October 15, 2019

2015 words 10 mins read

Paper Group NANR 164

Paper Group NANR 164

3D Ego-Pose Estimation via Imitation Learning. Referring Image Segmentation via Recurrent Refinement Networks. Learning Diachronic Analogies to Analyze Concept Change. Multilingual Parallel Corpus for Global Communication Plan. SSN MLRG1 at SemEval-2018 Task 3: Irony Detection in English Tweets Using MultiLayer Perceptron. Sentence Weighting for Ne …

3D Ego-Pose Estimation via Imitation Learning

Title 3D Ego-Pose Estimation via Imitation Learning
Authors Ye Yuan, Kris Kitani
Abstract Ego-pose estimation, i.e., estimating a person’s 3D pose with a single wearable camera, has many potential applications in activity monitoring. For these applications, both accurate and physically plausible estimates are desired, with the latter often overlooked by existing work. Traditional computer vision-based approaches using temporal smoothing only take into account the kinematics of the motion without considering the physics that underlies the dynamics of motion, which leads to pose estimates that are physically invalid. Motivated by this, we propose a novel control-based approach to model human motion with physics simulation and use imitation learning to learn a video-conditioned control policy for ego-pose estimation. Our imitation learning framework allows us to perform domain adaption to transfer our policy trained on simulation data to real-world data. Our experiments with real egocentric videos show that our method can estimate both accurate and physically plausible 3D ego-pose sequences without observing the cameras wearer’s body.
Tasks Domain Adaptation, Imitation Learning, Pose Estimation
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Ye_Yuan_3D_Ego-Pose_Estimation_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Ye_Yuan_3D_Ego-Pose_Estimation_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/3d-ego-pose-estimation-via-imitation-learning
Repo
Framework

Referring Image Segmentation via Recurrent Refinement Networks

Title Referring Image Segmentation via Recurrent Refinement Networks
Authors Ruiyu Li, Kaican Li, Yi-Chun Kuo, Michelle Shu, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia
Abstract We address the problem of image segmentation from natural language descriptions. Existing deep learning-based methods encode image representations based on the output of the last convolutional layer. One general issue is that the resulting image representation lacks multi-scale semantics, which are key components in advanced segmentation systems. In this paper, we utilize the feature pyramids inherently existing in convolutional neural networks to capture the semantics at different scales. To produce suitable information flow through the path of feature hierarchy, we propose Recurrent Refinement Network (RRN) that takes pyramidal features as input to refine the segmentation mask progressively. Experimental results on four available datasets show that our approach outperforms multiple baselines and state-of-the-art.
Tasks Semantic Segmentation
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Referring_Image_Segmentation_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Referring_Image_Segmentation_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/referring-image-segmentation-via-recurrent
Repo
Framework

Learning Diachronic Analogies to Analyze Concept Change

Title Learning Diachronic Analogies to Analyze Concept Change
Authors Matthias Orlikowski, Matthias Hartung, Philipp Cimiano
Abstract We propose to study the evolution of concepts by learning to complete diachronic analogies between lists of terms which relate to the same concept at different points in time. We present a number of models based on operations on word embedddings that correspond to different assumptions about the characteristics of diachronic analogies and change in concept vocabularies. These are tested in a quantitative evaluation for nine different concepts on a corpus of Dutch newspapers from the 1950s and 1980s. We show that a model which treats the concept terms as analogous and learns weights to compensate for diachronic changes (weighted linear combination) is able to more accurately predict the missing term than a learned transformation and two baselines for most of the evaluated concepts. We also find that all models tend to be coherent in relation to the represented concept, but less discriminative in regard to other concepts. Additionally, we evaluate the effect of aligning the time-specific embedding spaces using orthogonal Procrustes, finding varying effects on performance, depending on the model, concept and evaluation metric. For the weighted linear combination, however, results improve with alignment in a majority of cases. All related code is released publicly.
Tasks Word Embeddings
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4501/
PDF https://www.aclweb.org/anthology/W18-4501
PWC https://paperswithcode.com/paper/learning-diachronic-analogies-to-analyze
Repo
Framework

Multilingual Parallel Corpus for Global Communication Plan

Title Multilingual Parallel Corpus for Global Communication Plan
Authors Kenji Imamura, Eiichiro Sumita
Abstract
Tasks Domain Adaptation, Machine Translation, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1545/
PDF https://www.aclweb.org/anthology/L18-1545
PWC https://paperswithcode.com/paper/multilingual-parallel-corpus-for-global
Repo
Framework

