July 28, 2019

2996 words 15 mins read

Paper Group ANR 332

Including Dialects and Language Varieties in Author Profiling. A Note on a Tight Lower Bound for MNL-Bandit Assortment Selection Models. Deep Cross-Modal Audio-Visual Generation. Telling Cause from Effect using MDL-based Local and Global Regression. Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images. Fore …

Including Dialects and Language Varieties in Author Profiling


Title	Including Dialects and Language Varieties in Author Profiling
Authors	Alina Maria Ciobanu, Marcos Zampieri, Shervin Malmasi, Liviu P. Dinu
Abstract	This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00621v1
PDF	http://arxiv.org/pdf/1707.00621v1.pdf
PWC	https://paperswithcode.com/paper/including-dialects-and-language-varieties-in
Repo
Framework

A Note on a Tight Lower Bound for MNL-Bandit Assortment Selection Models


Title	A Note on a Tight Lower Bound for MNL-Bandit Assortment Selection Models
Authors	Xi Chen, Yining Wang
Abstract	In this short note we consider a dynamic assortment planning problem under the capacitated multinomial logit (MNL) bandit model. We prove a tight lower bound on the accumulated regret that matches existing regret upper bounds for all parameters (time horizon $T$, number of items $N$ and maximum assortment capacity $K$) up to logarithmic factors. Our results close an $O(\sqrt{K})$ gap between upper and lower regret bounds from existing works.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06109v3
PDF	http://arxiv.org/pdf/1709.06109v3.pdf
PWC	https://paperswithcode.com/paper/a-note-on-a-tight-lower-bound-for-mnl-bandit
Repo
Framework


Title	Deep Cross-Modal Audio-Visual Generation
Authors	Lele Chen, Sudhanshu Srivastava, Zhiyao Duan, Chenliang Xu
Abstract	Cross-modal audio-visual perception has been a long-lasting topic in psychology and neurology, and various studies have discovered strong correlations in human perception of auditory and visual stimuli. Despite works in computational multimodal modeling, the problem of cross-modal audio-visual generation has not been systematically studied in the literature. In this paper, we make the first attempt to solve this cross-modal generation problem leveraging the power of deep generative adversarial training. Specifically, we use conditional generative adversarial networks to achieve cross-modal audio-visual generation of musical performances. We explore different encoding methods for audio and visual signals, and work on two scenarios: instrument-oriented generation and pose-oriented generation. Being the first to explore this new problem, we compose two new datasets with pairs of images and sounds of musical performances of different instruments. Our experiments using both classification and human evaluations demonstrate that our model has the ability to generate one modality, i.e., audio/visual, from the other modality, i.e., visual/audio, to a good extent. Our experiments on various design choices along with the datasets will facilitate future research in this new problem space.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08292v1
PDF	http://arxiv.org/pdf/1704.08292v1.pdf
PWC	https://paperswithcode.com/paper/deep-cross-modal-audio-visual-generation
Repo
Framework

Telling Cause from Effect using MDL-based Local and Global Regression


Title	Telling Cause from Effect using MDL-based Local and Global Regression
Authors	Alexander Marx, Jilles Vreeken
Abstract	We consider the fundamental problem of inferring the causal direction between two univariate numeric random variables $X$ and $Y$ from observational data. The two-variable case is especially difficult to solve since it is not possible to use standard conditional independence tests between the variables. To tackle this problem, we follow an information theoretic approach based on Kolmogorov complexity and use the Minimum Description Length (MDL) principle to provide a practical solution. In particular, we propose a compression scheme to encode local and global functional relations using MDL-based regression. We infer $X$ causes $Y$ in case it is shorter to describe $Y$ as a function of $X$ than the inverse direction. In addition, we introduce Slope, an efficient linear-time algorithm that through thorough empirical evaluation on both synthetic and real world data we show outperforms the state of the art by a wide margin.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08915v1
PDF	http://arxiv.org/pdf/1709.08915v1.pdf
PWC	https://paperswithcode.com/paper/telling-cause-from-effect-using-mdl-based
Repo
Framework

Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images


Title	Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images
Authors	Tribhuvanesh Orekondy, Mario Fritz, Bernt Schiele
Abstract	Images convey a broad spectrum of personal information. If such images are shared on social media platforms, this personal information is leaked which conflicts with the privacy of depicted persons. Therefore, we aim for automated approaches to redact such private information and thereby protect privacy of the individual. By conducting a user study we find that obfuscating the image regions related to the private information leads to privacy while retaining utility of the images. Moreover, by varying the size of the regions different privacy-utility trade-offs can be achieved. Our findings argue for a “redaction by segmentation” paradigm. Hence, we propose the first sizable dataset of private images “in the wild” annotated with pixel and instance level labels across a broad range of privacy classes. We present the first model for automatic redaction of diverse private information.
Tasks
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01066v1
PDF	http://arxiv.org/pdf/1712.01066v1.pdf
PWC	https://paperswithcode.com/paper/connecting-pixels-to-privacy-and-utility
Repo
Framework

Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point clouds


Title	Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point clouds
Authors	Hamid Hamraz, Marco A. Contreras, Jun Zhang
Abstract	Airborne laser scanning (LiDAR) point clouds over large forested areas can be processed to segment individual trees and subsequently extract tree-level information. Existing segmentation procedures typically detect more than 90% of overstory trees, yet they barely detect 60% of understory trees because of the occlusion effect of higher canopy layers. Although understory trees provide limited financial value, they are an essential component of ecosystem functioning by offering habitat for numerous wildlife species and influencing stand development. Here we model the occlusion effect in terms of point density. We estimate the fractions of points representing different canopy layers (one overstory and multiple understory) and also pinpoint the required density for reasonable tree segmentation (where accuracy plateaus). We show that at a density of ~170 pt/m-sqr understory trees can likely be segmented as accurately as overstory trees. Given the advancements of LiDAR sensor technology, point clouds will affordably reach this required density. Using modern computational approaches for big data, the denser point clouds can efficiently be processed to ultimately allow accurate remote quantification of forest resources. The methodology can also be adopted for other similar remote sensing or advanced imaging applications such as geological subsurface modelling or biomedical tissue analysis.
Tasks
Published	2017-02-17
URL	http://arxiv.org/abs/1702.06188v2
PDF	http://arxiv.org/pdf/1702.06188v2.pdf
PWC	https://paperswithcode.com/paper/forest-understory-trees-can-be-segmented
Repo
Framework

Next Generation Business Intelligence and Analytics: A Survey


Title	Next Generation Business Intelligence and Analytics: A Survey
Authors	Quoc Duy Vo, Jaya Thomas, Shinyoung Cho, Pradipta De, Bong Jun Choi, Lee Sael
Abstract	Business Intelligence and Analytics (BI&A) is the process of extracting and predicting business-critical insights from data. Traditional BI focused on data collection, extraction, and organization to enable efficient query processing for deriving insights from historical data. With the rise of big data and cloud computing, there are many challenges and opportunities for the BI. Especially with the growing number of data sources, traditional BI&A are evolving to provide intelligence at different scales and perspectives - operational BI, situational BI, self-service BI. In this survey, we review the evolution of business intelligence systems in full scale from back-end architecture to and front-end applications. We focus on the changes in the back-end architecture that deals with the collection and organization of the data. We also review the changes in the front-end applications, where analytic services and visualization are the core components. Using a uses case from BI in Healthcare, which is one of the most complex enterprises, we show how BI&A will play an important role beyond the traditional usage. The survey provides a holistic view of Business Intelligence and Analytics for anyone interested in getting a complete picture of the different pieces in the emerging next generation BI&A solutions.
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03402v1
PDF	http://arxiv.org/pdf/1704.03402v1.pdf
PWC	https://paperswithcode.com/paper/next-generation-business-intelligence-and
Repo
Framework

Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English


Title	Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English
Authors	Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour
Abstract	Neural Machine Translation (NMT) is a new approach for Machine Translation (MT), and due to its success, it has absorbed the attention of many researchers in the field. In this paper, we study NMT model on Persian-English language pairs, to analyze the model and investigate the appropriateness of the model for scarce-resourced scenarios, the situation that exists for Persian-centered translation systems. We adjust the model for the Persian language and find the best parameters and hyper parameters for two tasks: translation and transliteration. We also apply some preprocessing task on the Persian dataset which yields to increase for about one point in terms of BLEU score. Also, we have modified the loss function to enhance the word alignment of the model. This new loss function yields a total of 1.87 point improvements in terms of BLEU score in the translation quality.
Tasks	Machine Translation, Transliteration, Word Alignment
Published	2017-01-07
URL	http://arxiv.org/abs/1701.01854v1
PDF	http://arxiv.org/pdf/1701.01854v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-on-scarce-resource
Repo
Framework

