May 7, 2019

3218 words 16 mins read

Paper Group ANR 84

Distributed Flexible Nonlinear Tensor Factorization. A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks. Distortion Varieties. Word and Document Embeddings based on Neural Network Approaches. Learning shape correspondence with anisotropic convolutional neural networks. Simultaneous independent image display technique on mu …

Distributed Flexible Nonlinear Tensor Factorization


Title	Distributed Flexible Nonlinear Tensor Factorization
Authors	Shandian Zhe, Kai Zhang, Pengyuan Wang, Kuang-chih Lee, Zenglin Xu, Yuan Qi, Zoubin Ghahramani
Abstract	Tensor factorization is a powerful tool to analyse multi-way data. Compared with traditional multi-linear methods, nonlinear tensor factorization models are capable of capturing more complex relationships in the data. However, they are computationally expensive and may suffer severe learning bias in case of extreme data sparsity. To overcome these limitations, in this paper we propose a distributed, flexible nonlinear tensor factorization model. Our model can effectively avoid the expensive computations and structural restrictions of the Kronecker-product in existing TGP formulations, allowing an arbitrary subset of tensorial entries to be selected to contribute to the training. At the same time, we derive a tractable and tight variational evidence lower bound (ELBO) that enables highly decoupled, parallel computations and high-quality inference. Based on the new bound, we develop a distributed inference algorithm in the MapReduce framework, which is key-value-free and can fully exploit the memory cache mechanism in fast MapReduce systems such as SPARK. Experimental results fully demonstrate the advantages of our method over several state-of-the-art approaches, in terms of both predictive performance and computational efficiency. Moreover, our approach shows a promising potential in the application of Click-Through-Rate (CTR) prediction for online advertising.
Tasks	Click-Through Rate Prediction
Published	2016-04-27
URL	http://arxiv.org/abs/1604.07928v2
PDF	http://arxiv.org/pdf/1604.07928v2.pdf
PWC	https://paperswithcode.com/paper/distributed-flexible-nonlinear-tensor
Repo
Framework

A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks


Title	A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
Authors	Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Prateek Vij
Abstract	Sarcasm detection is a key task for many natural language processing tasks. In sentiment analysis, for example, sarcasm can flip the polarity of an “apparently positive” sentence and, hence, negatively affect polarity detection performance. To date, most approaches to sarcasm detection have treated the task primarily as a text categorization problem. Sarcasm, however, can be expressed in very subtle ways and requires a deeper understanding of natural language that standard text categorization techniques cannot grasp. In this work, we develop models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection. Such features, along with the network’s baseline features, allow the proposed models to outperform the state of the art on benchmark datasets. We also address the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.
Tasks	Sarcasm Detection, Sentiment Analysis, Text Categorization
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08815v2
PDF	http://arxiv.org/pdf/1610.08815v2.pdf
PWC	https://paperswithcode.com/paper/a-deeper-look-into-sarcastic-tweets-using
Repo
Framework

Distortion Varieties


Title	Distortion Varieties
Authors	Joe Kileel, Zuzana Kukelova, Tomas Pajdla, Bernd Sturmfels
Abstract	The distortion varieties of a given projective variety are parametrized by duplicating coordinates and multiplying them with monomials. We study their degrees and defining equations. Exact formulas are obtained for the case of one-parameter distortions. These are based on Chow polytopes and Gr"obner bases. Multi-parameter distortions are studied using tropical geometry. The motivation for distortion varieties comes from multi-view geometry in computer vision. Our theory furnishes a new framework for formulating and solving minimal problems for camera models with image distortion.
Tasks
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01860v1
PDF	http://arxiv.org/pdf/1610.01860v1.pdf
PWC	https://paperswithcode.com/paper/distortion-varieties
Repo
Framework

