May 7, 2019

2884 words 14 mins read

Paper Group ANR 134

Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking. Efficient forward propagation of time-sequences in convolutional neural networks using Deep Shifting. Flow of Information in Feed-Forward Deep Neural Networks. A Unified View of Localized Kernel Learning. A Novel Fault Classification Scheme Based …

Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking


Title	Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking
Authors	Nannan Li, Dan Xu, Zhenqiang Ying, Zhihao Li, Ge Li
Abstract	In this paper, we address the problem of searching action proposals in unconstrained video clips. Our approach starts from actionness estimation on frame-level bounding boxes, and then aggregates the bounding boxes belonging to the same actor across frames via linking, associating, tracking to generate spatial-temporal continuous action paths. To achieve the target, a novel actionness estimation method is firstly proposed by utilizing both human appearance and motion cues. Then, the association of the action paths is formulated as a maximum set coverage problem with the results of actionness estimation as a priori. To further promote the performance, we design an improved optimization objective for the problem and provide a greedy search algorithm to solve it. Finally, a tracking-by-detection scheme is designed to further refine the searched action paths. Extensive experiments on two challenging datasets, UCF-Sports and UCF-101, show that the proposed approach advances state-of-the-art proposal generation performance in terms of both accuracy and proposal quantity.
Tasks
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06495v1
PDF	http://arxiv.org/pdf/1608.06495v1.pdf
PWC	https://paperswithcode.com/paper/searching-action-proposals-via-spatial
Repo
Framework

Efficient forward propagation of time-sequences in convolutional neural networks using Deep Shifting


Title	Efficient forward propagation of time-sequences in convolutional neural networks using Deep Shifting
Authors	Koen Groenland, Sander Bohte
Abstract	When a Convolutional Neural Network is used for on-the-fly evaluation of continuously updating time-sequences, many redundant convolution operations are performed. We propose the method of Deep Shifting, which remembers previously calculated results of convolution operations in order to minimize the number of calculations. The reduction in complexity is at least a constant and in the best case quadratic. We demonstrate that this method does indeed save significant computation time in a practical implementation, especially when the networks receives a large number of time-frames.
Tasks
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03657v1
PDF	http://arxiv.org/pdf/1603.03657v1.pdf
PWC	https://paperswithcode.com/paper/efficient-forward-propagation-of-time
Repo
Framework

Flow of Information in Feed-Forward Deep Neural Networks


Title	Flow of Information in Feed-Forward Deep Neural Networks
Authors	Pejman Khadivi, Ravi Tandon, Naren Ramakrishnan
Abstract	Feed-forward deep neural networks have been used extensively in various machine learning applications. Developing a precise understanding of the underling behavior of neural networks is crucial for their efficient deployment. In this paper, we use an information theoretic approach to study the flow of information in a neural network and to determine how entropy of information changes between consecutive layers. Moreover, using the Information Bottleneck principle, we develop a constrained optimization problem that can be used in the training process of a deep neural network. Furthermore, we determine a lower bound for the level of data representation that can be achieved in a deep neural network with an acceptable level of distortion.
Tasks
Published	2016-03-20
URL	http://arxiv.org/abs/1603.06220v1
PDF	http://arxiv.org/pdf/1603.06220v1.pdf
PWC	https://paperswithcode.com/paper/flow-of-information-in-feed-forward-deep
Repo
Framework

A Unified View of Localized Kernel Learning


Title	A Unified View of Localized Kernel Learning
Authors	John Moeller, Sarathkrishna Swaminathan, Suresh Venkatasubramanian
Abstract	Multiple Kernel Learning, or MKL, extends (kernelized) SVM by attempting to learn not only a classifier/regressor but also the best kernel for the training task, usually from a combination of existing kernel functions. Most MKL methods seek the combined kernel that performs best over every training example, sacrificing performance in some areas to seek a global optimum. Localized kernel learning (LKL) overcomes this limitation by allowing the training algorithm to match a component kernel to the examples that can exploit it best. Several approaches to the localized kernel learning problem have been explored in the last several years. We unify many of these approaches under one simple system and design a new algorithm with improved performance. We also develop enhanced versions of existing algorithms, with an eye on scalability and performance.
Tasks
Published	2016-03-04
URL	http://arxiv.org/abs/1603.01374v1
PDF	http://arxiv.org/pdf/1603.01374v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-view-of-localized-kernel-learning
Repo
Framework

