
Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition
| Title | Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition |
| Authors | Anders Glent Buch, Lilita Kiforenko, Dirk Kraft |
| Abstract | It is possible to associate a highly constrained subset of relative 6 DoF poses between two 3D shapes, as long as the local surface orientation, the normal vector, is available at every surface point. Local shape features can be used to find putative point correspondences between the models due to their ability to handle noisy and incomplete data. However, this correspondence set is usually contaminated by outliers in practical scenarios, which has led to many past contributions based on robust detectors such as the Hough transform or RANSAC. The key insight of our work is that a single correspondence between oriented points on the two models is constrained to cast votes in a 1 DoF rotational subgroup of the full group of poses, SE(3). Kernel density estimation allows combining the set of votes efficiently to determine a full 6 DoF candidate pose between the models. This modal pose with the highest density is stable under challenging conditions, such as noise, clutter, and occlusions, and provides the output estimate of our method. We first analyze the robustness of our method in relation to noise and show that it handles high outlier rates much better than RANSAC for the task of 6 DoF pose estimation. We then apply our method to four state of the art data sets for 3D object recognition that contain occluded and cluttered scenes. Our method achieves perfect recall on two LIDAR data sets and outperforms competing methods on two RGB-D data sets, thus setting a new standard for general 3D object recognition using point cloud data. |
| Tasks | 3D Object Recognition, Density Estimation, Object Recognition, Pose Estimation |
| Published | 2017-09-07 |
| URL | http://arxiv.org/abs/1709.02142v1 |
| http://arxiv.org/pdf/1709.02142v1.pdf | |
| PWC | https://paperswithcode.com/paper/rotational-subgroup-voting-and-pose |
| Repo | |
| Framework | |
Can We Boost the Power of the Viola-Jones Face Detector Using Pre-processing? An Empirical Study
| Title | Can We Boost the Power of the Viola-Jones Face Detector Using Pre-processing? An Empirical Study |
| Authors | Mahmoud Afifi, Marwa Nasser, Mostafa Korashy, Katherine Rohde, Aly Abdelrahim |
| Abstract | The Viola-Jones face detection algorithm was (and still is) a quite popular face detector. In spite of the numerous face detection techniques that have been recently presented, there are many research works that are still based on the Viola-Jones algorithm because of its simplicity. In this paper, we study the influence of a set of blind pre-processing methods on the face detection rate using the Viola-Jones algorithm. We focus on two aspects of improvement, specifically badly illuminated faces and blurred faces. Many methods for lighting invariant and deblurring are used in order to improve the detection accuracy. We want to avoid using blind pre-processing methods that may obstruct the face detector. To that end, we perform two sets of experiments. The first set is performed to avoid any blind pre-processing method that may hurt the face detector. The second set is performed to study the effect of the selected pre-processing methods on images that suffer from hard conditions. We present two manners of applying the pre-processing method to the image prior to being used by the Viola-Jones face detector. Four different datasets are used to draw a coherent conclusion about the potential improvement caused by using prior enhanced images. The results demonstrate that some of the pre-processing methods may hurt the accuracy of Viola-Jones face detection algorithm. However, other pre-processing methods have an evident positive impact on the accuracy of the face detector. Overall, we recommend three simple and fast blind photometric normalization methods as a pre-processing step in order to improve the accuracy of the pre-trained Viola-Jones face detector. |
| Tasks | Deblurring, Face Detection |
| Published | 2017-09-22 |
| URL | http://arxiv.org/abs/1709.07720v3 |
| http://arxiv.org/pdf/1709.07720v3.pdf | |
| PWC | https://paperswithcode.com/paper/can-we-boost-the-power-of-the-viola-jones |
| Repo | |
| Framework | |
Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition
| Title | Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition |
| Authors | Gee-Sern, Hsu, Hung-Cheng Shie, Cheng-Hua Hsieh |
| Abstract | Two approaches are proposed for cross-pose face recognition, one is based on the 3D reconstruction of facial components and the other is based on the deep Convolutional Neural Network (CNN). Unlike most 3D approaches that consider holistic faces, the proposed approach considers 3D facial components. It segments a 2D gallery face into components, reconstructs the 3D surface for each component, and recognizes a probe face by component features. The segmentation is based on the landmarks located by a hierarchical algorithm that combines the Faster R-CNN for face detection and the Reduced Tree Structured Model for landmark localization. The core part of the CNN-based approach is a revised VGG network. We study the performances with different settings on the training set, including the synthesized data from 3D reconstruction, the real-life data from an in-the-wild database, and both types of data combined. We investigate the performances of the network when it is employed as a classifier or designed as a feature extractor. The two recognition approaches and the fast landmark localization are evaluated in extensive experiments, and compared to stateof-the-art methods to demonstrate their efficacy. |
| Tasks | 3D Reconstruction, Face Detection, Face Recognition |
| Published | 2017-08-31 |
| URL | http://arxiv.org/abs/1708.09580v1 |
| http://arxiv.org/pdf/1708.09580v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-landmark-localization-with-3d-component |