Word and Document Embeddings based on Neural Network Approaches


Title	Word and Document Embeddings based on Neural Network Approaches
Authors	Siwei Lai
Abstract	Data representation is a fundamental task in machine learning. The representation of data affects the performance of the whole machine learning system. In a long history, the representation of data is done by feature engineering, and researchers aim at designing better features for specific tasks. Recently, the rapid development of deep learning and representation learning has brought new inspiration to various domains. In natural language processing, the most widely used feature representation is the Bag-of-Words model. This model has the data sparsity problem and cannot keep the word order information. Other features such as part-of-speech tagging or more complex syntax features can only fit for specific tasks in most cases. This thesis focuses on word representation and document representation. We compare the existing systems and present our new model. First, for generating word embeddings, we make comprehensive comparisons among existing word embedding models. In terms of theory, we figure out the relationship between the two most important models, i.e., Skip-gram and GloVe. In our experiments, we analyze three key points in generating word embeddings, including the model construction, the training corpus and parameter design. We evaluate word embeddings with three types of tasks, and we argue that they cover the existing use of word embeddings. Through theory and practical experiments, we present some guidelines for how to generate a good word embedding. Second, in Chinese character or word representation. We introduce the joint training of Chinese character and word. … Third, for document representation, we analyze the existing document representation models, including recursive NNs, recurrent NNs and convolutional NNs. We point out the drawbacks of these models and present our new model, the recurrent convolutional neural networks. …
Tasks	Feature Engineering, Part-Of-Speech Tagging, Representation Learning, Word Embeddings
Published	2016-11-18
URL	http://arxiv.org/abs/1611.05962v1
PDF	http://arxiv.org/pdf/1611.05962v1.pdf
PWC	https://paperswithcode.com/paper/word-and-document-embeddings-based-on-neural
Repo
Framework

Learning shape correspondence with anisotropic convolutional neural networks


Title	Learning shape correspondence with anisotropic convolutional neural networks
Authors	Davide Boscaini, Jonathan Masci, Emanuele Rodolà, Michael M. Bronstein
Abstract	Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. The problem is especially difficult in the setting of non-isometric deformations, as well as in the presence of topological noise and missing parts, mainly due to the limited capability to model such deformations axiomatically. Several recent works showed that invariance to complex shape transformations can be learned from examples. In this paper, we introduce an intrinsic convolutional neural network architecture based on anisotropic diffusion kernels, which we term Anisotropic Convolutional Neural Network (ACNN). In our construction, we generalize convolutions to non-Euclidean domains by constructing a set of oriented anisotropic diffusion kernels, creating in this way a local intrinsic polar representation of the data (`patch’), which is then correlated with a filter. Several cascades of such filters, linear, and non-linear operators are stacked to form a deep neural network whose parameters are learned by minimizing a task-specific cost. We use ACNNs to effectively learn intrinsic dense correspondences between deformable shapes in very challenging settings, achieving state-of-the-art results on some of the most difficult recent correspondence benchmarks. \|
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06437v1
PDF	http://arxiv.org/pdf/1605.06437v1.pdf
PWC	https://paperswithcode.com/paper/learning-shape-correspondence-with
Repo
Framework

Simultaneous independent image display technique on multiple 3D objects


Title	Simultaneous independent image display technique on multiple 3D objects
Authors	Takuto Hirukawa, Marco Visentini-Scarzanella, Hiroshi Kawasaki, Ryo Furukawa, Shinsaku Hiura
Abstract	We propose a new system to visualize depth-dependent patterns and images on solid objects with complex geometry using multiple projectors. The system, despite consisting of conventional passive LCD projectors, is able to project different images and patterns depending on the spatial location of the object. The technique is based on the simple principle that multiple patterns projected from multiple projectors interfere constructively with each other when their patterns are projected on the same object. Previous techniques based on the same principle can only achieve 1) low resolution volume colorization or 2) high resolution images but only on a limited number of flat planes. In this paper, we discretize a 3D object into a number of 3D points so that high resolution images can be projected onto the complex shapes. We also propose a dynamic ranges expansion technique as well as an efficient optimization procedure based on epipolar constraints. Such technique can be used to the extend projection mapping to have spatial dependency, which is desirable for practical applications. We also demonstrate the system potential as a visual instructor for object placement and assembling. Experiments prove the effectiveness of our method.
Tasks	Colorization
Published	2016-09-10
URL	http://arxiv.org/abs/1609.02994v1
PDF	http://arxiv.org/pdf/1609.02994v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-independent-image-display
Repo
Framework

