October 19, 2019

2644 words 13 mins read

Paper Group ANR 195

Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction. Local Contrast Learning. Attribute-aware Collaborative Filtering: Survey and Classification. Argument Harvesting Using Chatbots. Vertex nomination: The canonical sampling and the extended spectral nomination schemes. Elastic Neural Networks: A Scalable Framework for …

Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction


Title	Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction
Authors	Mohit Shridhar, David Hsu
Abstract	This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input images and language expressions. INGRESS allows for unconstrained object categories and unconstrained language expressions. Further, it asks questions to disambiguate referring expressions interactively. To achieve these, we take the approach of grounding by generation and propose a two-stage neural network model for grounding. The first stage uses a neural network to generate visual descriptions of objects, compares them with the input language expression, and identifies a set of candidate objects. The second stage uses another neural network to examine all pairwise relations between the candidates and infers the most likely referred object. The same neural networks are used for both grounding and question generation for disambiguation. Experiments show that INGRESS outperformed a state-of-the-art method on the RefCOCO dataset and in robot experiments with humans.
Tasks	Question Generation
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03831v1
PDF	http://arxiv.org/pdf/1806.03831v1.pdf
PWC	https://paperswithcode.com/paper/interactive-visual-grounding-of-referring
Repo
Framework

Local Contrast Learning


Title	Local Contrast Learning
Authors	Chuanyun Xu, Yang Zhang, Xin Feng, YongXing Ge, Yihao Zhang, Jianwu Long
Abstract	Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named Local Contrast Learning (LCL) based on the key insight about a human cognitive behavior that human recognizes the objects in a specific context by contrasting the objects in the context or in her/his memory. LCL is used to train a deep model that can contrast the recognizing sample with a couple of contrastive samples randomly drawn and shuffled. On one-shot classification task on Omniglot, the deep model based LCL with 122 layers and 1.94 millions of parameters, which was trained on a tiny dataset with only 60 classes and 20 samples per class, achieved the accuracy 97.99% that outperforms human and state-of-the-art established by Bayesian Program Learning (BPL) trained on 964 classes. LCL is a fundamental idea which can be applied to alleviate parametric model’s overfitting resulted by lack of training samples.
Tasks	Omniglot
Published	2018-02-10
URL	http://arxiv.org/abs/1802.03499v1
PDF	http://arxiv.org/pdf/1802.03499v1.pdf
PWC	https://paperswithcode.com/paper/local-contrast-learning
Repo
Framework

Attribute-aware Collaborative Filtering: Survey and Classification


Title	Attribute-aware Collaborative Filtering: Survey and Classification
Authors	Wen-Hao Chen, Chin-Chi Hsu, Yi-An Lai, Vincent Liu, Mi-Yen Yeh, Shou-De Lin
Abstract	Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e.g. age), items (e.g. price), or even ratings (e.g. rating time). This paper surveys works in the past decade developing attribute-aware CF systems, and discovered that mathematically they can be classified into four different categories. We provide the readers not only the high level mathematical interpretation of the existing works in this area but also the mathematical insight for each category of models. Finally we provide in-depth experiment results comparing the effectiveness of the major works in each category.
Tasks
Published	2018-10-20
URL	http://arxiv.org/abs/1810.08765v1
PDF	http://arxiv.org/pdf/1810.08765v1.pdf
PWC	https://paperswithcode.com/paper/attribute-aware-collaborative-filtering
Repo
Framework

Argument Harvesting Using Chatbots


Title	Argument Harvesting Using Chatbots
Authors	Lisa A. Chalaguine, Anthony Hunter, Henry W. W. Potts, Fiona L. Hamilton
Abstract	Much research in computational argumentation assumes that arguments and counterarguments can be obtained in some way. Yet, to improve and apply models of argument, we need methods for acquiring them. Current approaches include argument mining from text, hand coding of arguments by researchers, or generating arguments from knowledge bases. In this paper, we propose a new approach, which we call argument harvesting, that uses a chatbot to enter into a dialogue with a participant to get arguments and counterarguments from him or her. Because it is automated, the chatbot can be used repeatedly in many dialogues, and thereby it can generate a large corpus. We describe the architecture of the chatbot, provide methods for managing a corpus of arguments and counterarguments, and an evaluation of our approach in a case study concerning attitudes of women to participation in sport.
Tasks	Argument Mining, Chatbot
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04253v1
PDF	http://arxiv.org/pdf/1805.04253v1.pdf
PWC	https://paperswithcode.com/paper/argument-harvesting-using-chatbots
Repo
Framework