| Repo | |
| Framework | |
Interacting Conceptual Spaces I : Grammatical Composition of Concepts
| Title | Interacting Conceptual Spaces I : Grammatical Composition of Concepts |
| Authors | Joe Bolt, Bob Coecke, Fabrizio Genovese, Martha Lewis, Dan Marsden, Robin Piedeleu |
| Abstract | The categorical compositional approach to meaning has been successfully applied in natural language processing, outperforming other models in mainstream empirical language processing tasks. We show how this approach can be generalized to conceptual space models of cognition. In order to do this, first we introduce the category of convex relations as a new setting for categorical compositional semantics, emphasizing the convex structure important to conceptual space applications. We then show how to construct conceptual spaces for various types such as nouns, adjectives and verbs. Finally we show by means of examples how concepts can be systematically combined to establish the meanings of composite phrases from the meanings of their constituent parts. This provides the mathematical underpinnings of a new compositional approach to cognition. |
| Tasks | |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.08314v2 |
| http://arxiv.org/pdf/1703.08314v2.pdf | |
| PWC | https://paperswithcode.com/paper/interacting-conceptual-spaces-i-grammatical |
| Repo | |
| Framework | |
A Survey of Efficient Regression of General-Activity Human Poses from Depth Images
| Title | A Survey of Efficient Regression of General-Activity Human Poses from Depth Images |
| Authors | Wenye He |
| Abstract | This paper presents a comprehensive review on regression-based method for human pose estimation. The problem of human pose estimation has been intensively studied and enabled many application from entertainment to training. Traditional methods often rely on color image only which cannot completely ambiguity of joint 3D position, especially in the complex context. With the popularity of depth sensors, the precision of 3D estimation has significant improvement. In this paper, we give a detailed analysis of state-of-the-art on human pose estimation, including depth image based and RGB-D based approaches. The experimental results demonstrate their advantages and limitation for different scenarios. |
| Tasks | Pose Estimation |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.02246v1 |
| http://arxiv.org/pdf/1709.02246v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-efficient-regression-of-general |
| Repo | |
| Framework | |
Network Model Selection for Task-Focused Attributed Network Inference
| Title | Network Model Selection for Task-Focused Attributed Network Inference |
| Authors | Ivan Brugere, Chris Kanich, Tanya Y. Berger-Wolf |
| Abstract | Networks are models representing relationships between entities. Often these relationships are explicitly given, or we must learn a representation which generalizes and predicts observed behavior in underlying individual data (e.g. attributes or labels). Whether given or inferred, choosing the best representation affects subsequent tasks and questions on the network. This work focuses on model selection to evaluate network representations from data, focusing on fundamental predictive tasks on networks. We present a modular methodology using general, interpretable network models, task neighborhood functions found across domains, and several criteria for robust model selection. We demonstrate our methodology on three online user activity datasets and show that network model selection for the appropriate network task vs. an alternate task increases performance by an order of magnitude in our experiments. |
| Tasks | Model Selection |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06303v2 |
| http://arxiv.org/pdf/1708.06303v2.pdf | |
| PWC | https://paperswithcode.com/paper/network-model-selection-for-task-focused |
| Repo | |
| Framework | |
Beyond SIFT using Binary features for Loop Closure Detection
| Title | Beyond SIFT using Binary features for Loop Closure Detection |
| Authors | Lei Han, Guyue Zhou, Lan Xu, Lu Fang |
| Abstract | In this paper a binary feature based Loop Closure Detection (LCD) method is proposed, which for the first time achieves higher precision-recall (PR) performance compared with state-of-the-art SIFT feature based approaches. The proposed system originates from our previous work Multi-Index hashing for Loop closure Detection (MILD), which employs Multi-Index Hashing (MIH)~\cite{greene1994multi} for Approximate Nearest Neighbor (ANN) search of binary features. As the accuracy of MILD is limited by repeating textures and inaccurate image similarity measurement, burstiness handling is introduced to solve this problem and achieves considerable accuracy improvement. Additionally, a comprehensive theoretical analysis on MIH used in MILD is conducted to further explore the potentials of hashing methods for ANN search of binary features from probabilistic perspective. This analysis provides more freedom on best parameter choosing in MIH for different application scenarios. Experiments on popular public datasets show that the proposed approach achieved the highest accuracy compared with state-of-the-art while running at 30Hz for databases containing thousands of images. |
| Tasks | Loop Closure Detection |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.05833v1 |
| http://arxiv.org/pdf/1709.05833v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-sift-using-binary-features-for-loop |
| Repo | |
| Framework | |
Improved Face Detection and Alignment using Cascade Deep Convolutional Network
| Title | Improved Face Detection and Alignment using Cascade Deep Convolutional Network |
| Authors | Weilin Cong, Sanyuan Zhao, Hui Tian, Jianbing Shen |
