October 16, 2019

2401 words 12 mins read

Paper Group NAWR 29

Paper Group NAWR 29

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation. Contour Knowledge Transfer for Salient Object Detection. Inexact trust-region algorithms on Riemannian manifolds. Fixing Translation Divergences in Parallel Corpora for Neural MT. Encoding Crowd Interaction With Deep Neural Network for Pedestr …

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

Title Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
Authors Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, Seon Joo Kim
Abstract Video super-resolution (VSR) has become even more important recently to provide high resolution (HR) contents for ultra high definition displays. While many deep learning based VSR methods have been proposed, most of them rely heavily on the accuracy of motion estimation and compensation. We introduce a fundamentally different framework for VSR in this paper. We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation. With our approach, an HR image is reconstructed directly from the input image using the dynamic upsampling filters, and the fine details are added through the computed residual. Our network with the help of a new data augmentation technique can generate much sharper HR videos with temporal consistency, compared with the previous methods. We also provide analysis of our network through extensive experiments to show how the network deals with motions implicitly.
Tasks Data Augmentation, Motion Compensation, Motion Estimation, Super-Resolution, Video Super-Resolution
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Jo_Deep_Video_Super-Resolution_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Jo_Deep_Video_Super-Resolution_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-video-super-resolution-network-using
Repo https://github.com/yhjo09/VSR-DUF
Framework tf

Contour Knowledge Transfer for Salient Object Detection

Title Contour Knowledge Transfer for Salient Object Detection
Authors Xin Li, Fan Yang, Hong Cheng, Wei Liu, Dinggang Shen
Abstract In recent years, deep Convolutional Neural Networks (CNNs) have broken all records in salient object detection. However, training such a deep model requires a large amount of manual annotations. Our goal is to overcome this limitation by automatically converting an existing deep contour detection model into a salient object detection model without using any manual salient object masks. For this purpose, we have created a deep network architecture, namely Contour-to-Saliency Network (C2S-Net), by grafting a new branch onto a well-trained contour detection network. Therefore, our C2S-Net has two branches for performing two different tasks: 1) predicting contours with the original contour branch, and 2) estimating per-pixel saliency score of each image with the newly-added saliency branch. To bridge the gap between these two tasks, we further propose a contour-to-saliency transferring method to automatically generate salient object masks which can be used to train the saliency branch from outputs of the contour branch. Finally, we introduce a novel alternating training pipeline to gradually update the network parameters. In this scheme, the contour branch generates saliency masks for training the saliency branch, while the saliency branch, in turn, feeds back saliency knowledge in the form of saliency-aware contour labels, for fine-tuning the contour branch. The proposed method achieves state-of-the-art performance on five well-known benchmarks, outperforming existing fully supervised methods while also maintaining high efficiency.
Tasks Contour Detection, Object Detection, Salient Object Detection, Transfer Learning
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Xin_Li_Contour_Knowledge_Transfer_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Xin_Li_Contour_Knowledge_Transfer_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/contour-knowledge-transfer-for-salient-object
Repo https://github.com/lixin666/C2SNet
Framework none

Inexact trust-region algorithms on Riemannian manifolds

Title Inexact trust-region algorithms on Riemannian manifolds
Authors Hiroyuki Kasai, Bamdev Mishra
Abstract We consider an inexact variant of the popular Riemannian trust-region algorithm for structured big-data minimization problems. The proposed algorithm approximates the gradient and the Hessian in addition to the solution of a trust-region sub-problem. Addressing large-scale finite-sum problems, we specifically propose sub-sampled algorithms with a fixed bound on sub-sampled Hessian and gradient sizes, where the gradient and Hessian are computed by a random sampling technique. Numerical evaluations demonstrate that the proposed algorithms outperform state-of-the-art Riemannian deterministic and stochastic gradient algorithms across different applications.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7679-inexact-trust-region-algorithms-on-riemannian-manifolds
PDF http://papers.nips.cc/paper/7679-inexact-trust-region-algorithms-on-riemannian-manifolds.pdf
PWC https://paperswithcode.com/paper/inexact-trust-region-algorithms-on-riemannian
Repo https://github.com/hiroyuki-kasai/Subsampled-RTR
Framework none

