October 20, 2019

2772 words 14 mins read

Paper Group ANR 75

Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention. An Exploration of Unreliable News Classification in Brazil and The U.S. Answering the “why” in Answer Set Programming - A Survey of Explanation Approaches. Adaptive distributed methods under communication constraints. Prioritizin …

Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention


Title	Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention
Authors	Guyue Hu, Bo Cui, Shan Yu
Abstract	Benefiting from its succinctness and robustness, skeleton-based action recognition has recently attracted much attention. Most existing methods utilize local networks (e.g., recurrent, convolutional, and graph convolutional networks) to extract spatio-temporal dynamics hierarchically. As a consequence, the local and non-local dependencies, which contain more details and semantics respectively, are asynchronously captured in different level of layers. Moreover, existing methods are limited to the spatio-temporal domain and ignore information in the frequency domain. To better extract synchronous detailed and semantic information from multi-domains, we propose a residual frequency attention (rFA) block to focus on discriminative patterns in the frequency domain, and a synchronous local and non-local (SLnL) block to simultaneously capture the details and semantics in the spatio-temporal domain. Besides, a soft-margin focal loss (SMFL) is proposed to optimize the learning whole process, which automatically conducts data selection and encourages intrinsic margins in classifiers. Our approach significantly outperforms other state-of-the-art methods on several large-scale datasets.
Tasks	Skeleton Based Action Recognition, Temporal Action Localization
Published	2018-11-10
URL	https://arxiv.org/abs/1811.04237v3
PDF	https://arxiv.org/pdf/1811.04237v3.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-action-recognition-with
Repo
Framework

An Exploration of Unreliable News Classification in Brazil and The U.S


Title	An Exploration of Unreliable News Classification in Brazil and The U.S
Authors	Mauricio Gruppi, Benjamin D. Horne, Sibel Adali
Abstract	The propagation of unreliable information is on the rise in many places around the world. This expansion is facilitated by the rapid spread of information and anonymity granted by the Internet. The spread of unreliable information is a wellstudied issue and it is associated with negative social impacts. In a previous work, we have identified significant differences in the structure of news articles from reliable and unreliable sources in the US media. Our goal in this work was to explore such differences in the Brazilian media. We found significant features in two data sets: one with Brazilian news in Portuguese and another one with US news in English. Our results show that features related to the writing style were prominent in both data sets and, despite the language difference, some features have a universal behavior, being significant to both US and Brazilian news articles. Finally, we combined both data sets and used the universal features to build a machine learning classifier to predict the source type of a news article as reliable or unreliable.
Tasks
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02875v1
PDF	http://arxiv.org/pdf/1806.02875v1.pdf
PWC	https://paperswithcode.com/paper/an-exploration-of-unreliable-news
Repo
Framework

Answering the “why” in Answer Set Programming - A Survey of Explanation Approaches


Title	Answering the “why” in Answer Set Programming - A Survey of Explanation Approaches
Authors	Jorge Fandinno, Claudia Schulz
Abstract	Artificial Intelligence (AI) approaches to problem-solving and decision-making are becoming more and more complex, leading to a decrease in the understandability of solutions. The European Union’s new General Data Protection Regulation tries to tackle this problem by stipulating a “right to explanation” for decisions made by AI systems. One of the AI paradigms that may be affected by this new regulation is Answer Set Programming (ASP). Thanks to the emergence of efficient solvers, ASP has recently been used for problem-solving in a variety of domains, including medicine, cryptography, and biology. To ensure the successful application of ASP as a problem-solving paradigm in the future, explanations of ASP solutions are crucial. In this survey, we give an overview of approaches that provide an answer to the question of why an answer set is a solution to a given problem, notably off-line justifications, causal graphs, argumentative explanations and why-not provenance, and highlight their similarities and differences. Moreover, we review methods explaining why a set of literals is not an answer set or why no solution exists at all.
Tasks	Decision Making
Published	2018-09-21
URL	http://arxiv.org/abs/1809.08034v1
PDF	http://arxiv.org/pdf/1809.08034v1.pdf
PWC	https://paperswithcode.com/paper/answering-the-why-in-answer-set-programming-a
Repo
Framework