A Novel Fault Classification Scheme Based on Least Square SVM


Title	A Novel Fault Classification Scheme Based on Least Square SVM
Authors	Harishchandra Dubey, A. K. Tiwari, Nandita, P. K. Ray, S. R. Mohanty, Nand Kishor
Abstract	This paper presents a novel approach for fault classification and section identification in a series compensated transmission line based on least square support vector machine. The current signal corresponding to one-fourth of the post fault cycle is used as input to proposed modular LS-SVM classifier. The proposed scheme uses four binary classifier; three for selection of three phases and fourth for ground detection. The proposed classification scheme is found to be accurate and reliable in presence of noise as well. The simulation results validate the efficacy of proposed scheme for accurate classification of fault in a series compensated transmission line.
Tasks
Published	2016-05-30
URL	http://arxiv.org/abs/1605.09444v1
PDF	http://arxiv.org/pdf/1605.09444v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-fault-classification-scheme-based-on
Repo
Framework

CFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics


Title	CFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics
Authors	Adam James Summerville, James Ryan, Michael Mateas, Noah Wardrip-Fruin
Abstract	In this paper, we present a novel approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. Specifically, we take a CFG authored to generate dialogue for our target application for NLU, a videogame, and train a long short-term memory (LSTM) recurrent neural network (RNN) to map the surface utterances that it produces to traces of the grammatical expansions that yielded them. Critically, this CFG was authored using a tool we have developed that supports arbitrary annotation of the nonterminal symbols in the grammar. Because we already annotated the symbols in this grammar for the semantic and pragmatic considerations that our game’s dialogue manager operates over, we can use the grammatical trace associated with any surface utterance to infer such information. During gameplay, we translate player utterances into grammatical traces (using our RNN), collect the mark-up attributed to the symbols included in that trace, and pass this information to the dialogue manager, which updates the conversation state accordingly. From an offline evaluation task, we demonstrate that our trained RNN translates surface utterances to grammatical traces with great accuracy. To our knowledge, this is the first usage of seq2seq learning for conversational agents (our game’s characters) who explicitly reason over semantic and pragmatic considerations.
Tasks
Published	2016-07-22
URL	http://arxiv.org/abs/1607.06852v1
PDF	http://arxiv.org/pdf/1607.06852v1.pdf
PWC	https://paperswithcode.com/paper/cfgs-2-nlu-sequence-to-sequence-learning-for
Repo
Framework

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning


Title	Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
Authors	Quanshi Zhang, Ruiming Cao, Ying Nian Wu, Song-Chun Zhu
Abstract	This paper proposes a learning strategy that extracts object-part concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their internal semantic hierarchy. Our method is guided by a small number of part annotations, and it achieves superior performance (about 13%-107% improvement) in part center prediction on the PASCAL VOC and ImageNet datasets.
Tasks
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04246v2
PDF	http://arxiv.org/pdf/1611.04246v2.pdf
PWC	https://paperswithcode.com/paper/growing-interpretable-part-graphs-on-convnets
Repo
Framework

Online Nonnegative Matrix Factorization with Outliers


Title	Online Nonnegative Matrix Factorization with Outliers
Authors	Renbo Zhao, Vincent Y. F. Tan
Abstract	We propose a unified and systematic framework for performing online nonnegative matrix factorization in the presence of outliers. Our framework is particularly suited to large-scale data. We propose two solvers based on projected gradient descent and the alternating direction method of multipliers. We prove that the sequence of objective values converges almost surely by appealing to the quasi-martingale convergence theorem. We also show the sequence of learned dictionaries converges to the set of stationary points of the expected loss function almost surely. In addition, we extend our basic problem formulation to various settings with different constraints and regularizers. We also adapt the solvers and analyses to each setting. We perform extensive experiments on both synthetic and real datasets. These experiments demonstrate the computational efficiency and efficacy of our algorithms on tasks such as (parts-based) basis learning, image denoising, shadow removal and foreground-background separation.
Tasks	Denoising, Image Denoising
Published	2016-04-10
URL	http://arxiv.org/abs/1604.02634v2
PDF	http://arxiv.org/pdf/1604.02634v2.pdf
PWC	https://paperswithcode.com/paper/online-nonnegative-matrix-factorization-with-1
Repo
Framework