Fixing Translation Divergences in Parallel Corpora for Neural MT

Title Fixing Translation Divergences in Parallel Corpora for Neural MT
Authors MinhQuang Pham, Josep Crego, Jean Senellart, Fran{\c{c}}ois Yvon
Abstract Corpus-based approaches to machine translation rely on the availability of clean parallel corpora. Such resources are scarce, and because of the automatic processes involved in their preparation, they are often noisy. This paper describes an unsupervised method for detecting translation divergences in parallel sentences. We rely on a neural network that computes cross-lingual sentence similarity scores, which are then used to effectively filter out divergent translations. Furthermore, similarity scores predicted by the network are used to identify and fix some partial divergences, yielding additional parallel segments. We evaluate these methods for English-French and English-German machine translation tasks, and show that using filtered/corrected corpora actually improves MT performance.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1328/
PDF https://www.aclweb.org/anthology/D18-1328
PWC https://paperswithcode.com/paper/fixing-translation-divergences-in-parallel
Repo https://github.com/jmcrego/similarity
Framework tf

Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory Prediction

Title Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory Prediction
Authors Yanyu Xu, Zhixin Piao, Shenghua Gao
Abstract Pedestrian trajectory prediction is a challenging task because of the complex nature of humans. In this paper, we tackle the problem within a deep learning framework by considering motion information of each pedestrian and its interaction with the crowd. Specifically, motivated by the residual learning in deep learning, we propose to predict displacement between neighboring frames for each pedestrian sequentially. To predict such displacement, we design a crowd interaction deep neural network (CIDNN) which considers the different importance of different pedestrians for the displacement prediction of a target pedestrian. Specifically, we use an LSTM to model motion information for all pedestrians and use a multi-layer perceptron to map the location of each pedestrian to a high dimensional feature space where the inner product between features is used as a measurement for the spatial affinity between two pedestrians. Then we weight the motion features of all pedestrians based on their spatial affinity to the target pedestrian for location displacement prediction. Extensive experiments on publicly available datasets validate the effectiveness of our method for trajectory prediction.
Tasks Trajectory Prediction
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Xu_Encoding_Crowd_Interaction_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Encoding_Crowd_Interaction_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/encoding-crowd-interaction-with-deep-neural
Repo https://github.com/svip-lab/CIDNN
Framework pytorch

Scoring and Classifying Implicit Positive Interpretations: A Challenge of Class Imbalance

Title Scoring and Classifying Implicit Positive Interpretations: A Challenge of Class Imbalance
Authors Chantal van Son, Roser Morante, Lora Aroyo, Piek Vossen
Abstract This paper reports on a reimplementation of a system on detecting implicit positive meaning from negated statements. In the original regression experiment, different positive interpretations per negation are scored according to their likelihood. We convert the scores to classes and report our results on both the regression and classification tasks. We show that a baseline taking the mean score or most frequent class is hard to beat because of class imbalance in the dataset. Our error analysis indicates that an approach that takes the information structure into account (i.e. which information is new or contrastive) may be promising, which requires looking beyond the syntactic and semantic characteristics of negated statements.
Tasks Natural Language Inference, Question Answering
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1191/
PDF https://www.aclweb.org/anthology/C18-1191
PWC https://paperswithcode.com/paper/scoring-and-classifying-implicit-positive
Repo https://github.com/cltl/positive-interpretations
Framework none

Discovering Implicit Knowledge with Unary Relations

Title Discovering Implicit Knowledge with Unary Relations
Authors Michael Glass, Alfio Gliozzo
Abstract State-of-the-art relation extraction approaches are only able to recognize relationships between mentions of entity arguments stated explicitly in the text and typically localized to the same sentence. However, the vast majority of relations are either implicit or not sententially localized. This is a major problem for Knowledge Base Population, severely limiting recall. In this paper we propose a new methodology to identify relations between two entities, consisting of detecting a very large number of unary relations, and using them to infer missing entities. We describe a deep learning architecture able to learn thousands of such relations very efficiently by using a common deep learning based representation. Our approach largely outperforms state of the art relation extraction technology on a newly introduced web scale knowledge base population benchmark, that we release to the research community.
Tasks Knowledge Base Population, Natural Language Inference, Relation Extraction
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1147/
PDF https://www.aclweb.org/anthology/P18-1147
PWC https://paperswithcode.com/paper/discovering-implicit-knowledge-with-unary
Repo https://github.com/IBM/cc-dbp
Framework none