Adaptive distributed methods under communication constraints


Title	Adaptive distributed methods under communication constraints
Authors	Botond Szabo, Harry van Zanten
Abstract	We study distributed estimation methods under communication constraints in a distributed version of the nonparametric random design regression model. We derive minimax lower bounds and exhibit methods that attain those bounds. Moreover, we show that adaptive estimation is possible in this setting.
Tasks
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00864v2
PDF	http://arxiv.org/pdf/1804.00864v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-distributed-methods-under
Repo
Framework

Prioritizing network communities


Title	Prioritizing network communities
Authors	Marinka Zitnik, Rok Sosic, Jure Leskovec
Abstract	Uncovering modular structure in networks is fundamental for systems in biology, physics, and engineering. Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory. Only a few communities can typically be validated, and it is thus important to prioritize which communities to select for downstream experimentation. Here we develop CRank, a mathematically principled approach for prioritizing network communities. CRank efficiently evaluates robustness and magnitude of structural features of each community and then combines these features into the community prioritization. CRank can be used with any community detection method. It needs only information provided by the network structure and does not require any additional metadata or labels. However, when available, CRank can incorporate domain-specific information to further boost performance. Experiments on many large networks show that CRank effectively prioritizes communities, yielding a nearly 50-fold improvement in community prioritization.
Tasks	Community Detection
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02411v2
PDF	http://arxiv.org/pdf/1805.02411v2.pdf
PWC	https://paperswithcode.com/paper/prioritizing-network-communities
Repo
Framework

When and where do feed-forward neural networks learn localist representations?


Title	When and where do feed-forward neural networks learn localist representations?
Authors	Ella M. Gale, Nicolas Martin, Jeffrey S. Bowers
Abstract	According to parallel distributed processing (PDP) theory in psychology, neural networks (NN) learn distributed rather than interpretable localist representations. This view has been held so strongly that few researchers have analysed single units to determine if this assumption is correct. However, recent results from psychology, neuroscience and computer science have shown the occasional existence of local codes emerging in artificial and biological neural networks. In this paper, we undertake the first systematic survey of when local codes emerge in a feed-forward neural network, using generated input and output data with known qualities. We find that the number of local codes that emerge from a NN follows a well-defined distribution across the number of hidden layer neurons, with a peak determined by the size of input data, number of examples presented and the sparsity of input data. Using a 1-hot output code drastically decreases the number of local codes on the hidden layer. The number of emergent local codes increases with the percentage of dropout applied to the hidden layer, suggesting that the localist encoding may offer a resilience to noisy networks. This data suggests that localist coding can emerge from feed-forward PDP networks and suggests some of the conditions that may lead to interpretable localist representations in the cortex. The findings highlight how local codes should not be dismissed out of hand.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03934v1
PDF	http://arxiv.org/pdf/1806.03934v1.pdf
PWC	https://paperswithcode.com/paper/when-and-where-do-feed-forward-neural
Repo
Framework

Subsampled Turbulence Removal Network


Title	Subsampled Turbulence Removal Network
Authors	Wai Ho Chak, Chun Pong Lau, Lok Ming Lui
Abstract	We present a deep-learning approach to restore a sequence of turbulence-distorted video frames from turbulent deformations and space-time varying blurs. Instead of requiring a massive training sample size in deep networks, we purpose a training strategy that is based on a new data augmentation method to model turbulence from a relatively small dataset. Then we introduce a subsampled method to enhance the restoration performance of the presented GAN model. The contributions of the paper is threefold: first, we introduce a simple but effective data augmentation algorithm to model the turbulence in real life for training in the deep network; Second, we firstly purpose the Wasserstein GAN combined with $\ell_1$ cost for successful restoration of turbulence-corrupted video sequence; Third, we combine the subsampling algorithm to filter out strongly corrupted frames to generate a video sequence with better quality.
Tasks	Data Augmentation
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04418v2
PDF	http://arxiv.org/pdf/1807.04418v2.pdf
PWC	https://paperswithcode.com/paper/subsampled-turbulence-removal-network
Repo
Framework

