May 6, 2019

2877 words 14 mins read

Paper Group ANR 160

Learning text representation using recurrent convolutional neural network with highway layers. Identifying individual facial expressions by deconstructing a neural network. Model-based Outdoor Performance Capture. Large Collection of Diverse Gene Set Search Queries Recapitulate Known Protein-Protein Interactions and Gene-Gene Functional Association …

Learning text representation using recurrent convolutional neural network with highway layers


Title	Learning text representation using recurrent convolutional neural network with highway layers
Authors	Ying Wen, Weinan Zhang, Rui Luo, Jun Wang
Abstract	Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers. The highway network module is incorporated in the middle takes the output of the bi-directional Recurrent Neural Network (Bi-RNN) module in the first stage and provides the Convolutional Neural Network (CNN) module in the last stage with the input. The experiment shows that our model outperforms common neural network models (CNN, RNN, Bi-RNN) on a sentiment analysis task. Besides, the analysis of how sequence length influences the RCNN with highway layers shows that our model could learn good representation for the long text.
Tasks	Sentiment Analysis
Published	2016-06-22
URL	http://arxiv.org/abs/1606.06905v2
PDF	http://arxiv.org/pdf/1606.06905v2.pdf
PWC	https://paperswithcode.com/paper/learning-text-representation-using-recurrent
Repo
Framework

Identifying individual facial expressions by deconstructing a neural network


Title	Identifying individual facial expressions by deconstructing a neural network
Authors	Farhad Arbabzadah, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Abstract	This paper focuses on the problem of explaining predictions of psychological attributes such as attractiveness, happiness, confidence and intelligence from face photographs using deep neural networks. Since psychological attribute datasets typically suffer from small sample sizes, we apply transfer learning with two base models to avoid overfitting. These models were trained on an age and gender prediction task, respectively. Using a novel explanation method we extract heatmaps that highlight the parts of the image most responsible for the prediction. We further observe that the explanation method provides important insights into the nature of features of the base model, which allow one to assess the aptitude of the base model for a given transfer learning task. Finally, we observe that the multiclass model is more feature rich than its binary counterpart. The experimental evaluation is performed on the 2222 images from the 10k US faces dataset containing psychological attribute labels as well as on a subset of KDEF images.
Tasks	Gender Prediction, Transfer Learning
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07285v2
PDF	http://arxiv.org/pdf/1606.07285v2.pdf
PWC	https://paperswithcode.com/paper/identifying-individual-facial-expressions-by
Repo
Framework

Model-based Outdoor Performance Capture


Title	Model-based Outdoor Performance Capture
Authors	Nadia Robertini, Dan Casas, Helge Rhodin, Hans-Peter Seidel, Christian Theobalt
Abstract	We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and nonrigid surface shape refinement. Our method fits the template to unsegmented video frames in two stages - first, the coarse skeletal pose is estimated, and subsequently non-rigid surface shape and body pose are jointly refined. Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection. We obtain reconstructions of much higher quality in outdoor settings than existing methods, and show that we are on par with state-of-the-art methods on indoor scenes for which they were designed
Tasks	Edge Detection
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06740v1
PDF	http://arxiv.org/pdf/1610.06740v1.pdf
PWC	https://paperswithcode.com/paper/model-based-outdoor-performance-capture
Repo
Framework

Large Collection of Diverse Gene Set Search Queries Recapitulate Known Protein-Protein Interactions and Gene-Gene Functional Associations


Title	Large Collection of Diverse Gene Set Search Queries Recapitulate Known Protein-Protein Interactions and Gene-Gene Functional Associations
Authors	Avi Ma’ayan, Neil R. Clark
Abstract	Popular online enrichment analysis tools from the field of molecular systems biology provide users with the ability to submit their experimental results as gene sets for individual analysis. Such queries are kept private, and have never before been considered as a resource for integrative analysis. By harnessing gene set query submissions from thousands of users, we aim to discover biological knowledge beyond the scope of an individual study. In this work, we investigated a large collection of gene sets submitted to the tool Enrichr by thousands of users. Based on co-occurrence, we constructed a global gene-gene association network. We interpret this inferred network as providing a summary of the structure present in this crowdsourced gene set library, and show that this network recapitulates known protein-protein interactions and functional associations between genes. This finding implies that this network also offers predictive value. Furthermore, we visualize this gene-gene association network using a new edge-pruning algorithm that retains both the local and global structures of large-scale networks. Our ability to make predictions for currently unknown gene associations, that may not be captured by individual researchers and data sources, is a demonstration of the potential of harnessing collective knowledge from users of popular tools in the field of molecular systems biology.
Tasks
Published	2016-01-07
URL	http://arxiv.org/abs/1601.01653v1
PDF	http://arxiv.org/pdf/1601.01653v1.pdf
PWC	https://paperswithcode.com/paper/large-collection-of-diverse-gene-set-search
Repo
Framework