SSN MLRG1 at SemEval-2018 Task 3: Irony Detection in English Tweets Using MultiLayer Perceptron

Title SSN MLRG1 at SemEval-2018 Task 3: Irony Detection in English Tweets Using MultiLayer Perceptron
Authors Rajalakshmi S, Angel Deborah S, S Milton Rajendram, Mirnalinee T T
Abstract Sentiment analysis plays an important role in E-commerce. Identifying ironic and sarcastic content in text plays a vital role in inferring the actual intention of the user, and is necessary to increase the accuracy of sentiment analysis. This paper describes the work on identifying the irony level in twitter texts. The system developed by the SSN MLRG1 team in SemEval-2018 for task 3 (irony detection) uses rule based approach for feature selection and MultiLayer Perceptron (MLP) technique to build the model for multiclass irony classification subtask, which classifies the given text into one of the four class labels.
Tasks Feature Selection, Opinion Mining, Sarcasm Detection, Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1103/
PDF https://www.aclweb.org/anthology/S18-1103
PWC https://paperswithcode.com/paper/ssn-mlrg1-at-semeval-2018-task-3-irony
Repo
Framework

Sentence Weighting for Neural Machine Translation Domain Adaptation

Title Sentence Weighting for Neural Machine Translation Domain Adaptation
Authors Shiqi Zhang, Deyi Xiong
Abstract In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation. We introduce a domain similarity metric to evaluate the relevance between a sentence and an available entire domain dataset. The similarity of each sentence to the target domain is calculated with various methods. The computed similarity is then integrated into the training objective to weight sentences. The adaptation results on both IWSLT Chinese-English TED task and a task with only synthetic training parallel data show that our sentence weighting method is able to achieve an significant improvement over strong baselines.
Tasks Domain Adaptation, Language Modelling, Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1269/
PDF https://www.aclweb.org/anthology/C18-1269
PWC https://paperswithcode.com/paper/sentence-weighting-for-neural-machine
Repo
Framework

SHADE: SHAnnon DEcay Information-Based Regularization for Deep Learning

Title SHADE: SHAnnon DEcay Information-Based Regularization for Deep Learning
Authors Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord
Abstract Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. We explain why this quantity makes our model able to achieve invariance with respect to input variations. We empirically validate the efficiency of our approach to improve classification performances compared to standard regularization schemes on several standard architectures.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=SJSVuReCZ
PDF https://openreview.net/pdf?id=SJSVuReCZ
PWC https://paperswithcode.com/paper/shade-shannon-decay-information-based
Repo
Framework

Generative Bridging Network for Neural Sequence Prediction

Title Generative Bridging Network for Neural Sequence Prediction
Authors Wenhu Chen, Guanlin Li, Shuo Ren, Shujie Liu, Zhirui Zhang, Mu Li, Ming Zhou
Abstract In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional likelihood, the bridge extends the point-wise ground truth to a bridge distribution conditioned on it, and the generator is optimized to minimize their KL-divergence. Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN, are proposed to penalize confidence, enhance language smoothness and relieve learning burden. Experiments conducted on two recognized sequence prediction tasks (machine translation and abstractive text summarization) show that our proposed GBNs can yield significant improvements over strong baselines. Furthermore, by analyzing samples drawn from different bridges, expected influences on the generator are verified.
Tasks Abstractive Text Summarization, Image Captioning, Language Modelling, Machine Translation, Speech Recognition, Spelling Correction, Text Summarization
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1154/
PDF https://www.aclweb.org/anthology/N18-1154
PWC https://paperswithcode.com/paper/generative-bridging-network-for-neural
Repo
Framework

Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation

Title Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
Authors Zhenyu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang
Abstract In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks. TRL can recursively refine the results of both tasks through serialized task-level interactions. In order to mutually-boost for each other, we encapsulate the interaction into a specific Task-Attentional Module (TAM) to adaptively enhance some counterpart patterns of both tasks. Further, to make the inference more credible, we propagate previous learning experiences on both tasks into the next network evolution by explicitly concatenating previous responses. The sequence of task-level interactions are finally evolved along a coarse-to-fine scale space such that the required details may be reconstructed progressively. Extensive experiments on NYU-Depth v2 and SUN RGB-D datasets demonstrate that our method achieves state-of-the-art results for monocular depth estimation and semantic segmentation.
Tasks Depth Estimation, Monocular Depth Estimation, Semantic Segmentation
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Zhenyu_Zhang_Joint_Task-Recursive_Learning_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhenyu_Zhang_Joint_Task-Recursive_Learning_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/joint-task-recursive-learning-for-semantic
Repo
Framework