Vertex nomination: The canonical sampling and the extended spectral nomination schemes


Title	Vertex nomination: The canonical sampling and the extended spectral nomination schemes
Authors	Jordan Yoder, Li Chen, Henry Pao, Eric Bridgeford, Keith Levin, Donniell Fishkind, Carey Priebe, Vince Lyzinski
Abstract	Suppose that one particular block in a stochastic block model is of interest, but block labels are only observed for a few of the vertices in the network. Utilizing a graph realized from the model and the observed block labels, the vertex nomination task is to order the vertices with unobserved block labels into a ranked nomination list with the goal of having an abundance of interesting vertices near the top of the list. There are vertex nomination schemes in the literature, including the optimally precise canonical nomination scheme~$\mathcal{L}^C$ and the consistent spectral partitioning nomination scheme~$\mathcal{L}^P$. While the canonical nomination scheme $\mathcal{L}^C$ is provably optimally precise, it is computationally intractable, being impractical to implement even on modestly sized graphs. With this in mind, an approximation of the canonical scheme—denoted the {\it canonical sampling nomination scheme} $\mathcal{L}^{CS}$—is introduced; $\mathcal{L}^{CS}$ relies on a scalable, Markov chain Monte Carlo-based approximation of $\mathcal{L}^{C}$, and converges to $\mathcal{L}^{C}$ as the amount of sampling goes to infinity. The spectral partitioning nomination scheme is also extended to the {\it extended spectral partitioning nomination scheme}, $\mathcal{L}^{EP}$, which introduces a novel semisupervised clustering framework to improve upon the precision of $\mathcal{L}^P$. Real-data and simulation experiments are employed to illustrate the precision of these vertex nomination schemes, as well as their empirical computational complexity. Keywords: vertex nomination, Markov chain Monte Carlo, spectral partitioning, Mclust MSC[2010]: 60J22, 65C40, 62H30, 62H25
Tasks
Published	2018-02-14
URL	https://arxiv.org/abs/1802.04960v2
PDF	https://arxiv.org/pdf/1802.04960v2.pdf
PWC	https://paperswithcode.com/paper/vertex-nomination-the-canonical-sampling-and
Repo
Framework

Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision


Title	Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
Authors	Yue Bai, Shuvra S. Bhattacharyya, Antti P. Happonen, Heikki Huttunen
Abstract	We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables flexible control of the computational load and balances the tradeoff between accuracy and execution time. Moreover, we present an interesting finding that the intermediate outputs can act as a regularizer at training time, improving the prediction accuracy. In the experimental section we demonstrate the performance of our proposed framework with various commonly used pretrained deep networks in the use case of apparent age estimation.
Tasks	Age Estimation, Image Classification
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00453v2
PDF	http://arxiv.org/pdf/1807.00453v2.pdf
PWC	https://paperswithcode.com/paper/elastic-neural-networks-a-scalable-framework
Repo
Framework

Can a Chatbot Determine My Diet?: Addressing Challenges of Chatbot Application for Meal Recommendation


Title	Can a Chatbot Determine My Diet?: Addressing Challenges of Chatbot Application for Meal Recommendation
Authors	Ahmed Fadhil
Abstract	Poor nutrition can lead to reduced immunity, increased susceptibility to disease, impaired physical and mental development, and reduced productivity. A conversational agent can support people as a virtual coach, however building such systems still have its associated challenges and limitations. This paper describes the background and motivation for chatbot systems in the context of healthy nutrition recommendation. We discuss current challenges associated with chatbot application, we tackled technical, theoretical, behavioural, and social aspects of the challenges. We then propose a pipeline to be used as guidelines by developers to implement theoretically and technically robust chatbot systems.
Tasks	Chatbot
Published	2018-02-25
URL	http://arxiv.org/abs/1802.09100v1
PDF	http://arxiv.org/pdf/1802.09100v1.pdf
PWC	https://paperswithcode.com/paper/can-a-chatbot-determine-my-diet-addressing
Repo
Framework

Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach


Title	Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
Authors	Ming Yu, Varun Gupta, Mladen Kolar
Abstract	We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We propose a GDT (Gradient Descent with hard Thresholding) algorithm to efficiently recover matrices with such structure, by minimizing a bi-convex function over a nonconvex set of constraints. We show linear convergence of the iterates obtained by GDT to a region within statistical error of an optimal solution. As an application of our method, we consider multi-task learning problems and show that the statistical error rate obtained by GDT is near optimal compared to minimax rate. Experiments demonstrate competitive performance and much faster running speed compared to existing methods, on both simulations and real data sets.
Tasks	Multi-Task Learning
Published	2018-02-20
URL	http://arxiv.org/abs/1802.06967v2
PDF	http://arxiv.org/pdf/1802.06967v2.pdf
PWC	https://paperswithcode.com/paper/recovery-of-simultaneous-low-rank-and-two-way
Repo
Framework

Minutia Texture Cylinder Codes for fingerprint matching


Title	Minutia Texture Cylinder Codes for fingerprint matching
Authors	Wajih Ullah Baig, Umar Munir, Waqas Ellahi, Adeel Ejaz, Kashif Sardar
Abstract	Minutia Cylinder Codes (MCC) are minutiae based fingerprint descriptors that take into account minutiae information in a fingerprint image for fingerprint matching. In this paper, we present a modification to the underlying information of the MCC descriptor and show that using different features, the accuracy of matching is highly affected by such changes. MCC originally being a minutia only descriptor is transformed into a texture descriptor. The transformation is from minutiae angular information to orientation, frequency and energy information using Short Time Fourier Transform (STFT) analysis. The minutia cylinder codes are converted to minutiae texture cylinder codes (MTCC). Based on a fixed set of parameters, the proposed changes to MCC show improved performance on FVC 2002 and 2004 data sets and surpass the traditional MCC performance.
Tasks
Published	2018-07-06
URL	http://arxiv.org/abs/1807.02251v1
PDF	http://arxiv.org/pdf/1807.02251v1.pdf
PWC	https://paperswithcode.com/paper/minutia-texture-cylinder-codes-for
Repo
Framework

Cheap Non-standard Analysis and Computability


Title	Cheap Non-standard Analysis and Computability
Authors	Olivier Bournez, Sabrina Ouazzani
Abstract	Non standard analysis is an area of Mathematics dealing with notions of infinitesimal and infinitely large numbers, in which many statements from classical analysis can be expressed very naturally. Cheap non-standard analysis introduced by Terence Tao in 2012 is based on the idea that considering that a property holds eventually is sufficient to give the essence of many of its statements. This provides constructivity but at some (acceptable) price. We consider computability in cheap non-standard analysis. We prove that many concepts from computable analysis as well as several concepts from computability can be very elegantly and alternatively presented in this framework. It provides a dual view and dual proofs to several statements already known in these fields.
Tasks
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09746v2
PDF	http://arxiv.org/pdf/1804.09746v2.pdf
PWC	https://paperswithcode.com/paper/cheap-non-standard-analysis-and-computability
Repo
Framework

Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging


Title	Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging
Authors	Diego Patiño, Jonathan Avendaño, John Willian Branch
Abstract	We present a superpixel-based strategy for segmenting skin lesion on dermoscopic images. The segmentation is carried out by over-segmenting the original image using the SLIC algorithm, and then merge the resulting superpixels into two regions: healthy skin and lesion. The mean RGB color of each superpixel was used as merging criterion. The presented method is capable of dealing with segmentation problems commonly found in dermoscopic images such as hair removal, oil bubbles, changes in illumination, and reflections images without any additional steps. The method was evaluated on the PH2 and ISIC 2017 dataset with results comparable to the state-of-art.
Tasks	Lesion Segmentation
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06759v1
PDF	http://arxiv.org/pdf/1808.06759v1.pdf
PWC	https://paperswithcode.com/paper/automatic-skin-lesion-segmentation-on
Repo
Framework