Variational Information Maximization for Feature Selection


Title	Variational Information Maximization for Feature Selection
Authors	Shuyang Gao, Greg Ver Steeg, Aram Galstyan
Abstract	Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximizing mutual information between subsets of features and class labels. Practical methods are forced to rely on approximations due to the difficulty of estimating mutual information. We demonstrate that approximations made by existing methods are based on unrealistic assumptions. We formulate a more flexible and general class of assumptions based on variational distributions and use them to tractably generate lower bounds for mutual information. These bounds define a novel information-theoretic framework for feature selection, which we prove to be optimal under tree graphical models with proper choice of variational distributions. Our experiments demonstrate that the proposed method strongly outperforms existing information-theoretic feature selection approaches.
Tasks	Feature Selection
Published	2016-06-09
URL	http://arxiv.org/abs/1606.02827v1
PDF	http://arxiv.org/pdf/1606.02827v1.pdf
PWC	https://paperswithcode.com/paper/variational-information-maximization-for
Repo
Framework

A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure


Title	A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure
Authors	Soumitra Samanta, Bhabatosh Chanda
Abstract	In this paper, we present a data-driven approach for human pose tracking in video data. We formulate the human pose tracking problem as a discrete optimization problem based on spatio-temporal pictorial structure model and solve this problem in a greedy framework very efficiently. We propose the model to track the human pose by combining the human pose estimation from single image and traditional object tracking in a video. Our pose tracking objective function consists of the following terms: likeliness of appearance of a part within a frame, temporal displacement of the part from previous frame to the current frame, and the spatial dependency of a part with its parent in the graph structure. Experimental evaluation on benchmark datasets (VideoPose2, Poses in the Wild and Outdoor Pose) as well as on our newly build ICDPose dataset shows the usefulness of our proposed method.
Tasks	Object Tracking, Pose Estimation, Pose Tracking
Published	2016-07-31
URL	http://arxiv.org/abs/1608.00199v1
PDF	http://arxiv.org/pdf/1608.00199v1.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-human-pose
Repo
Framework

A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization


Title	A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization
Authors	Shun Zheng, Jialei Wang, Fen Xia, Wei Xu, Tong Zhang
Abstract	In modern large-scale machine learning applications, the training data are often partitioned and stored on multiple machines. It is customary to employ the “data parallelism” approach, where the aggregated training loss is minimized without moving data across machines. In this paper, we introduce a novel distributed dual formulation for regularized loss minimization problems that can directly handle data parallelism in the distributed setting. This formulation allows us to systematically derive dual coordinate optimization procedures, which we refer to as Distributed Alternating Dual Maximization (DADM). The framework extends earlier studies described in (Boyd et al., 2011; Ma et al., 2015a; Jaggi et al., 2014; Yang, 2013) and has rigorous theoretical analyses. Moreover with the help of the new formulation, we develop the accelerated version of DADM (Acc-DADM) by generalizing the acceleration technique from (Shalev-Shwartz and Zhang, 2014) to the distributed setting. We also provide theoretical results for the proposed accelerated version and the new result improves previous ones (Yang, 2013; Ma et al., 2015a) whose runtimes grow linearly on the condition number. Our empirical studies validate our theory and show that our accelerated approach significantly improves the previous state-of-the-art distributed dual coordinate optimization algorithms.
Tasks
Published	2016-04-13
URL	http://arxiv.org/abs/1604.03763v3
PDF	http://arxiv.org/pdf/1604.03763v3.pdf
PWC	https://paperswithcode.com/paper/a-general-distributed-dual-coordinate
Repo
Framework