An Iterative Co-Saliency Framework for RGBD Images


Title	An Iterative Co-Saliency Framework for RGBD Images
Authors	Runmin Cong, Jianjun Lei, Huazhu Fu, Weisi Lin, Qingming Huang, Xiaochun Cao, Chunping Hou
Abstract	As a newly emerging and significant topic in computer vision community, co-saliency detection aims at discovering the common salient objects in multiple related images. The existing methods often generate the co-saliency map through a direct forward pipeline which is based on the designed cues or initialization, but lack the refinement-cycle scheme. Moreover, they mainly focus on RGB image and ignore the depth information for RGBD images. In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model. Three schemes are employed in the proposed RGBD co-saliency framework, which include the addition scheme, deletion scheme, and iteration scheme. The addition scheme is used to highlight the salient regions based on intra-image depth propagation and saliency propagation, while the deletion scheme filters the saliency regions and removes the non-common salient regions based on interimage constraint. The iteration scheme is proposed to obtain more homogeneous and consistent co-saliency map. Furthermore, a novel descriptor, named depth shape prior, is proposed in the addition scheme to introduce the depth information to enhance identification of co-salient objects. The proposed method can effectively exploit any existing 2D saliency model to work well in RGBD co-saliency scenarios. The experiments on two RGBD cosaliency datasets demonstrate the effectiveness of our proposed framework.
Tasks	Co-Saliency Detection, Saliency Detection
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01371v1
PDF	http://arxiv.org/pdf/1711.01371v1.pdf
PWC	https://paperswithcode.com/paper/an-iterative-co-saliency-framework-for-rgbd
Repo
Framework

The Dialog State Tracking Challenge with Bayesian Approach


Title	The Dialog State Tracking Challenge with Bayesian Approach
Authors	Quan Nguyen
Abstract	Generative model has been one of the most common approaches for solving the Dialog State Tracking Problem with the capabilities to model the dialog hypotheses in an explicit manner. The most important task in such Bayesian networks models is constructing the most reliable user models by learning and reflecting the training data into the probability distribution of user actions conditional on networks states. This paper provides an overall picture of the learning process in a Bayesian framework with an emphasize on the state-of-the-art theoretical analyses of the Expectation Maximization learning algorithm.
Tasks
Published	2017-02-20
URL	http://arxiv.org/abs/1702.06199v1
PDF	http://arxiv.org/pdf/1702.06199v1.pdf
PWC	https://paperswithcode.com/paper/the-dialog-state-tracking-challenge-with
Repo
Framework

Semantic Code Repair using Neuro-Symbolic Transformation Networks


Title	Semantic Code Repair using Neuro-Symbolic Transformation Networks
Authors	Jacob Devlin, Jonathan Uesato, Rishabh Singh, Pushmeet Kohli
Abstract	We study the problem of semantic code repair, which can be broadly defined as automatically fixing non-syntactic bugs in source code. The majority of past work in semantic code repair assumed access to unit tests against which candidate repairs could be validated. In contrast, the goal here is to develop a strong statistical model to accurately predict both bug locations and exact fixes without access to information about the intended correct behavior of the program. Achieving such a goal requires a robust contextual repair model, which we train on a large corpus of real-world source code that has been augmented with synthetically injected bugs. Our framework adopts a two-stage approach where first a large set of repair candidates are generated by rule-based processors, and then these candidates are scored by a statistical model using a novel neural network architecture which we refer to as Share, Specialize, and Compete. Specifically, the architecture (1) generates a shared encoding of the source code using an RNN over the abstract syntax tree, (2) scores each candidate repair using specialized network modules, and (3) then normalizes these scores together so they can compete against one another in comparable probability space. We evaluate our model on a real-world test set gathered from GitHub containing four common categories of bugs. Our model is able to predict the exact correct repair 41% of the time with a single guess, compared to 13% accuracy for an attentional sequence-to-sequence model.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11054v1
PDF	http://arxiv.org/pdf/1710.11054v1.pdf
PWC	https://paperswithcode.com/paper/semantic-code-repair-using-neuro-symbolic
Repo
Framework

Deep adversarial neural decoding


Title	Deep adversarial neural decoding
Authors	Yağmur Güçlütürk, Umut Güçlü, Katja Seeliger, Sander Bosch, Rob van Lier, Marcel van Gerven
Abstract	Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the nonlinear transformation from perceived stimuli to latent features with adversarial training of convolutional neural networks. We test our approach with a functional magnetic resonance imaging experiment and show that it can generate state-of-the-art reconstructions of perceived faces from brain activations.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07109v3
PDF	http://arxiv.org/pdf/1705.07109v3.pdf
PWC	https://paperswithcode.com/paper/deep-adversarial-neural-decoding
Repo
Framework