A Tight Bound of Hard Thresholding


Title	A Tight Bound of Hard Thresholding
Authors	Jie Shen, Ping Li
Abstract	This paper is concerned with the hard thresholding operator which sets all but the $k$ largest absolute elements of a vector to zero. We establish a {\em tight} bound to quantitatively characterize the deviation of the thresholded solution from a given signal. Our theoretical result is universal in the sense that it holds for all choices of parameters, and the underlying analysis depends only on fundamental arguments in mathematical optimization. We discuss the implications for two domains: Compressed Sensing. On account of the crucial estimate, we bridge the connection between the restricted isometry property (RIP) and the sparsity parameter for a vast volume of hard thresholding based algorithms, which renders an improvement on the RIP condition especially when the true sparsity is unknown. This suggests that in essence, many more kinds of sensing matrices or fewer measurements are admissible for the data acquisition procedure. Machine Learning. In terms of large-scale machine learning, a significant yet challenging problem is learning accurate sparse models in an efficient manner. In stark contrast to prior work that attempted the $\ell_1$-relaxation for promoting sparsity, we present a novel stochastic algorithm which performs hard thresholding in each iteration, hence ensuring such parsimonious solutions. Equipped with the developed bound, we prove the {\em global linear convergence} for a number of prevalent statistical models under mild assumptions, even though the problem turns out to be non-convex.
Tasks
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01656v3
PDF	http://arxiv.org/pdf/1605.01656v3.pdf
PWC	https://paperswithcode.com/paper/a-tight-bound-of-hard-thresholding
Repo
Framework

Video Summarization using Deep Semantic Features


Title	Video Summarization using Deep Semantic Features
Authors	Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, Naokazu Yokoya
Abstract	This paper presents a video summarization technique for an Internet video to provide a quick way to overview its content. This is a challenging problem because finding important or informative parts of the original video requires to understand its content. Furthermore the content of Internet videos is very diverse, ranging from home videos to documentaries, which makes video summarization much more tough as prior knowledge is almost not available. To tackle this problem, we propose to use deep video features that can encode various levels of content semantics, including objects, actions, and scenes, improving the efficiency of standard video summarization techniques. For this, we design a deep neural network that maps videos as well as descriptions to a common semantic space and jointly trained it with associated pairs of videos and descriptions. To generate a video summary, we extract the deep features from each segment of the original video and apply a clustering-based summarization technique to them. We evaluate our video summaries using the SumMe dataset as well as baseline approaches. The results demonstrated the advantages of incorporating our deep semantic features in a video summarization technique.
Tasks	Video Summarization
Published	2016-09-28
URL	http://arxiv.org/abs/1609.08758v1
PDF	http://arxiv.org/pdf/1609.08758v1.pdf
PWC	https://paperswithcode.com/paper/video-summarization-using-deep-semantic
Repo
Framework

Robust Kernel (Cross-) Covariance Operators in Reproducing Kernel Hilbert Space toward Kernel Methods


Title	Robust Kernel (Cross-) Covariance Operators in Reproducing Kernel Hilbert Space toward Kernel Methods
Authors	Md. Ashad Alam, Kenji Fukumizu, Yu-Ping Wang
Abstract	To the best of our knowledge, there are no general well-founded robust methods for statistical unsupervised learning. Most of the unsupervised methods explicitly or implicitly depend on the kernel covariance operator (kernel CO) or kernel cross-covariance operator (kernel CCO). They are sensitive to contaminated data, even when using bounded positive definite kernels. First, we propose robust kernel covariance operator (robust kernel CO) and robust kernel crosscovariance operator (robust kernel CCO) based on a generalized loss function instead of the quadratic loss function. Second, we propose influence function of classical kernel canonical correlation analysis (classical kernel CCA). Third, using this influence function, we propose a visualization method to detect influential observations from two sets of data. Finally, we propose a method based on robust kernel CO and robust kernel CCO, called robust kernel CCA, which is designed for contaminated data and less sensitive to noise than classical kernel CCA. The principles we describe also apply to many kernel methods which must deal with the issue of kernel CO or kernel CCO. Experiments on synthesized and imaging genetics analysis demonstrate that the proposed visualization and robust kernel CCA can be applied effectively to both ideal data and contaminated data. The robust methods show the superior performance over the state-of-the-art methods.
Tasks
Published	2016-02-17
URL	http://arxiv.org/abs/1602.05563v1
PDF	http://arxiv.org/pdf/1602.05563v1.pdf
PWC	https://paperswithcode.com/paper/robust-kernel-cross-covariance-operators-in
Repo
Framework

