July 27, 2019

3294 words 16 mins read

Paper Group ANR 670

μ-MAR: Multiplane 3D Marker based Registration for Depth-sensing Cameras. A Perceptual Measure for Deep Single Image Camera Calibration. Weakly-Supervised Spatial Context Networks. Decision Trees for Helpdesk Advisor Graphs. Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning. Deep Region Hashing for Efficien …

μ-MAR: Multiplane 3D Marker based Registration for Depth-sensing Cameras


Title	μ-MAR: Multiplane 3D Marker based Registration for Depth-sensing Cameras
Authors	Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo, Higinio Mora-Mora
Abstract	Many applications including object reconstruction, robot guidance, and scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown an it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the Signal-to-Noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, {\mu}-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The …
Tasks	Object Reconstruction
Published	2017-08-04
URL	http://arxiv.org/abs/1708.01405v1
PDF	http://arxiv.org/pdf/1708.01405v1.pdf
PWC	https://paperswithcode.com/paper/-mar-multiplane-3d-marker-based-registration
Repo
Framework

A Perceptual Measure for Deep Single Image Camera Calibration


Title	A Perceptual Measure for Deep Single Image Camera Calibration
Authors	Yannick Hold-Geoffroy, Kalyan Sunkavalli, Jonathan Eisenmann, Matt Fisher, Emiliano Gambaretto, Sunil Hadap, Jean-François Lalonde
Abstract	Most current single image camera calibration methods rely on specific image features or user input, and cannot be applied to natural images captured in uncontrolled settings. We propose directly inferring camera calibration parameters from a single image using a deep convolutional neural network. This network is trained using automatically generated samples from a large-scale panorama dataset, and considerably outperforms other methods, including recent deep learning-based approaches, in terms of standard L2 error. However, we argue that in many cases it is more important to consider how humans perceive errors in camera estimation. To this end, we conduct a large-scale human perception study where we ask users to judge the realism of 3D objects composited with and without ground truth camera calibration. Based on this study, we develop a new perceptual measure for camera calibration, and demonstrate that our deep calibration network outperforms other methods on this measure. Finally, we demonstrate the use of our calibration network for a number of applications including virtual object insertion, image retrieval and compositing.
Tasks	Calibration, Image Retrieval
Published	2017-12-02
URL	http://arxiv.org/abs/1712.01259v3
PDF	http://arxiv.org/pdf/1712.01259v3.pdf
PWC	https://paperswithcode.com/paper/a-perceptual-measure-for-deep-single-image
Repo
Framework

Weakly-Supervised Spatial Context Networks


Title	Weakly-Supervised Spatial Context Networks
Authors	Zuxuan Wu, Larry S. Davis, Leonid Sigal
Abstract	We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch, within the same image, conditioned on their real-valued relative spatial offset. Unlike auto-encoders, that aim to encode and reconstruct original image patches, our network aims to encode and reconstruct intermediate representations of the spatially offset patches. As such, the network learns a spatially conditioned contextual representation. By testing performance with various patch selection mechanisms we show that focusing on object-centric patches is important, and that using object proposal as a patch selection mechanism leads to the highest improvement in performance. Further, unlike auto-encoders, context encoders [21], or other forms of unsupervised feature learning, we illustrate that contextual supervision (with pre-trained model initialization) can improve on existing pre-trained model performance. We build our spatial context networks on top of standard VGG_19 and CNN_M architectures and, among other things, show that we can achieve improvements (with no additional explicit supervision) over the original ImageNet pre-trained VGG_19 and CNN_M models in object categorization and detection on VOC2007.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02998v2
PDF	http://arxiv.org/pdf/1704.02998v2.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-spatial-context-networks
Repo
Framework

Decision Trees for Helpdesk Advisor Graphs


Title	Decision Trees for Helpdesk Advisor Graphs
Authors	Spyros Gkezerlis, Dimitris Kalles
Abstract	We use decision trees to build a helpdesk agent reference network to facilitate the on-the-job advising of junior or less experienced staff on how to better address telecommunication customer fault reports. Such reports generate field measurements and remote measurements which, when coupled with location data and client attributes, and fused with organization-level statistics, can produce models of how support should be provided. Beyond decision support, these models can help identify staff who can act as advisors, based on the quality, consistency and predictability of dealing with complex troubleshooting reports. Advisor staff models are then used to guide less experienced staff in their decision making; thus, we advocate the deployment of a simple mechanism which exploits the availability of staff with a sound track record at the helpdesk to act as dormant tutors.
Tasks	Decision Making
Published	2017-10-19
URL	http://arxiv.org/abs/1710.07075v1
PDF	http://arxiv.org/pdf/1710.07075v1.pdf
PWC	https://paperswithcode.com/paper/decision-trees-for-helpdesk-advisor-graphs
Repo
Framework

Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning


Title	Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning
Authors	Sahil Sharma, Girish Raguvir J, Srivatsan Ramesh, Balaraman Ravindran
Abstract	Reinforcement Learning (RL) can model complex behavior policies for goal-directed sequential decision making tasks. A hallmark of RL algorithms is Temporal Difference (TD) learning: value function for the current state is moved towards a bootstrapped target that is estimated using next state’s value function. $\lambda$-returns generalize beyond 1-step returns and strike a balance between Monte Carlo and TD learning methods. While lambda-returns have been extensively studied in RL, they haven’t been explored a lot in Deep RL. This paper’s first contribution is an exhaustive benchmarking of lambda-returns. Although mathematically tractable, the use of exponentially decaying weighting of n-step returns based targets in lambda-returns is a rather ad-hoc design choice. Our second major contribution is that we propose a generalization of lambda-returns called Confidence-based Autodidactic Returns (CAR), wherein the RL agent learns the weighting of the n-step returns in an end-to-end manner. This allows the agent to learn to decide how much it wants to weigh the n-step returns based targets. In contrast, lambda-returns restrict RL agents to use an exponentially decaying weighting scheme. Autodidactic returns can be used for improving any RL algorithm which uses TD learning. We empirically demonstrate that using sophisticated weighted mixtures of multi-step returns (like CAR and lambda-returns) considerably outperforms the use of n-step returns. We perform our experiments on the Asynchronous Advantage Actor Critic (A3C) algorithm in the Atari 2600 domain.
Tasks	Decision Making
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07445v2
PDF	http://arxiv.org/pdf/1705.07445v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-mix-n-step-returns-generalizing
Repo
Framework

Deep Region Hashing for Efficient Large-scale Instance Search from Images


Title	Deep Region Hashing for Efficient Large-scale Instance Search from Images
Authors	Jingkuan Song, Tao He, Lianli Gao, Xing Xu, Heng Tao Shen
Abstract	Instance Search (INS) is a fundamental problem for many applications, while it is more challenging comparing to traditional image search since the relevancy is defined at the instance level. Existing works have demonstrated the success of many complex ensemble systems that are typically conducted by firstly generating object proposals, and then extracting handcrafted and/or CNN features of each proposal for matching. However, object bounding box proposals and feature extraction are often conducted in two separated steps, thus the effectiveness of these methods collapses. Also, due to the large amount of generated proposals, matching speed becomes the bottleneck that limits its application to large-scale datasets. To tackle these issues, in this paper we propose an effective and efficient Deep Region Hashing (DRH) approach for large-scale INS using an image patch as the query. Specifically, DRH is an end-to-end deep neural network which consists of object proposal, feature extraction, and hash code generation. DRH shares full-image convolutional feature map with the region proposal network, thus enabling nearly cost-free region proposals. Also, each high-dimensional, real-valued region features are mapped onto a low-dimensional, compact binary codes for the efficient object region level matching on large-scale dataset. Experimental results on four datasets show that our DRH can achieve even better performance than the state-of-the-arts in terms of MAP, while the efficiency is improved by nearly 100 times.
Tasks	Code Generation, Image Retrieval, Instance Search
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07901v1
PDF	http://arxiv.org/pdf/1701.07901v1.pdf
PWC	https://paperswithcode.com/paper/deep-region-hashing-for-efficient-large-scale
Repo
Framework

On the Unreported-Profile-is-Negative Assumption for Predictive Cheminformatics


Title	On the Unreported-Profile-is-Negative Assumption for Predictive Cheminformatics
Authors	Chao Lan, Sai Nivedita Chandrasekaran, Jun Huan
Abstract	In cheminformatics, compound-target binding profiles has been a main source of data for research. For data repositories that only provide positive profiles, a popular assumption is that unreported profiles are all negative. In this paper, we caution audience not to take this assumption for granted, and present empirical evidence of its ineffectiveness from a machine learning perspective. Our examination is based on a setting where binding profiles are used as features to train predictive models; we show (1) prediction performance degrades when the assumption fails and (2) explicit recovery of unreported profiles improves prediction performance. In particular, we propose a framework that jointly recovers profiles and learns predictive model, and show it achieves further performance improvement. The presented study not only suggests applying matrix recovery methods to recover unreported profiles, but also initiates a new missing feature problem which we called Learning with Positive and Unknown Features.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.01184v3
PDF	http://arxiv.org/pdf/1704.01184v3.pdf
PWC	https://paperswithcode.com/paper/on-the-unreported-profile-is-negative
Repo
Framework