Towards the Self-constructive Brain: emergence of adaptive behavior


Title	Towards the Self-constructive Brain: emergence of adaptive behavior
Authors	Fernando Corbacho
Abstract	Adaptive behavior is mainly the result of adaptive brains. We go a step beyond and claim that the brain does not only adapt to its surrounding reality but rather, it builds itself up to constructs its own reality. That is, rather than just trying to passively understand its environment, the brain is the architect of its own reality in an active process where its internal models of the external world frame how its new interactions with the environment are assimilated. These internal models represent relevant predictive patterns of interaction all over the different brain structures: perceptual, sensorimotor, motor, etc. The emergence of adaptive behavior arises from this self-constructive nature of the brain, based on the following principles of organization: self-experimental, self- growing, and self-repairing. Self-experimental, since to ensure survival, the self-constructive brain (SCB) is an active machine capable of performing experiments of its own interactions with the environment by mental simulation. Self-growing, since it dynamically and incrementally constructs internal structures in order to build a model of the world as it gathers statistics from its interactions with the environment. Self-repairing, since to survive the SCB must also be robust and capable of finding ways to repair parts of previously working structures and hence re-construct a previous relevant pattern of activity.
Tasks
Published	2016-08-07
URL	http://arxiv.org/abs/1608.02229v1
PDF	http://arxiv.org/pdf/1608.02229v1.pdf
PWC	https://paperswithcode.com/paper/towards-the-self-constructive-brain-emergence
Repo
Framework

Multiple Hypothesis Colorization


Title	Multiple Hypothesis Colorization
Authors	Mohammad Haris Baig, Lorenzo Torresani
Abstract	In this work we focus on the problem of colorization for image compression. Since color information occupies a large proportion of the total storage size of an image, a method that can predict accurate color from its grayscale version can produce dramatic reduction in image file size. But colorization for compression poses several challenges. First, while colorization for artistic purposes simply involves predicting plausible chroma, colorization for compression requires generating output colors that are as close as possible to the ground truth. Second, many objects in the real world exhibit multiple possible colors. Thus, to disambiguate the colorization problem some additional information must be stored to reproduce the true colors with good accuracy. To account for the multimodal color distribution of objects we propose a deep tree-structured network that generates multiple color hypotheses for every pixel from a grayscale picture (as opposed to a single color produced by most prior colorization approaches). We show how to leverage the multimodal output of our model to reproduce with high fidelity the true colors of an image by storing very little additional information. In the experiments we show that our proposed method outperforms traditional JPEG color coding by a large margin, producing colors that are nearly indistinguishable from the ground truth at the storage cost of just a few hundred bytes for high-resolution pictures!
Tasks	Colorization, Image Compression
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06314v3
PDF	http://arxiv.org/pdf/1606.06314v3.pdf
PWC	https://paperswithcode.com/paper/multiple-hypothesis-colorization
Repo
Framework

Forward Table-Based Presynaptic Event-Triggered Spike-Timing-Dependent Plasticity