Improving domain-specific SMT for low-resourced languages using data from different domains

Title Improving domain-specific SMT for low-resourced languages using data from different domains
Authors Fathima Farhath, Pranavan Theivendiram, Surangika Ranathunga, Sanath Jayasena, Gihan Dias
Abstract
Tasks Domain Adaptation, Language Modelling, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1598/
PDF https://www.aclweb.org/anthology/L18-1598
PWC https://paperswithcode.com/paper/improving-domain-specific-smt-for-low
Repo
Framework

Proceedings of the Fourth International Workshop on Computational Linguistics of Uralic Languages

Title Proceedings of the Fourth International Workshop on Computational Linguistics of Uralic Languages
Authors
Abstract
Tasks
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0200/
PDF https://www.aclweb.org/anthology/W18-0200
PWC https://paperswithcode.com/paper/proceedings-of-the-fourth-international
Repo
Framework

Statistical Analysis of Missing Translation in Simultaneous Interpretation Using A Large-scale Bilingual Speech Corpus

Title Statistical Analysis of Missing Translation in Simultaneous Interpretation Using A Large-scale Bilingual Speech Corpus
Authors Zhongxi Cai, Koichiro Ryu, Shigeki Matsubara
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1676/
PDF https://www.aclweb.org/anthology/L18-1676
PWC https://paperswithcode.com/paper/statistical-analysis-of-missing-translation
Repo
Framework

A Diachronic Corpus for Literary Style Analysis

Title A Diachronic Corpus for Literary Style Analysis
Authors Carmen Klaussner, Carl Vogel
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1552/
PDF https://www.aclweb.org/anthology/L18-1552
PWC https://paperswithcode.com/paper/a-diachronic-corpus-for-literary-style
Repo
Framework
Title RCAA: Relational Context-Aware Agents for Person Search
Authors Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang, Alexander G. Hauptmann
Abstract We aim to search for a target person from a gallery of whole scene images for which the annotations of pedestrian bounding boxes are unavailable. Previous approaches to this problem have relied on a pedestrian proposal net, which may generate redundant proposals and increase the computational burden. In this paper, we address this problem by training relational context-aware agents which learn the actions to localize the target person from the gallery of whole scene images. We incorporate the relational spatial and temporal contexts into the framework. Specifically, we propose to use the target person as the query in the query-dependent relational network. The agent determines the best action to take at each time step by simultaneously considering the local visual information, the relational and temporal contexts, together with the target person. To validate the performance of our approach, we conduct extensive experiments on the large-scale Person Search benchmark dataset and achieve significant improvements over the compared approaches. It is also worth noting that the proposed model even performs better than traditional methods with perfect pedestrian detectors.
Tasks Person Search
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaojun_Chang_RCAA_Relational_Context-Aware_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaojun_Chang_RCAA_Relational_Context-Aware_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/rcaa-relational-context-aware-agents-for
Repo
Framework

Statistical Tomography of Microscopic Life

Title Statistical Tomography of Microscopic Life
Authors Aviad Levis, Yoav Y. Schechner, Ronen Talmon
Abstract We achieve tomography of 3D volumetric natural objects, where each projected 2D image corresponds to a different specimen. Each specimen has unknown random 3D orientation, location, and scale. This imaging scenario is relevant to microscopic and mesoscopic organisms, aerosols and hydrosols viewed naturally by a microscope. In-class scale variation inhibits prior single-particle reconstruction methods. We thus generalize tomographic recovery to account for all degrees of freedom of a similarity transformation. This enables geometric self-calibration in imaging of transparent objects. We make the computational load manageable and reach good quality reconstruction in a short time. This enables extraction of statistics that are important for a scientific study of specimen populations, specifically size distribution parameters. We apply the method to study of plankton.
Tasks Calibration
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Levis_Statistical_Tomography_of_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Levis_Statistical_Tomography_of_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/statistical-tomography-of-microscopic-life
Repo
Framework
comments powered by Disqus