On the Proximal Gradient Algorithm with Alternated Inertia


Title	On the Proximal Gradient Algorithm with Alternated Inertia
Authors	Franck Iutzeler, Jerome Malick
Abstract	In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm with alternated inertia based on local geometric properties of the objective function. The results are put into perspective by discussions on several extensions and illustrations on common regularized problems.
Tasks
Published	2018-01-17
URL	http://arxiv.org/abs/1801.05589v1
PDF	http://arxiv.org/pdf/1801.05589v1.pdf
PWC	https://paperswithcode.com/paper/on-the-proximal-gradient-algorithm-with
Repo
Framework

Translating LPOD and CR-Prolog2 into Standard Answer Set Programs


Title	Translating LPOD and CR-Prolog2 into Standard Answer Set Programs
Authors	Joohyung Lee, Zhun Yang
Abstract	Logic Programs with Ordered Disjunction (LPOD) is an extension of standard answer set programs to handle preference using the construct of ordered disjunction, and CR-Prolog2 is an extension of standard answer set programs with consistency restoring rules and LPOD-like ordered disjunction. We present reductions of each of these languages into the standard ASP language, which gives us an alternative way to understand the extensions in terms of the standard ASP language.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00643v1
PDF	http://arxiv.org/pdf/1805.00643v1.pdf
PWC	https://paperswithcode.com/paper/translating-lpod-and-cr-prolog2-into-standard
Repo
Framework

Graph-Based Decoding for Event Sequencing and Coreference Resolution


Title	Graph-Based Decoding for Event Sequencing and Coreference Resolution
Authors	Zhengzhong Liu, Teruko Mitamura, Eduard Hovy
Abstract	Events in text documents are interrelated in complex ways. In this paper, we study two types of relation: Event Coreference and Event Sequencing. We show that the popular tree-like decoding structure for automated Event Coreference is not suitable for Event Sequencing. To this end, we propose a graph-based decoding algorithm that is applicable to both tasks. The new decoding algorithm supports flexible feature sets for both tasks. Empirically, our event coreference system has achieved state-of-the-art performance on the TAC-KBP 2015 event coreference task and our event sequencing system beats a strong temporal-based, oracle-informed baseline. We discuss the challenges of studying these event relations.
Tasks	Coreference Resolution
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05099v1
PDF	http://arxiv.org/pdf/1806.05099v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-decoding-for-event-sequencing-and-1
Repo
Framework

Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image


Title	Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
Authors	Yusuke Yoshiyasu, Ryusuke Sagawa, Ko Ayusawa, Akihiko Murai
Abstract	In this paper, we present Skeleton Transformer Networks (SkeletonNet), an end-to-end framework that can predict not only 3D joint positions but also 3D angular pose (bone rotations) of a human skeleton from a single color image. This in turn allows us to generate skinned mesh animations. Here, we propose a two-step regression approach. The first step regresses bone rotations in order to obtain an initial solution by considering skeleton structure. The second step performs refinement based on heatmap regressor using a 3D pose representation called cross heatmap which stacks heatmaps of xy and zy coordinates. By training the network using the proposed 3D human pose dataset that is comprised of images annotated with 3D skeletal angular poses, we showed that SkeletonNet can predict a full 3D human pose (joint positions and bone rotations) from a single image in-the-wild.
Tasks
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11328v1
PDF	http://arxiv.org/pdf/1812.11328v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-transformer-networks-3d-human-pose
Repo
Framework