Title	Forward Table-Based Presynaptic Event-Triggered Spike-Timing-Dependent Plasticity
Authors	Bruno U. Pedroni, Sadique Sheik, Siddharth Joshi, Georgios Detorakis, Somnath Paul, Charles Augustine, Emre Neftci, Gert Cauwenberghs
Abstract	Spike-timing-dependent plasticity (STDP) incurs both causal and acausal synaptic weight updates, for negative and positive time differences between pre-synaptic and post-synaptic spike events. For realizing such updates in neuromorphic hardware, current implementations either require forward and reverse lookup access to the synaptic connectivity table, or rely on memory-intensive architectures such as crossbar arrays. We present a novel method for realizing both causal and acausal weight updates using only forward lookup access of the synaptic connectivity table, permitting memory-efficient implementation. A simplified implementation in FPGA, using a single timer variable for each neuron, closely approximates exact STDP cumulative weight updates for neuron refractory periods greater than 10 ms, and reduces to exact STDP for refractory periods greater than the STDP time window. Compared to conventional crossbar implementation, the forward table-based implementation leads to substantial memory savings for sparsely connected networks supporting scalable neuromorphic systems with fully reconfigurable synaptic connectivity and plasticity.
Tasks
Published	2016-07-11
URL	http://arxiv.org/abs/1607.03070v2
PDF	http://arxiv.org/pdf/1607.03070v2.pdf
PWC	https://paperswithcode.com/paper/forward-table-based-presynaptic-event
Repo
Framework

A Novel Term_Class Relevance Measure for Text Categorization


Title	A Novel Term_Class Relevance Measure for Text Categorization
Authors	D S Guru, Mahamad Suhil
Abstract	In this paper, we introduce a new measure called Term_Class relevance to compute the relevancy of a term in classifying a document into a particular class. The proposed measure estimates the degree of relevance of a given term, in placing an unlabeled document to be a member of a known class, as a product of Class_Term weight and Class_Term density; where the Class_Term weight is the ratio of the number of documents of the class containing the term to the total number of documents containing the term and the Class_Term density is the relative density of occurrence of the term in the class to the total occurrence of the term in the entire population. Unlike the other existing term weighting schemes such as TF-IDF and its variants, the proposed relevance measure takes into account the degree of relative participation of the term across all documents of the class to the entire population. To demonstrate the significance of the proposed measure experimentation has been conducted on the 20 Newsgroups dataset. Further, the superiority of the novel measure is brought out through a comparative analysis.
Tasks	Text Categorization
Published	2016-08-25
URL	http://arxiv.org/abs/1608.07094v2
PDF	http://arxiv.org/pdf/1608.07094v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-term_class-relevance-measure-for-text
Repo
Framework

Nearly-optimal Robust Matrix Completion


Title	Nearly-optimal Robust Matrix Completion
Authors	Yeshwanth Cherapanamjeri, Kartik Gupta, Prateek Jain
Abstract	In this paper, we consider the problem of Robust Matrix Completion (RMC) where the goal is to recover a low-rank matrix by observing a small number of its entries out of which a few can be arbitrarily corrupted. We propose a simple projected gradient descent method to estimate the low-rank matrix that alternately performs a projected gradient descent step and cleans up a few of the corrupted entries using hard-thresholding. Our algorithm solves RMC using nearly optimal number of observations as well as nearly optimal number of corruptions. Our result also implies significant improvement over the existing time complexity bounds for the low-rank matrix completion problem. Finally, an application of our result to the robust PCA problem (low-rank+sparse matrix separation) leads to nearly linear time (in matrix dimensions) algorithm for the same; existing state-of-the-art methods require quadratic time. Our empirical results corroborate our theoretical results and show that even for moderate sized problems, our method for robust PCA is an an order of magnitude faster than the existing methods.
Tasks	Low-Rank Matrix Completion, Matrix Completion
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07315v3
PDF	http://arxiv.org/pdf/1606.07315v3.pdf
PWC	https://paperswithcode.com/paper/nearly-optimal-robust-matrix-completion
Repo
Framework