Object Detection using Image Processing


Title	Object Detection using Image Processing
Authors	Fares Jalled, Ilia Voronkov
Abstract	An Unmanned Ariel vehicle (UAV) has greater importance in the army for border security. The main objective of this article is to develop an OpenCV-Python code using Haar Cascade algorithm for object and face detection. Currently, UAVs are used for detecting and attacking the infiltrated ground targets. The main drawback for this type of UAVs is that sometimes the object are not properly detected, which thereby causes the object to hit the UAV. This project aims to avoid such unwanted collisions and damages of UAV. UAV is also used for surveillance that uses Voila-jones algorithm to detect and track humans. This algorithm uses cascade object detector function and vision. train function to train the algorithm. The main advantage of this code is the reduced processing time. The Python code was tested with the help of available database of video and image, the output was verified.
Tasks	Face Detection, Object Detection
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07791v1
PDF	http://arxiv.org/pdf/1611.07791v1.pdf
PWC	https://paperswithcode.com/paper/object-detection-using-image-processing
Repo
Framework

Attention-Based Convolutional Neural Network for Machine Comprehension


Title	Attention-Based Convolutional Neural Network for Machine Comprehension
Authors	Wenpeng Yin, Sebastian Ebert, Hinrich Schütze
Abstract	Understanding open-domain text is one of the primary challenges in natural language processing (NLP). Machine comprehension benchmarks evaluate the system’s ability to understand text based on the text content only. In this work, we investigate machine comprehension on MCTest, a question answering (QA) benchmark. Prior work is mainly based on feature engineering approaches. We come up with a neural network framework, named hierarchical attention-based convolutional neural network (HABCNN), to address this task without any manually designed features. Specifically, we explore HABCNN for this task by two routes, one is through traditional joint modeling of passage, question and answer, one is through textual entailment. HABCNN employs an attention mechanism to detect key phrases, key sentences and key snippets that are relevant to answering the question. Experiments show that HABCNN outperforms prior deep learning approaches by a big margin.
Tasks	Feature Engineering, Natural Language Inference, Question Answering, Reading Comprehension
Published	2016-02-13
URL	http://arxiv.org/abs/1602.04341v1
PDF	http://arxiv.org/pdf/1602.04341v1.pdf
PWC	https://paperswithcode.com/paper/attention-based-convolutional-neural-network
Repo
Framework

A Geometric Framework for Convolutional Neural Networks


Title	A Geometric Framework for Convolutional Neural Networks
Authors	Anthony L. Caterini, Dong Eui Chang
Abstract	In this paper, a geometric framework for neural networks is proposed. This framework uses the inner product space structure underlying the parameter set to perform gradient descent not in a component-based form, but in a coordinate-free manner. Convolutional neural networks are described in this framework in a compact form, with the gradients of standard — and higher-order — loss functions calculated for each layer of the network. This approach can be applied to other network structures and provides a basis on which to create new networks.
Tasks
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04374v2
PDF	http://arxiv.org/pdf/1608.04374v2.pdf
PWC	https://paperswithcode.com/paper/a-geometric-framework-for-convolutional
Repo
Framework

Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization


Title	Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization
Authors	Tianbao Yang, Qihang Lin, Zhe Li
Abstract	Recently, {\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov’s accelerated gradient method. We hope that the basic convergence results developed in this paper can serve the reference to the convergence of stochastic momentum methods and also serve the baselines for comparison in future development of stochastic momentum methods. The novelty of convergence analysis presented in this paper is a unified framework, revealing more insights about the similarities and differences between different stochastic momentum methods and stochastic gradient method. The unified framework exhibits a continuous change from the gradient method to Nesterov’s accelerated gradient method and finally the heavy-ball method incurred by a free parameter, which can help explain a similar change observed in the testing error convergence behavior for deep learning. Furthermore, our empirical results for optimizing deep neural networks demonstrate that the stochastic variant of Nesterov’s accelerated gradient method achieves a good tradeoff (between speed of convergence in training error and robustness of convergence in testing error) among the three stochastic methods.
Tasks
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03257v2
PDF	http://arxiv.org/pdf/1604.03257v2.pdf
PWC	https://paperswithcode.com/paper/unified-convergence-analysis-of-stochastic
Repo
Framework

The Actias system: supervised multi-strategy learning paradigm using categorical logic