Optimal Scheduling of Electrolyzer in Power Market with Dynamic Prices


Title	Optimal Scheduling of Electrolyzer in Power Market with Dynamic Prices
Authors	Yusheng Luo, Min Xian, Manish Mohanpurkar, Bishnu P. Bhattarai, Anudeep Medam, Rahul Kadavil, Rob Hovsapian
Abstract	Optimal scheduling of hydrogen production in dynamic pricing power market can maximize the profit of hydrogen producer; however, it highly depends on the accurate forecast of hydrogen consumption. In this paper, we propose a deep leaning based forecasting approach for predicting hydrogen consumption of fuel cell vehicles in future taxi industry. The cost of hydrogen production is minimized by utilizing the proposed forecasting tool to reduce the hydrogen produced during high cost on-peak hours and guide hydrogen producer to store sufficient hydrogen during low cost off-peak hours.
Tasks
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10283v1
PDF	http://arxiv.org/pdf/1806.10283v1.pdf
PWC	https://paperswithcode.com/paper/optimal-scheduling-of-electrolyzer-in-power
Repo
Framework

Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding


Title	Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
Authors	Guozhen An, Mehrnoosh Shafiee, Davood Shamsi
Abstract	To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.
Tasks	Chatbot
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05373v2
PDF	http://arxiv.org/pdf/1802.05373v2.pdf
PWC	https://paperswithcode.com/paper/improving-retrieval-modeling-using-cross
Repo
Framework

Causal effects based on distributional distances


Title	Causal effects based on distributional distances
Authors	Kwangho Kim, Jisu Kim, Edward H. Kennedy
Abstract	We develop a novel framework for estimating causal effects based on the discrepancy between unobserved counterfactual distributions. In our setting a causal effect is defined in terms of the $L_1$ distance between different counterfactual outcome distributions, rather than a mean difference in outcome values. Directly comparing counterfactual outcome distributions can provide more nuanced and valuable information about causality than a simple comparison of means. We consider single- and multi-source randomized studies, as well as observational studies, and analyze error bounds and asymptotic properties of the proposed estimators. We further propose methods to construct confidence intervals for the unknown mean distribution distance. Finally, we illustrate the new methods and verify their effectiveness in empirical studies.
Tasks
Published	2018-06-08
URL	http://arxiv.org/abs/1806.02935v1
PDF	http://arxiv.org/pdf/1806.02935v1.pdf
PWC	https://paperswithcode.com/paper/causal-effects-based-on-distributional
Repo
Framework

Differential Variable Speed Limits Control for Freeway Recurrent Bottlenecks via Deep Reinforcement learning


Title	Differential Variable Speed Limits Control for Freeway Recurrent Bottlenecks via Deep Reinforcement learning
Authors	Yuankai Wu, Huachun Tan, Bin Ran
Abstract	Variable speed limits (VSL) control is a flexible way to improve traffic condition,increase safety and reduce emission. There is an emerging trend of using reinforcement learning technique for VSL control and recent studies have shown promising results. Currently, deep learning is enabling reinforcement learning to develope autonomous control agents for problems that were previously intractable. In this paper, we propose a more effective deep reinforcement learning (DRL) model for differential variable speed limits (DVSL) control, in which the dynamic and different speed limits among lanes can be imposed. The proposed DRL models use a novel actor-critic architecture which can learn a large number of discrete speed limits in a continues action space. Different reward signals, e.g. total travel time, bottleneck speed, emergency braking, and vehicular emission are used to train the DVSL controller, and comparison between these reward signals are conducted. We test proposed DRL baased DVSL controllers on a simulated freeway recurrent bottleneck. Results show that the efficiency, safety and emissions can be improved by the proposed method. We also show some interesting findings through the visulization of the control policies generated from DRL models.
Tasks
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10952v1
PDF	http://arxiv.org/pdf/1810.10952v1.pdf
PWC	https://paperswithcode.com/paper/differential-variable-speed-limits-control
Repo
Framework