| Abstract | Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and alignment methods have been proposed. Recent studies have utilized the relation between face detection and alignment to make models computationally efficiency, however they ignore the connection between each cascade CNNs. In this paper, we propose an structure to propose higher quality training data for End-to-End cascade network training, which give computers more space to automatic adjust weight parameter and accelerate convergence. Experiments demonstrate considerable improvement over existing detection and alignment models. |
| Tasks | Face Detection |
| Published | 2017-07-28 |
| URL | http://arxiv.org/abs/1707.09364v1 |
| http://arxiv.org/pdf/1707.09364v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-face-detection-and-alignment-using |
| Repo | |
| Framework | |
Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition
| Title | Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition |
| Authors | Yong Jiang, Wenjuan Han, Kewei Tu |
| Abstract | Unsupervised dependency parsing aims to learn a dependency parser from unannotated sentences. Existing work focuses on either learning generative models using the expectation-maximization algorithm and its variants, or learning discriminative models using the discriminative clustering algorithm. In this paper, we propose a new learning strategy that learns a generative model and a discriminative model jointly based on the dual decomposition method. Our method is simple and general, yet effective to capture the advantages of both models and improve their learning results. We tested our method on the UD treebank and achieved a state-of-the-art performance on thirty languages. |
| Tasks | Dependency Grammar Induction |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00790v2 |
| http://arxiv.org/pdf/1708.00790v2.pdf | |
| PWC | https://paperswithcode.com/paper/combining-generative-and-discriminative-1 |
| Repo | |
| Framework | |
What Weights Work for You? Adapting Weights for Any Pareto Front Shape in Decomposition-based Evolutionary Multi-Objective Optimisation
| Title | What Weights Work for You? Adapting Weights for Any Pareto Front Shape in Decomposition-based Evolutionary Multi-Objective Optimisation |
| Authors | Miqing Li, Xin Yao |
| Abstract | The quality of solution sets generated by decomposition-based evolutionary multiobjective optimisation (EMO) algorithms depends heavily on the consistency between a given problem’s Pareto front shape and the specified weights’ distribution. A set of weights distributed uniformly in a simplex often lead to a set of well-distributed solutions on a Pareto front with a simplex-like shape, but may fail on other Pareto front shapes. It is an open problem on how to specify a set of appropriate weights without the information of the problem’s Pareto front beforehand. In this paper, we propose an approach to adapt the weights during the evolutionary process (called AdaW). AdaW progressively seeks a suitable distribution of weights for the given problem by elaborating five parts in the weight adaptation — weight generation, weight addition, weight deletion, archive maintenance, and weight update frequency. Experimental results have shown the effectiveness of the proposed approach. AdaW works well for Pareto fronts with very different shapes: 1) the simplex-like, 2) the inverted simplex-like, 3) the highly nonlinear, 4) the disconnect, 5) the degenerated, 6) the badly-scaled, and 7) the high-dimensional. |
| Tasks | |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02679v1 |
| http://arxiv.org/pdf/1709.02679v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-weights-work-for-you-adapting-weights |
| Repo | |
| Framework | |
Automatic tracking of vessel-like structures from a single starting point
| Title | Automatic tracking of vessel-like structures from a single starting point |
| Authors | Dario Augusto Borges Oliveira, Laura Leal-Taixe, Raul Queiroz Feitosa, Bodo Rosenhahn |
| Abstract | The identification of vascular networks is an important topic in the medical image analysis community. While most methods focus on single vessel tracking, the few solutions that exist for tracking complete vascular networks are usually computationally intensive and require a lot of user interaction. In this paper we present a method to track full vascular networks iteratively using a single starting point. Our approach is based on a cloud of sampling points distributed over concentric spherical layers. We also proposed a vessel model and a metric of how well a sample point fits this model. Then, we implement the network tracking as a min-cost flow problem, and propose a novel optimization scheme to iteratively track the vessel structure by inherently handling bifurcations and paths. The method was tested using both synthetic and real images. On the 9 different data-sets of synthetic blood vessels, we achieved maximum accuracies of more than 98%. We further use the synthetic data-set to analyse the sensibility of our method to parameter setting, showing the robustness of the proposed algorithm. For real images, we used coronary, carotid and pulmonary data to segment vascular structures and present the visual results. Still for real images, we present numerical and visual results for networks of nerve fibers in the olfactory system. Further visual results also show the potential of our approach for identifying vascular networks topologies. The presented method delivers good results for the several different datasets tested and have potential for segmenting vessel-like structures. Also, the topology information, inherently extracted, can be used for further analysis to computed aided diagnosis and surgical planning. Finally, the method’s modular aspect holds potential for problem-oriented adjustments and improvements. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02434v1 |
| http://arxiv.org/pdf/1706.02434v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-tracking-of-vessel-like-structures |
| Repo | |
| Framework | |