Dilated Convolutional Neural Networks for Time Series Forecasting

Title Dilated Convolutional Neural Networks for Time Series Forecasting
Authors Anastasia Borovykh ∗ Sander Bohte † Cornelis W. Oosterlee
Abstract We present a method for conditional time series forecasting based on an adaptation of the recent deep convolutional WaveNet architecture. The proposed network contains stacks of dilated convolutions that allow it to access a broad range of history when forecasting, a ReLU activation function and conditioning is performed by applying multiple convolutional filters in parallel to separate time series which allows for the fast processing of data and the exploitation of the correlation structure between the multivariate time series. We test and analyze the performance of the convolutional network both unconditionally as well as conditionally for financial time series forecasting using the S&P500, the volatility index, the CBOE interest rate and several exchange rates and extensively compare it to the performance of the well-known autoregressive model and a long-short term memory network. We show that a convolutional network is well-suited for regression-type problems and is able to effectively learn dependencies in and between the series without the need for long historical time series, is a time-efficient and easy to implement alternative to recurrent-type networks and tends to outperform linear and recurrent models.
Tasks Time Series, Time Series Forecasting
Published 2018-01-02
URL http://papers.ssrn.com/sol3/Delivery.cfm?abstractid=3272962
PDF http://papers.ssrn.com/sol3/Delivery.cfm?abstractid=3272962
PWC https://paperswithcode.com/paper/dilated-convolutional-neural-networks-for-3
Repo https://github.com/RitikaAg/dilated_convolution_network
Framework none

Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis

Title Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis
Authors Lishuang Li, Yang Liu, AnQiao Zhou
Abstract Aspect-level sentiment analysis aims to identify the sentiment of a specific target in its context. Previous works have proved that the interactions between aspects and the contexts are important. On this basis, we also propose a succinct hierarchical attention based mechanism to fuse the information of targets and the contextual words. In addition, most existing methods ignore the position information of the aspect when encoding the sentence. In this paper, we argue that the position-aware representations are beneficial to this task. Therefore, we propose a hierarchical attention based position-aware network (HAPN), which introduces position embeddings to learn the position-aware representations of sentences and further generate the target-specific representations of contextual words. The experimental results on SemEval 2014 dataset show that our approach outperforms the state-of-the-art methods.
Tasks Aspect-Based Sentiment Analysis, Feature Engineering, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-1018/
PDF https://www.aclweb.org/anthology/K18-1018
PWC https://paperswithcode.com/paper/hierarchical-attention-based-position-aware
Repo https://github.com/DUT-LiuYang/Aspect-Sentiment-Analysis
Framework none

EuroGames16: Evaluating Change Detection in Online Conversation

Title EuroGames16: Evaluating Change Detection in Online Conversation
Authors Cyril Goutte, Yunli Wang, Fangming Liao, Zachary Zanussi, Samuel Larkin, Yuri Grinberg
Abstract
Tasks Time Series
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1277/
PDF https://www.aclweb.org/anthology/L18-1277
PWC https://paperswithcode.com/paper/eurogames16-evaluating-change-detection-in
Repo https://github.com/cyrilgoutte/EuroGames16
Framework none

Word Error Rate Estimation for Speech Recognition: e-WER

Title Word Error Rate Estimation for Speech Recognition: e-WER
Authors Ahmed Ali, Steve Renals
Abstract Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive. In this paper, we propose a novel approach to estimate WER, or e-WER, which does not require a gold-standard transcription of the test set. Our e-WER framework uses a comprehensive set of features: ASR recognised text, character recognition results to complement recognition output, and internal decoder features. We report results for the two features; black-box and glass-box using unseen 24 Arabic broadcast programs. Our system achieves 16.9{%} WER root mean squared error (RMSE) across 1,400 sentences. The estimated overall WER e-WER was 25.3{%} for the three hours test set, while the actual WER was 28.5{%}.
Tasks Language Modelling, Large Vocabulary Continuous Speech Recognition, Machine Translation, Speech Recognition, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2004/
PDF https://www.aclweb.org/anthology/P18-2004
PWC https://paperswithcode.com/paper/word-error-rate-estimation-for-speech
Repo https://github.com/qcri/e-wer
Framework none