Convolutional Neural Networks for Sentiment Classification on Business Reviews


Title	Convolutional Neural Networks for Sentiment Classification on Business Reviews
Authors	Andreea Salinca
Abstract	Recently Convolutional Neural Networks (CNNs) models have proven remarkable results for text classification and sentiment analysis. In this paper, we present our approach on the task of classifying business reviews using word embeddings on a large-scale dataset provided by Yelp: Yelp 2017 challenge dataset. We compare word-based CNN using several pre-trained word embeddings and end-to-end vector representations for text reviews classification. We conduct several experiments to capture the semantic relationship between business reviews and we use deep learning techniques that prove that the obtained results are competitive with traditional methods.
Tasks	Sentiment Analysis, Text Classification, Word Embeddings
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05978v1
PDF	http://arxiv.org/pdf/1710.05978v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-sentiment
Repo
Framework

A Survey of Human Activity Recognition Using WiFi CSI


Title	A Survey of Human Activity Recognition Using WiFi CSI
Authors	Siamak Yousefi, Hirokazu Narui, Sankalp Dayal, Stefano Ermon, Shahrokh Valaee
Abstract	In this article, we present a survey of recent advances in passive human behaviour recognition in indoor areas using the channel state information (CSI) of commercial WiFi systems. Movement of human body causes a change in the wireless signal reflections, which results in variations in the CSI. By analyzing the data streams of CSIs for different activities and comparing them against stored models, human behaviour can be recognized. This is done by extracting features from CSI data streams and using machine learning techniques to build models and classifiers. The techniques from the literature that are presented herein have great performances, however, instead of the machine learning techniques employed in these works, we propose to use deep learning techniques such as long-short term memory (LSTM) recurrent neural network (RNN), and show the improved performance. We also discuss about different challenges such as environment change, frame rate selection, and multi-user scenario, and suggest possible directions for future work.
Tasks	Activity Recognition, Human Activity Recognition
Published	2017-08-23
URL	http://arxiv.org/abs/1708.07129v1
PDF	http://arxiv.org/pdf/1708.07129v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-human-activity-recognition-using
Repo
Framework

Early Improving Recurrent Elastic Highway Network


Title	Early Improving Recurrent Elastic Highway Network
Authors	Hyunsin Park, Chang D. Yoo
Abstract	To model time-varying nonlinear temporal dynamics in sequential data, a recurrent network capable of varying and adjusting the recurrence depth between input intervals is examined. The recurrence depth is extended by several intermediate hidden state units, and the weight parameters involved in determining these units are dynamically calculated. The motivation behind the paper lies on overcoming a deficiency in Recurrent Highway Networks and improving their performances which are currently at the forefront of RNNs: 1) Determining the appropriate number of recurrent depth in RHN for different tasks is a huge burden and just setting it to a large number is computationally wasteful with possible repercussion in terms of performance degradation and high latency. Expanding on the idea of adaptive computation time (ACT), with the use of an elastic gate in the form of a rectified exponentially decreasing function taking on as arguments as previous hidden state and input, the proposed model is able to evaluate the appropriate recurrent depth for each input. The rectified gating function enables the most significant intermediate hidden state updates to come early such that significant performance gain is achieved early. 2) Updating the weights from that of previous intermediate layer offers a richer representation than the use of shared weights across all intermediate recurrence layers. The weight update procedure is just an expansion of the idea underlying hypernetworks. To substantiate the effectiveness of the proposed network, we conducted three experiments: regression on synthetic data, human activity recognition, and language modeling on the Penn Treebank dataset. The proposed networks showed better performance than other state-of-the-art recurrent networks in all three experiments.
Tasks	Activity Recognition, Human Activity Recognition, Language Modelling
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04116v1
PDF	http://arxiv.org/pdf/1708.04116v1.pdf
PWC	https://paperswithcode.com/paper/early-improving-recurrent-elastic-highway
Repo
Framework

Conceptualization Topic Modeling


Title	Conceptualization Topic Modeling
Authors	Yi-Kun Tang, Xian-Ling Mao, Heyan Huang, Guihua Wen
Abstract	Recently, topic modeling has been widely used to discover the abstract topics in text corpora. Most of the existing topic models are based on the assumption of three-layer hierarchical Bayesian structure, i.e. each document is modeled as a probability distribution over topics, and each topic is a probability distribution over words. However, the assumption is not optimal. Intuitively, it’s more reasonable to assume that each topic is a probability distribution over concepts, and then each concept is a probability distribution over words, i.e. adding a latent concept layer between topic layer and word layer in traditional three-layer assumption. In this paper, we verify the proposed assumption by incorporating the new assumption in two representative topic models, and obtain two novel topic models. Extensive experiments were conducted among the proposed models and corresponding baselines, and the results show that the proposed models significantly outperform the baselines in terms of case study and perplexity, which means the new assumption is more reasonable than traditional one.
Tasks	Topic Models
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02090v1
PDF	http://arxiv.org/pdf/1704.02090v1.pdf
PWC	https://paperswithcode.com/paper/conceptualization-topic-modeling
Repo
Framework

Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians


Title	Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians
Authors	Zhiyuan Liu, Soumya Kundu, Lijun Chen, Enoch Yeung
Abstract	In this paper we propose a new Koopman operator approach to the decomposition of nonlinear dynamical systems using Koopman Gramians. We introduce the notion of an input-Koopman operator, and show how input-Koopman operators can be used to cast a nonlinear system into the classical state-space form, and identify conditions under which input and state observable functions are well separated. We then extend an existing method of dynamic mode decomposition for learning Koopman operators from data known as deep dynamic mode decomposition to systems with controls or disturbances. We illustrate the accuracy of the method in learning an input-state separable Koopman operator for an example system, even when the underlying system exhibits mixed state-input terms. We next introduce a nonlinear decomposition algorithm, based on Koopman Gramians, that maximizes internal subsystem observability and disturbance rejection from unwanted noise from other subsystems. We derive a relaxation based on Koopman Gramians and multi-way partitioning for the resulting NP-hard decomposition problem. We lastly illustrate the proposed algorithm with the swing dynamics for an IEEE 39-bus system.
Tasks
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01719v1
PDF	http://arxiv.org/pdf/1710.01719v1.pdf
PWC	https://paperswithcode.com/paper/decomposition-of-nonlinear-dynamical-systems
Repo
Framework

Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization


Title	Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization
Authors	Qunwei Li, Yi Zhou, Yingbin Liang, Pramod K. Varshney
Abstract	In many modern machine learning applications, structures of underlying mathematical models often yield nonconvex optimization problems. Due to the intractability of nonconvexity, there is a rising need to develop efficient methods for solving general nonconvex problems with certain performance guarantee. In this work, we investigate the accelerated proximal gradient method for nonconvex programming (APGnc). The method compares between a usual proximal gradient step and a linear extrapolation step, and accepts the one that has a lower function value to achieve a monotonic decrease. In specific, under a general nonsmooth and nonconvex setting, we provide a rigorous argument to show that the limit points of the sequence generated by APGnc are critical points of the objective function. Then, by exploiting the Kurdyka-{\L}ojasiewicz (\KL) property for a broad class of functions, we establish the linear and sub-linear convergence rates of the function value sequence generated by APGnc. We further propose a stochastic variance reduced APGnc (SVRG-APGnc), and establish its linear convergence under a special case of the \KL property. We also extend the analysis to the inexact version of these methods and develop an adaptive momentum strategy that improves the numerical performance.
Tasks
Published	2017-05-14
URL	http://arxiv.org/abs/1705.04925v1
PDF	http://arxiv.org/pdf/1705.04925v1.pdf
PWC	https://paperswithcode.com/paper/convergence-analysis-of-proximal-gradient
Repo
Framework

Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection


Title	Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection
Authors	Marek Rei, Luana Bulat, Douwe Kiela, Ekaterina Shutova
Abstract	The ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date rely on hand-engineered features and there is still no consensus in the field as to which features are optimal for this task. In this paper, we present the first deep learning architecture designed to capture metaphorical composition. Our results demonstrate that it outperforms the existing approaches in the metaphor identification task.
Tasks
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00575v1
PDF	http://arxiv.org/pdf/1709.00575v1.pdf
PWC	https://paperswithcode.com/paper/grasping-the-finer-point-a-supervised
Repo
Framework

Dynamic classifier chains for multi-label learning


Title	Dynamic classifier chains for multi-label learning
Authors	Pawel Trajdos, Marek Kurzynski
Abstract	In this paper, we deal with the task of building a dynamic ensemble of chain classifiers for multi-label classification. To do so, we proposed two concepts of classifier chains algorithms that are able to change label order of the chain without rebuilding the entire model. Such modes allows anticipating the instance-specific chain order without a significant increase in computational burden. The proposed chain models are built using the Naive Bayes classifier and nearest neighbour approach as a base single-label classifiers. To take the benefits of the proposed algorithms, we developed a simple heuristic that allows the system to find relatively good label order. The heuristic sort labels according to the label-specific classification quality gained during the validation phase. The heuristic tries to minimise the phenomenon of error propagation in the chain. The experimental results showed that the proposed model based on Naive Bayes classifier the above-mentioned heuristic is an efficient tool for building dynamic chain classifiers.
Tasks	Multi-Label Classification, Multi-Label Learning
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07491v2
PDF	http://arxiv.org/pdf/1710.07491v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-classifier-chains-for-multi-label
Repo
Framework