July 28, 2019

2878 words 14 mins read

Paper Group ANR 345

Learning 2D Gabor Filters by Infinite Kernel Learning Regression. Adiabatic Quantum Computing for Binary Clustering. Extractive Multi-document Summarization Using Multilayer Networks. Towards a theory of word order. Comment on “Dependency distance: a new perspective on syntactic patterns in natural language” by Haitao Liu et al. Feature Mapping for …

Learning 2D Gabor Filters by Infinite Kernel Learning Regression


Title	Learning 2D Gabor Filters by Infinite Kernel Learning Regression
Authors	Kamaledin Ghiasi-Shirazi
Abstract	Gabor functions have wide-spread applications in image processing and computer vision. In this paper, we prove that 2D Gabor functions are translation-invariant positive-definite kernels and propose a novel formulation for the problem of image representation with Gabor functions based on infinite kernel learning regression. Using this formulation, we obtain a support vector expansion of an image based on a mixture of Gabor functions. The problem with this representation is that all Gabor functions are present at all support vector pixels. Applying LASSO to this support vector expansion, we obtain a sparse representation in which each Gabor function is positioned at a very small set of pixels. As an application, we introduce a method for learning a dataset-specific set of Gabor filters that can be used subsequently for feature extraction. Our experiments show that use of the learned Gabor filters improves the recognition accuracy of a recently introduced face recognition algorithm.
Tasks	Face Recognition
Published	2017-12-08
URL	http://arxiv.org/abs/1712.02974v1
PDF	http://arxiv.org/pdf/1712.02974v1.pdf
PWC	https://paperswithcode.com/paper/learning-2d-gabor-filters-by-infinite-kernel
Repo
Framework

Adiabatic Quantum Computing for Binary Clustering


Title	Adiabatic Quantum Computing for Binary Clustering
Authors	Christian Bauckhage, Eduardo Brito, Kostadin Cvejoski, Cesar Ojeda, Rafet Sifa, Stefan Wrobel
Abstract	Quantum computing for machine learning attracts increasing attention and recent technological developments suggest that especially adiabatic quantum computing may soon be of practical interest. In this paper, we therefore consider this paradigm and discuss how to adopt it to the problem of binary clustering. Numerical simulations demonstrate the feasibility of our approach and illustrate how systems of qubits adiabatically evolve towards a solution.
Tasks
Published	2017-06-17
URL	http://arxiv.org/abs/1706.05528v1
PDF	http://arxiv.org/pdf/1706.05528v1.pdf
PWC	https://paperswithcode.com/paper/adiabatic-quantum-computing-for-binary
Repo
Framework

Extractive Multi-document Summarization Using Multilayer Networks


Title	Extractive Multi-document Summarization Using Multilayer Networks
Authors	Jorge V. Tohalino, Diego R. Amancio
Abstract	Huge volumes of textual information has been produced every single day. In order to organize and understand such large datasets, in recent years, summarization techniques have become popular. These techniques aims at finding relevant, concise and non-redundant content from such a big data. While network methods have been adopted to model texts in some scenarios, a systematic evaluation of multilayer network models in the multi-document summarization task has been limited to a few studies. Here, we evaluate the performance of a multilayer-based method to select the most relevant sentences in the context of an extractive multi document summarization (MDS) task. In the adopted model, nodes represent sentences and edges are created based on the number of shared words between sentences. Differently from previous studies in multi-document summarization, we make a distinction between edges linking sentences from different documents (inter-layer) and those connecting sentences from the same document (intra-layer). As a proof of principle, our results reveal that such a discrimination between intra- and inter-layer in a multilayered representation is able to improve the quality of the generated summaries. This piece of information could be used to improve current statistical methods and related textual models.
Tasks	Document Summarization, Multi-Document Summarization
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02608v1
PDF	http://arxiv.org/pdf/1711.02608v1.pdf
PWC	https://paperswithcode.com/paper/extractive-multi-document-summarization-using
Repo
Framework

Towards a theory of word order. Comment on “Dependency distance: a new perspective on syntactic patterns in natural language” by Haitao Liu et al


Title	Towards a theory of word order. Comment on “Dependency distance: a new perspective on syntactic patterns in natural language” by Haitao Liu et al
Authors	Ramon Ferrer-i-Cancho
Abstract	Comment on “Dependency distance: a new perspective on syntactic patterns in natural language” by Haitao Liu et al
Tasks
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04872v1
PDF	http://arxiv.org/pdf/1706.04872v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-theory-of-word-order-comment-on
Repo
Framework

Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images


Title	Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
Authors	Mahdi Rad, Markus Oberweger, Vincent Lepetit
Abstract	We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome. However, synthetic images do not resemble real images exactly, and using them for training can result in suboptimal performance. It was recently shown that for exemplar-based approaches, it is possible to learn a mapping from the exemplar representations of real images to the exemplar representations of synthetic images. In this paper, we show that this approach is more general, and that a network can also be applied after the mapping to infer a 3D pose: At run time, given a real image of the target object, we first compute the features for the image, map them to the feature space of synthetic images, and finally use the resulting features as input to another network which predicts the 3D pose. Since this network can be trained very effectively by using synthetic images, it performs very well in practice, and inference is faster and more accurate than with an exemplar-based approach. We demonstrate our approach on the LINEMOD dataset for 3D object pose estimation from color images, and the NYU dataset for 3D hand pose estimation from depth maps. We show that it allows us to outperform the state-of-the-art on both datasets.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03904v2
PDF	http://arxiv.org/pdf/1712.03904v2.pdf
PWC	https://paperswithcode.com/paper/feature-mapping-for-learning-fast-and
Repo
Framework

An evidential Markov decision making model


Title	An evidential Markov decision making model
Authors	Zichang He, Wen Jiang
Abstract	The sure thing principle and the law of total probability are basic laws in classic probability theory. A disjunction fallacy leads to the violation of these two classical laws. In this paper, an Evidential Markov (EM) decision making model based on Dempster-Shafer (D-S) evidence theory and Markov modelling is proposed to address this issue and model the real human decision-making process. In an evidential framework, the states are extended by introducing an uncertain state which represents the hesitance of a decision maker. The classical Markov model can not produce the disjunction effect, which assumes that a decision has to be certain at one time. However, the state is allowed to be uncertain in the EM model before the final decision is made. An extra uncertainty degree parameter is defined by a belief entropy, named Deng entropy, to assignment the basic probability assignment of the uncertain state, which is the key to predict the disjunction effect. A classical categorization decision-making experiment is used to illustrate the effectiveness and validity of EM model. The disjunction effect can be well predicted and the free parameters are less compared with the existing models.
Tasks	Decision Making
Published	2017-05-10
URL	http://arxiv.org/abs/1705.06578v1
PDF	http://arxiv.org/pdf/1705.06578v1.pdf
PWC	https://paperswithcode.com/paper/an-evidential-markov-decision-making-model
Repo
Framework

Using a single RGB frame for real time 3D hand pose estimation in the wild


Title	Using a single RGB frame for real time 3D hand pose estimation in the wild
Authors	Paschalis Panteleris, Iason Oikonomidis, Antonis Argyros
Abstract	We present a method for the real-time estimation of the full 3D pose of one or more human hands using a single commodity RGB camera. Recent work in the area has displayed impressive progress using RGBD input. However, since the introduction of RGBD sensors, there has been little progress for the case of monocular color input. We capitalize on the latest advancements of deep learning, combining them with the power of generative hand pose estimation techniques to achieve real-time monocular 3D hand pose estimation in unrestricted scenarios. More specifically, given an RGB image and the relevant camera calibration information, we employ a state-of-the-art detector to localize hands. Given a crop of a hand in the image, we run the pretrained network of OpenPose for hands to estimate the 2D location of hand joints. Finally, non-linear least-squares minimization fits a 3D model of the hand to the estimated 2D joint positions, recovering the 3D hand pose. Extensive experimental results provide comparison to the state of the art as well as qualitative assessment of the method in the wild.
Tasks	Calibration, Hand Pose Estimation, Pose Estimation
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03866v1
PDF	http://arxiv.org/pdf/1712.03866v1.pdf
PWC	https://paperswithcode.com/paper/using-a-single-rgb-frame-for-real-time-3d
Repo
Framework