Title	The Actias system: supervised multi-strategy learning paradigm using categorical logic
Authors	Carlos Leandro, Helder Pita, Luís Monteiro
Abstract	One of the most difficult problems in the development of intelligent systems is the construction of the underlying knowledge base. As a consequence, the rate of progress in the development of this type of system is directly related to the speed with which knowledge bases can be assembled, and on its quality. We attempt to solve the knowledge acquisition problem, for a Business Information System, developing a supervised multistrategy learning paradigm. This paradigm is centred on a collaborative data mining strategy, where groups of experts collaborate using data-mining process on the supervised acquisition of new knowledge extracted from heterogeneous machine learning data models. The Actias system is our approach to this paradigm. It is the result of applying the graphic logic based language of sketches to knowledge integration. The system is a data mining collaborative workplace, where the Information System knowledge base is an algebraic structure. It results from the integration of background knowledge with new insights extracted from data models, generated for specific data modelling tasks, and represented as rules using the sketches language.
Tasks
Published	2016-05-06
URL	http://arxiv.org/abs/1607.08098v1
PDF	http://arxiv.org/pdf/1607.08098v1.pdf
PWC	https://paperswithcode.com/paper/the-actias-system-supervised-multi-strategy
Repo
Framework

The Power of Normalization: Faster Evasion of Saddle Points


Title	The Power of Normalization: Faster Evasion of Saddle Points
Authors	Kfir Y. Levy
Abstract	A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored. We analyze this heuristic and show that with carefully chosen parameters and noise injection, this method can provably evade saddle points. We establish the convergence of NGD to a local minimum, and demonstrate rates which improve upon the fastest known first order algorithm due to Ge e al. (2015). The effectiveness of our method is demonstrated via an application to the problem of online tensor decomposition; a task for which saddle point evasion is known to result in convergence to global minima.
Tasks
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04831v1
PDF	http://arxiv.org/pdf/1611.04831v1.pdf
PWC	https://paperswithcode.com/paper/the-power-of-normalization-faster-evasion-of
Repo
Framework

Appearance Based Robot and Human Activity Recognition System


Title	Appearance Based Robot and Human Activity Recognition System
Authors	Bappaditya Mandal
Abstract	In this work, we present an appearance based human activity recognition system. It uses background modeling to segment the foreground object and extracts useful discriminative features for representing activities performed by humans and robots. Subspace based method like principal component analysis is used to extract low dimensional features from large voluminous activity images. These low dimensional features are then used to classify an activity. An apparatus is designed using a webcam, which watches a robot replicating a human fall under indoor environment. In this apparatus, a robot performs various activities (like walking, bending, moving arms) replicating humans, which also includes a sudden fall. Experimental results on robot performing various activities and standard human activity recognition databases show the efficacy of our proposed method.
Tasks	Activity Recognition, Human Activity Recognition
Published	2016-02-04
URL	http://arxiv.org/abs/1602.01608v2
PDF	http://arxiv.org/pdf/1602.01608v2.pdf
PWC	https://paperswithcode.com/paper/appearance-based-robot-and-human-activity
Repo
Framework

DualNet: Domain-Invariant Network for Visual Question Answering


Title	DualNet: Domain-Invariant Network for Visual Question Answering
Authors	Kuniaki Saito, Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada
Abstract	Visual question answering (VQA) task not only bridges the gap between images and language, but also requires that specific contents within the image are understood as indicated by linguistic context of the question, in order to generate the accurate answers. Thus, it is critical to build an efficient embedding of images and texts. We implement DualNet, which fully takes advantage of discriminative power of both image and textual features by separately performing two operations. Building an ensemble of DualNet further boosts the performance. Contrary to common belief, our method proved effective in both real images and abstract scenes, in spite of significantly different properties of respective domain. Our method was able to outperform previous state-of-the-art methods in real images category even without explicitly employing attention mechanism, and also outperformed our own state-of-the-art method in abstract scenes category, which recently won the first place in VQA Challenge 2016.
Tasks	Question Answering, Visual Question Answering
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06108v2
PDF	http://arxiv.org/pdf/1606.06108v2.pdf
PWC	https://paperswithcode.com/paper/dualnet-domain-invariant-network-for-visual
Repo
Framework