Augmented Reality for Depth Cues in Monocular Minimally Invasive Surgery


Title	Augmented Reality for Depth Cues in Monocular Minimally Invasive Surgery
Authors	Long Chen, Wen Tang, Nigel W. John, Tao Ruan Wan, Jian Jun Zhang
Abstract	One of the major challenges in Minimally Invasive Surgery (MIS) such as laparoscopy is the lack of depth perception. In recent years, laparoscopic scene tracking and surface reconstruction has been a focus of investigation to provide rich additional information to aid the surgical process and compensate for the depth perception issue. However, robust 3D surface reconstruction and augmented reality with depth perception on the reconstructed scene are yet to be reported. This paper presents our work in this area. First, we adopt a state-of-the-art visual simultaneous localization and mapping (SLAM) framework - ORB-SLAM - and extend the algorithm for use in MIS scenes for reliable endoscopic camera tracking and salient point mapping. We then develop a robust global 3D surface reconstruction frame- work based on the sparse point clouds extracted from the SLAM framework. Our approach is to combine an outlier removal filter within a Moving Least Squares smoothing algorithm and then employ Poisson surface reconstruction to obtain smooth surfaces from the unstructured sparse point cloud. Our proposed method has been quantitatively evaluated compared with ground-truth camera trajectories and the organ model surface we used to render the synthetic simulation videos. In vivo laparoscopic videos used in the tests have demonstrated the robustness and accuracy of our proposed framework on both camera tracking and surface reconstruction, illustrating the potential of our algorithm for depth augmentation and depth-corrected augmented reality in MIS with monocular endoscopes.
Tasks	Simultaneous Localization and Mapping
Published	2017-03-01
URL	http://arxiv.org/abs/1703.01243v1
PDF	http://arxiv.org/pdf/1703.01243v1.pdf
PWC	https://paperswithcode.com/paper/augmented-reality-for-depth-cues-in-monocular
Repo
Framework

Optimal Warping Paths are unique for almost every Pair of Time Series


Title	Optimal Warping Paths are unique for almost every Pair of Time Series
Authors	Brijnesh J. Jain, David Schultz
Abstract	Update rules for learning in dynamic time warping spaces are based on optimal warping paths between parameter and input time series. In general, optimal warping paths are not unique resulting in adverse effects in theory and practice. Under the assumption of squared error local costs, we show that no two warping paths have identical costs almost everywhere in a measure-theoretic sense. Two direct consequences of this result are: (i) optimal warping paths are unique almost everywhere, and (ii) the set of all pairs of time series with multiple equal-cost warping paths coincides with the union of exponentially many zero sets of quadratic forms. One implication of the proposed results is that typical distance-based cost functions such as the k-means objective are differentiable almost everywhere and can be minimized by subgradient methods.
Tasks	Time Series
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05681v2
PDF	http://arxiv.org/pdf/1705.05681v2.pdf
PWC	https://paperswithcode.com/paper/optimal-warping-paths-are-unique-for-almost
Repo
Framework

Learning Robust Features with Incremental Auto-Encoders


Title	Learning Robust Features with Incremental Auto-Encoders
Authors	Yanan Li, Donghui Wang
Abstract	Automatically learning features, especially robust features, has attracted much attention in the machine learning community. In this paper, we propose a new method to learn non-linear robust features by taking advantage of the data manifold structure. We first follow the commonly used trick of the trade, that is learning robust features with artificially corrupted data, which are training samples with manually injected noise. Following the idea of the auto-encoder, we first assume features should contain much information to well reconstruct the input from its corrupted copies. However, merely reconstructing clean input from its noisy copies could make data manifold in the feature space noisy. To address this problem, we propose a new method, called Incremental Auto-Encoders, to iteratively denoise the extracted features. We assume the noisy manifold structure is caused by a diffusion process. Consequently, we reverse this specific diffusion process to further contract this noisy manifold, which results in an incremental optimization of model parameters . Furthermore, we show these learned non-linear features can be stacked into a hierarchy of features. Experimental results on real-world datasets demonstrate the proposed method can achieve better classification performances.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09476v1
PDF	http://arxiv.org/pdf/1705.09476v1.pdf
PWC	https://paperswithcode.com/paper/learning-robust-features-with-incremental
Repo
Framework