Learning to Reason with Third Order Tensor Products

Title Learning to Reason with Third Order Tensor Products
Authors Imanol Schlag, Jürgen Schmidhuber
Abstract We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation. Our architecture is trained end-to-end through gradient descent on a variety of simple natural language reasoning tasks, significantly outperforming the latest state-of-the-art models in single-task and all-tasks settings. We also augment a subset of the data such that training and test data exhibit large systematic differences and show that our approach generalises better than the previous state-of-the-art.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8203-learning-to-reason-with-third-order-tensor-products
PDF http://papers.nips.cc/paper/8203-learning-to-reason-with-third-order-tensor-products.pdf
PWC https://paperswithcode.com/paper/learning-to-reason-with-third-order-tensor-1
Repo https://github.com/ischlag/TPR-RNN
Framework tf

PDFAnno: a Web-based Linguistic Annotation Tool for PDF Documents

Title PDFAnno: a Web-based Linguistic Annotation Tool for PDF Documents
Authors Hiroyuki Shindo, Yohei Munesada, Yuji Matsumoto
Abstract
Tasks Coreference Resolution, Optical Character Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1175/
PDF https://www.aclweb.org/anthology/L18-1175
PWC https://paperswithcode.com/paper/pdfanno-a-web-based-linguistic-annotation
Repo https://github.com/paperai/pdfanno
Framework none

Real-time ‘Actor-Critic’ Tracking

Title Real-time ‘Actor-Critic’ Tracking
Authors Boyu Chen, Dong Wang, Peixia Li, Shuang Wang, Huchuan Lu
Abstract In this work, we propose a novel tracking algorithm with real-time performance based on the ‘Actor-Critic’ framework. This framework consists of two major components: ‘Actor’ and ‘Critic’. The ‘Actor’ model aims to infer the optimal choice in a continuous action space, which directly makes the tracker move the bounding box to the object location in the current frame. For offline training,the‘Critic’modelisintroducedtoforma‘Actor-Critic’frameworkwith reinforcement learning and outputs a Q-value to guide the learning process of both ‘Actor’ and ‘Critic’ deep networks. Then, we modify the original deep deterministic policy gradient algorithm to effectively train our ‘Actor-Critic’ model for the tracking task. For online tracking, the ‘Actor’ model provides a dynamic search strategy to locate the tracked object efficiently and the ‘Critic’ model acts as a verification module to make our tracker more robust. To the best of our knowledge, this work is the first attempt to exploit the continuous action and ‘Actor-Critic’ framework for visual tracking. Extensive experimental results on popular benchmarks demonstrate that the proposed tracker performs favorably against many state-of-the-art methods, with real-time performance.
Tasks Visual Tracking
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Boyu_Chen_Real-time_Actor-Critic_Tracking_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Boyu_Chen_Real-time_Actor-Critic_Tracking_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/real-time-actor-critic-tracking
Repo https://github.com/bychen515/ACT
Framework pytorch

Corpus Building and Evaluation of Aspect-based Opinion Summaries from Tweets in Spanish

Title Corpus Building and Evaluation of Aspect-based Opinion Summaries from Tweets in Spanish
Authors Daniel Pe{~n}aloza, Rodrigo L{'o}pez, Juanjos{'e} Tenorio, H{'e}ctor G{'o}mez, Arturo Oncevay-Marcos, Marco A. Sobrevilla Cabezudo
Abstract
Tasks Abstractive Text Summarization, Opinion Mining
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1663/
PDF https://www.aclweb.org/anthology/L18-1663
PWC https://paperswithcode.com/paper/corpus-building-and-evaluation-of-aspect
Repo https://github.com/iapucp/spop-summ-lrec2018
Framework none
comments powered by Disqus