Bike Flow Prediction with Multi-Graph Convolutional Networks


Title	Bike Flow Prediction with Multi-Graph Convolutional Networks
Authors	Di Chai, Leye Wang, Qiang Yang
Abstract	One fundamental issue in managing bike sharing systems is the bike flow prediction. Due to the hardness of predicting the flow for a single station, recent research works often predict the bike flow at cluster-level. While such studies gain satisfactory prediction accuracy, they cannot directly guide some fine-grained bike sharing system management issues at station-level. In this paper, we revisit the problem of the station-level bike flow prediction, aiming to boost the prediction accuracy leveraging the breakthroughs of deep learning techniques. We propose a new multi-graph convolutional neural network model to predict the bike flow at station-level, where the key novelty is viewing the bike sharing system from the graph perspective. More specifically, we construct multiple inter-station graphs for a bike sharing system. In each graph, nodes are stations, and edges are a certain type of relations between stations. Then, multiple graphs are constructed to reflect heterogeneous relationships (e.g., distance, ride record correlation). Afterward, we fuse the multiple graphs and then apply the convolutional layers on the fused graph to predict station-level future bike flow. In addition to the estimated bike flow value, our model also gives the prediction confidence interval so as to help the bike sharing system managers make decisions. Using New York City and Chicago bike sharing data for experiments, our model can outperform state-of-the-art station-level prediction models by reducing 25.1% and 17.0% of prediction error in New York City and Chicago, respectively.
Tasks
Published	2018-07-28
URL	http://arxiv.org/abs/1807.10934v1
PDF	http://arxiv.org/pdf/1807.10934v1.pdf
PWC	https://paperswithcode.com/paper/bike-flow-prediction-with-multi-graph
Repo
Framework

Entropic Latent Variable Discovery


Title	Entropic Latent Variable Discovery
Authors	Murat Kocaoglu, Sanjay Shakkottai, Alexandros G. Dimakis, Constantine Caramanis, Sriram Vishwanath
Abstract	We consider the problem of discovering the simplest latent variable that can make two observed discrete variables conditionally independent. This problem has appeared in the literature as probabilistic latent semantic analysis (pLSA), and has connections to non-negative matrix factorization. When the simplicity of the variable is measured through its cardinality, we show that a solution to this latent variable discovery problem can be used to distinguish direct causal relations from spurious correlations among almost all joint distributions on simple causal graphs with two observed variables. Conjecturing a similar identifiability result holds with Shannon entropy, we study a loss function that trades-off between entropy of the latent variable and the conditional mutual information of the observed variables. We then propose a latent variable discovery algorithm – LatentSearch – and show that its stationary points are the stationary points of our loss function. We experimentally show that LatentSearch can indeed be used to distinguish direct causal relations from spurious correlations.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10399v1
PDF	http://arxiv.org/pdf/1807.10399v1.pdf
PWC	https://paperswithcode.com/paper/entropic-latent-variable-discovery
Repo
Framework

Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation


Title	Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation
Authors	Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho, David K. Park, Ziming Wu, Xiaojuan Ma, Jaegul Choo
Abstract	This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. In contrast to existing approaches, our model can understand rich text, whether it is a single word, a phrase, or a sentence, and generate multiple possible palettes from it. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT). Our proposed model called Text2Colors consists of two conditional generative adversarial networks: the text-to-palette generation networks and the palette-based colorization networks. The former captures the semantics of the text input and produce relevant color palettes. The latter colorizes a grayscale image using the generated color palette. Our evaluation results show that people preferred our generated palettes over ground truth palettes and that our model can effectively reflect the given palette when colorizing an image.
Tasks	Colorization
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04128v2
PDF	http://arxiv.org/pdf/1804.04128v2.pdf
PWC	https://paperswithcode.com/paper/coloring-with-words-guiding-image
Repo
Framework

Adversarial Semantic Scene Completion from a Single Depth Image


Title	Adversarial Semantic Scene Completion from a Single Depth Image
Authors	Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari
Abstract	We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular, we suggest using multiple adversarial loss terms that not only enforce realistic outputs with respect to the ground truth, but also an effective embedding of the internal features. This is done by correlating the latent features of the encoder working on partial 2.5D data with the latent features extracted from a variational 3D auto-encoder trained to reconstruct the complete semantic scene. In addition, differently from other approaches that operate entirely through 3D convolutions, at test time we retain the original 2.5D structure of the input during downsampling to improve the effectiveness of the internal representation of our model. We test our approach on the main benchmark datasets for semantic scene completion to qualitatively and quantitatively assess the effectiveness of our proposal.
Tasks
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10901v1
PDF	http://arxiv.org/pdf/1810.10901v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-semantic-scene-completion-from-a
Repo
Framework