On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits


Title	On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits
Authors	Shahin Shahrampour, Mohammad Noshad, Vahid Tarokh
Abstract	We consider the best-arm identification problem in multi-armed bandits, which focuses purely on exploration. A player is given a fixed budget to explore a finite set of arms, and the rewards of each arm are drawn independently from a fixed, unknown distribution. The player aims to identify the arm with the largest expected reward. We propose a general framework to unify sequential elimination algorithms, where the arms are dismissed iteratively until a unique arm is left. Our analysis reveals a novel performance measure expressed in terms of the sampling mechanism and number of eliminated arms at each round. Based on this result, we develop an algorithm that divides the budget according to a nonlinear function of remaining arms at each round. We provide theoretical guarantees for the algorithm, characterizing the suitable nonlinearity for different problem environments described by the number of competitive arms. Matching the theoretical results, our experiments show that the nonlinear algorithm outperforms the state-of-the-art. We finally study the side-observation model, where pulling an arm reveals the rewards of its related arms, and we establish improved theoretical guarantees in the pure-exploration setting.
Tasks	Multi-Armed Bandits
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02606v2
PDF	http://arxiv.org/pdf/1609.02606v2.pdf
PWC	https://paperswithcode.com/paper/on-sequential-elimination-algorithms-for-best
Repo
Framework

Automatic text extraction and character segmentation using maximally stable extremal regions


Title	Automatic text extraction and character segmentation using maximally stable extremal regions
Authors	Nitigya Sambyal, Pawanesh Abrol
Abstract	Text detection and segmentation is an important prerequisite for many content based image analysis tasks. The paper proposes a novel text extraction and character segmentation algorithm using Maximally Stable Extremal Regions as basic letter candidates. These regions are then subjected to thresholding and thereafter various connected components are determined to identify separate characters. The algorithm is tested along a set of various JPEG, PNG and BMP images over four different character sets; English, Russian, Hindi and Urdu. The algorithm gives good results for English and Russian character set; however character segmentation in Urdu and Hindi language is not much accurate. The algorithm is simple, efficient, involves no overhead as required in training and gives good results for even low quality images. The paper also proposes various challenges in text extraction and segmentation for multilingual inputs.
Tasks
Published	2016-08-11
URL	http://arxiv.org/abs/1608.03374v1
PDF	http://arxiv.org/pdf/1608.03374v1.pdf
PWC	https://paperswithcode.com/paper/automatic-text-extraction-and-character
Repo
Framework

Divide and…conquer? On the limits of algorithmic approaches to syntactic semantic structure


Title	Divide and…conquer? On the limits of algorithmic approaches to syntactic semantic structure
Authors	Diego Gabriel Krivochen
Abstract	In computer science, divide and conquer (D&C) is an algorithm design paradigm based on multi-branched recursion. A D&C algorithm works by recursively and monotonically breaking down a problem into sub problems of the same (or a related) type, until these become simple enough to be solved directly. The solutions to the sub problems are then combined to give a solution to the original problem. The present work identifies D&C algorithms assumed within contemporary syntactic theory, and discusses the limits of their applicability in the realms of the syntax semantics and syntax morphophonology interfaces. We will propose that D&C algorithms, while valid for some processes, fall short on flexibility given a mixed approach to the structure of linguistic phrase markers. Arguments in favour of a computationally mixed approach to linguistic structure will be presented as an alternative that offers advantages to uniform D&C approaches.
Tasks
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03148v1
PDF	http://arxiv.org/pdf/1609.03148v1.pdf
PWC	https://paperswithcode.com/paper/divide-andconquer-on-the-limits-of
Repo
Framework

Following Gaze Across Views


Title	Following Gaze Across Views
Authors	Adrià Recasens, Carl Vondrick, Aditya Khosla, Antonio Torralba
Abstract	Following the gaze of people inside videos is an important signal for understanding people and their actions. In this paper, we present an approach for following gaze across views by predicting where a particular person is looking throughout a scene. We collect VideoGaze, a new dataset which we use as a benchmark to both train and evaluate models. Given one view with a person in it and a second view of the scene, our model estimates a density for gaze location in the second view. A key aspect of our approach is an end-to-end model that solves the following sub-problems: saliency, gaze pose, and geometric relationships between views. Although our model is supervised only with gaze, we show that the model learns to solve these subproblems automatically without supervision. Experiments suggest that our approach follows gaze better than standard baselines and produces plausible results for everyday situations.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03094v1
PDF	http://arxiv.org/pdf/1612.03094v1.pdf
PWC	https://paperswithcode.com/paper/following-gaze-across-views
Repo
Framework