Learning Neural Network Classifiers with Low Model Complexity


Title	Learning Neural Network Classifiers with Low Model Complexity
Authors	Jayadeva, Himanshu Pant, Mayank Sharma, Abhimanyu Dubey, Sumit Soman, Suraj Tripathi, Sai Guruju, Nihal Goalla
Abstract	Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning techniques have focused on architectural modifications to improve parameter efficiency and performance. In this paper, we derive a continuous and differentiable error functional for a neural network that minimizes its empirical error as well as a measure of the model complexity. The latter measure is obtained by deriving a differentiable upper bound on the Vapnik-Chervonenkis (VC) dimension of the classifier layer of a class of deep networks. Using standard backpropagation, we realize a training rule that tries to minimize the error on training samples, while improving generalization by keeping the model complexity low. We demonstrate the effectiveness of our formulation (the Low Complexity Neural Network - LCNN) across several deep learning algorithms, and a variety of large benchmark datasets. We show that hidden layer neurons in the resultant networks learn features that are crisp, and in the case of image datasets, quantitatively sharper. Our proposed approach yields benefits across a wide range of architectures, in comparison to and in conjunction with methods such as Dropout and Batch Normalization, and our results strongly suggest that deep learning techniques can benefit from model complexity control methods such as the LCNN learning rule.
Tasks
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09933v2
PDF	http://arxiv.org/pdf/1707.09933v2.pdf
PWC	https://paperswithcode.com/paper/learning-neural-network-classifiers-with-low
Repo
Framework

Sentiment Classification using Images and Label Embeddings


Title	Sentiment Classification using Images and Label Embeddings
Authors	Laura Graesser, Abhinav Gupta, Lakshay Sharma, Evelina Bakhturina
Abstract	In this project we analysed how much semantic information images carry, and how much value image data can add to sentiment analysis of the text associated with the images. To better understand the contribution from images, we compared models which only made use of image data, models which only made use of text data, and models which combined both data types. We also analysed if this approach could help sentiment classifiers generalize to unknown sentiments.
Tasks	Sentiment Analysis
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00725v1
PDF	http://arxiv.org/pdf/1712.00725v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-classification-using-images-and
Repo
Framework

Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image


Title	Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
Authors	Jameel Malik, Ahmed Elhayek, Didier Stricker
Abstract	Articulated hand pose estimation is a challenging task for human-computer interaction. The state-of-the-art hand pose estimation algorithms work only with one or a few subjects for which they have been calibrated or trained. Particularly, the hybrid methods based on learning followed by model fitting or model based deep learning do not explicitly consider varying hand shapes and sizes. In this work, we introduce a novel hybrid algorithm for estimating the 3D hand pose as well as bone-lengths of the hand skeleton at the same time, from a single depth image. The proposed CNN architecture learns hand pose parameters and scale parameters associated with the bone-lengths simultaneously. Subsequently, a new hybrid forward kinematics layer employs both parameters to estimate 3D joint positions of the hand. For end-to-end training, we combine three public datasets NYU, ICVL and MSRA-2015 in one unified format to achieve large variation in hand shapes and sizes. Among hybrid methods, our method shows improved accuracy over the state-of-the-art on the combined dataset and the ICVL dataset that contain multiple subjects. Also, our algorithm is demonstrated to work well with unseen images.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03121v1
PDF	http://arxiv.org/pdf/1712.03121v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-hand-pose-and-skeleton-bone
Repo
Framework

Parameter Estimation in Finite Mixture Models by Regularized Optimal Transport: A Unified Framework for Hard and Soft Clustering


Title	Parameter Estimation in Finite Mixture Models by Regularized Optimal Transport: A Unified Framework for Hard and Soft Clustering
Authors	Arnaud Dessein, Nicolas Papadakis, Charles-Alban Deledalle
Abstract	In this short paper, we formulate parameter estimation for finite mixture models in the context of discrete optimal transportation with convex regularization. The proposed framework unifies hard and soft clustering methods for general mixture models. It also generalizes the celebrated $k$\nobreakdash-means and expectation-maximization algorithms in relation to associated Bregman divergences when applied to exponential family mixture models.
Tasks
Published	2017-11-12
URL	http://arxiv.org/abs/1711.04366v1
PDF	http://arxiv.org/pdf/1711.04366v1.pdf
PWC	https://paperswithcode.com/paper/parameter-estimation-in-finite-mixture-models
Repo
Framework

Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options


Title	Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options
Authors	Peeyush Kumar, Doina Precup
Abstract	Deliberating on large or continuous state spaces have been long standing challenges in reinforcement learning. Temporal Abstraction have somewhat made this possible, but efficiently planing using temporal abstraction still remains an issue. Moreover using spatial abstractions to learn policies for various situations at once while using temporal abstraction models is an open problem. We propose here an efficient algorithm which is convergent under linear function approximation while planning using temporally abstract actions. We show how this algorithm can be used along with randomly generated option models over multiple time scales to plan agents which need to act real time. Using these randomly generated option models over multiple time scales are shown to reduce number of decision epochs required to solve the given task, hence effectively reducing the time needed for deliberation.
Tasks
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06471v1
PDF	http://arxiv.org/pdf/1703.06471v1.pdf
PWC	https://paperswithcode.com/paper/multi-timescale-gradient-descent-temporal
Repo
Framework

Exploiting the Pruning Power of Strong Local Consistencies Through Parallelization


Title	Exploiting the Pruning Power of Strong Local Consistencies Through Parallelization
Authors	Minas Dasygenis, Kostas Stergiou
Abstract	Local consistencies stronger than arc consistency have received a lot of attention since the early days of CSP research. %because of the strong pruning they can achieve. However, they have not been widely adopted by CSP solvers. This is because applying such consistencies can sometimes result in considerably smaller search tree sizes and therefore in important speed-ups, but in other cases the search space reduction may be small, causing severe run time penalties. Taking advantage of recent advances in parallelization, we propose a novel approach for the application of strong local consistencies (SLCs) that can improve their performance by largely preserving the speed-ups they offer in cases where they are successful, and eliminating the run time penalties in cases where they are unsuccessful. This approach is presented in the form of two search algorithms. Both algorithms consist of a master search process, which is a typical CSP solver, and a number of slave processes, with each one implementing a SLC method. The first algorithm runs the different SLCs synchronously at each node of the search tree explored in the master process, while the second one can run them asynchronously at different nodes of the search tree. Experimental results demonstrate the benefits of the proposed method.
Tasks
Published	2017-05-15
URL	http://arxiv.org/abs/1705.05316v1
PDF	http://arxiv.org/pdf/1705.05316v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-the-pruning-power-of-strong-local
Repo
Framework

‘Viral’ Turing Machines, Computation from Noise and Combinatorial Hierarchies


Title	‘Viral’ Turing Machines, Computation from Noise and Combinatorial Hierarchies
Authors	T. E. Raptis
Abstract	The interactive computation paradigm is reviewed and a particular example is extended to form the stochastic analog of a computational process via a transcription of a minimal Turing Machine into an equivalent asynchronous Cellular Automaton with an exponential waiting times distribution of effective transitions. Furthermore, a special toolbox for analytic derivation of recursive relations of important statistical and other quantities is introduced in the form of an Inductive Combinatorial Hierarchy.
Tasks
Published	2017-01-31
URL	http://arxiv.org/abs/1702.06000v1
PDF	http://arxiv.org/pdf/1702.06000v1.pdf
PWC	https://paperswithcode.com/paper/viral-turing-machines-computation-from-noise
Repo
Framework

Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network


Title	Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network
Authors	Qi Ye, Tae-Kyun Kim
Abstract	Learning and predicting the pose parameters of a 3D hand model given an image, such as locations of hand joints, is challenging due to large viewpoint changes and articulations, and severe self-occlusions exhibited particularly in egocentric views. Both feature learning and prediction modeling have been investigated to tackle the problem. Though effective, most existing discriminative methods yield a single deterministic estimation of target poses. Due to their single-value mapping intrinsic, they fail to adequately handle self-occlusion problems, where occluded joints present multiple modes. In this paper, we tackle the self-occlusion issue and provide a complete description of observed poses given an input depth image by a novel method called hierarchical mixture density networks (HMDN). The proposed method leverages the state-of-the-art hand pose estimators based on Convolutional Neural Networks to facilitate feature learning, while it models the multiple modes in a two-level hierarchy to reconcile single-valued and multi-valued mapping in its output. The whole framework with a mixture of two differentiable density functions is naturally end-to-end trainable. In the experiments, HMDN produces interpretable and diverse candidate samples, and significantly outperforms the state-of-the-art methods on two benchmarks with occlusions, and performs comparably on another benchmark free of occlusions.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10872v2
PDF	http://arxiv.org/pdf/1711.10872v2.pdf
PWC	https://paperswithcode.com/paper/occlusion-aware-hand-pose-estimation-using
Repo
Framework