User Bias Removal in Review Score Prediction


Title	User Bias Removal in Review Score Prediction
Authors	Rahul Wadbude, Vivek Gupta, Dheeraj Mekala, Harish Karnick
Abstract	Review score prediction of text reviews has recently gained a lot of attention in recommendation systems. A major problem in models for review score prediction is the presence of noise due to user-bias in review scores. We propose two simple statistical methods to remove such noise and improve review score prediction. Compared to other methods that use multiple classifiers, one for each user, our model uses a single global classifier to predict review scores. We empirically evaluate our methods on two major categories (\textit{Electronics} and \textit{Movies and TV}) of the SNAP published Amazon e-Commerce Reviews data-set and Amazon \textit{Fine Food} reviews data-set. We obtain improved review score prediction for three commonly used text feature representations.
Tasks	Recommendation Systems
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06821v2
PDF	http://arxiv.org/pdf/1612.06821v2.pdf
PWC	https://paperswithcode.com/paper/user-bias-removal-in-review-score-prediction
Repo
Framework

No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering “Simple” Questions)


Title	No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering “Simple” Questions)
Authors	Ferhan Ture, Oliver Jojic
Abstract	First-order factoid question answering assumes that the question can be answered by a single fact in a knowledge base (KB). While this does not seem like a challenging task, many recent attempts that apply either complex linguistic reasoning or deep neural networks achieve 65%-76% accuracy on benchmark sets. Our approach formulates the task as two machine learning problems: detecting the entities in the question, and classifying the question as one of the relation types in the KB. We train a recurrent neural network to solve each problem. On the SimpleQuestions dataset, our approach yields substantial improvements over previously published results — even neural networks based on much more complex architectures. The simplicity of our approach also has practical advantages, such as efficiency and modularity, that are valuable especially in an industry setting. In fact, we present a preliminary analysis of the performance of our model on real queries from Comcast’s X1 entertainment platform with millions of users every day.
Tasks	Question Answering
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05029v2
PDF	http://arxiv.org/pdf/1606.05029v2.pdf
PWC	https://paperswithcode.com/paper/no-need-to-pay-attention-simple-recurrent-1
Repo
Framework

Neural Paraphrase Generation with Stacked Residual LSTM Networks


Title	Neural Paraphrase Generation with Stacked Residual LSTM Networks
Authors	Aaditya Prakash, Sadid A. Hasan, Kathy Lee, Vivek Datla, Ashequl Qadir, Joey Liu, Oladimeji Farri
Abstract	In this paper, we propose a novel neural approach for paraphrase generation. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation. Our primary contribution is a stacked residual LSTM network, where we add residual connections between LSTM layers. This allows for efficient training of deep LSTMs. We evaluate our model and other state-of-the-art deep learning models on three different datasets: PPDB, WikiAnswers and MSCOCO. Evaluation results demonstrate that our model outperforms sequence to sequence, attention-based and bi- directional LSTM models on BLEU, METEOR, TER and an embedding-based sentence similarity metric.
Tasks	Paraphrase Generation
Published	2016-10-10
URL	http://arxiv.org/abs/1610.03098v3
PDF	http://arxiv.org/pdf/1610.03098v3.pdf
PWC	https://paperswithcode.com/paper/neural-paraphrase-generation-with-stacked
Repo
Framework

Detecting Context Dependence in Exercise Item Candidates Selected from Corpora


Title	Detecting Context Dependence in Exercise Item Candidates Selected from Corpora
Authors	Ildikó Pilán
Abstract	We explore the factors influencing the dependence of single sentences on their larger textual context in order to automatically identify candidate sentences for language learning exercises from corpora which are presentable in isolation. An in-depth investigation of this question has not been previously carried out. Understanding this aspect can contribute to a more efficient selection of candidate sentences which, besides reducing the time required for item writing, can also ensure a higher degree of variability and authenticity. We present a set of relevant aspects collected based on the qualitative analysis of a smaller set of context-dependent corpus example sentences. Furthermore, we implemented a rule-based algorithm using these criteria which achieved an average precision of 0.76 for the identification of different issues related to context dependence. The method has also been evaluated empirically where 80% of the sentences in which our system did not detect context-dependent elements were also considered context-independent by human raters.
Tasks
Published	2016-05-06
URL	http://arxiv.org/abs/1605.01845v1
PDF	http://arxiv.org/pdf/1605.01845v1.pdf
PWC	https://paperswithcode.com/paper/detecting-context-dependence-in-exercise-item
Repo
Framework