January 25, 2020

2433 words 12 mins read

Paper Group NANR 53

Incorporating Emoji Descriptions Improves Tweet Classification. Learning Joint Gait Representation via Quintuplet Loss Minimization. Stochastic Class-Based Hard Example Mining for Deep Metric Learning. Word order variation in Mby'a Guaran'\i. Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Ir …

Incorporating Emoji Descriptions Improves Tweet Classification


Title	Incorporating Emoji Descriptions Improves Tweet Classification
Authors	Abhishek Singh, Eduardo Blanco, Wei Jin
Abstract	Tweets are short messages that often include specialized language such as hashtags and emojis. In this paper, we present a simple strategy to process emojis: replace them with their natural language description and use pretrained word embeddings as normally done with standard words. We show that this strategy is more effective than using pretrained emoji embeddings for tweet classification. Specifically, we obtain new state-of-the-art results in irony detection and sentiment analysis despite our neural network is simpler than previous proposals.
Tasks	Sentiment Analysis, Word Embeddings
Published	2019-06-01
URL	https://www.aclweb.org/anthology/N19-1214/
PDF	https://www.aclweb.org/anthology/N19-1214
PWC	https://paperswithcode.com/paper/incorporating-emoji-descriptions-improves
Repo
Framework

Learning Joint Gait Representation via Quintuplet Loss Minimization


Title	Learning Joint Gait Representation via Quintuplet Loss Minimization
Authors	Kaihao Zhang, Wenhan Luo, Lin Ma, Wei Liu, Hongdong Li
Abstract	Gait recognition is an important biometric method popularly used in video surveillance, where the task is to identify people at a distance by their walking patterns from video sequences. Most of the current successful approaches for gait recognition either use a pair of gait images to form a cross-gait representation or rely on a single gait image for unique-gait representation. These two types of representations emperically complement one another. In this paper, we propose a new Joint Unique-gait and Cross-gait Network (JUCNet), to combine the advantages of unique-gait representation with that of cross-gait representation, leading to an significantly improved performance. Another key contribution of this paper is a novel quintuplet loss function, which simultaneously increases the inter-class differences by pushing representations extracted from different subjects apart and decreases the intra-class variations by pulling representations extracted from the same subject together. Experiments show that our method achieves the state-of-the-art performance tested on standard benchmark datasets, demonstrating its superiority over existing methods.
Tasks	Gait Recognition
Published	2019-06-01
URL	http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Learning_Joint_Gait_Representation_via_Quintuplet_Loss_Minimization_CVPR_2019_paper.html
PDF	http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Learning_Joint_Gait_Representation_via_Quintuplet_Loss_Minimization_CVPR_2019_paper.pdf
PWC	https://paperswithcode.com/paper/learning-joint-gait-representation-via
Repo
Framework

Stochastic Class-Based Hard Example Mining for Deep Metric Learning


Title	Stochastic Class-Based Hard Example Mining for Deep Metric Learning
Authors	Yumin Suh, Bohyung Han, Wonsik Kim, Kyoung Mu Lee
Abstract	Performance of deep metric learning depends heavily on the capability of mining hard negative examples during training. However, many metric learning algorithms often require intractable computational cost due to frequent feature computations and nearest neighbor searches in a large-scale dataset. As a result, existing approaches often suffer from trade-off between training speed and prediction accuracy. To alleviate this limitation, we propose a stochastic hard negative mining method. Our key idea is to adopt class signatures that keep track of feature embedding online with minor additional cost during training, and identify hard negative example candidates using the signatures. Given an anchor instance, our algorithm first selects a few hard negative classes based on the class-to-sample distances and then performs a refined search in an instance-level only from the selected classes. As most of the classes are discarded at the first step, it is much more efficient than exhaustive search while effectively mining a large number of hard examples. Our experiment shows that the proposed technique improves image retrieval accuracy substantially; it achieves the state-of-the-art performance on the several standard benchmark datasets.
Tasks	Image Retrieval, Metric Learning
Published	2019-06-01
URL	http://openaccess.thecvf.com/content_CVPR_2019/html/Suh_Stochastic_Class-Based_Hard_Example_Mining_for_Deep_Metric_Learning_CVPR_2019_paper.html
PDF	http://openaccess.thecvf.com/content_CVPR_2019/papers/Suh_Stochastic_Class-Based_Hard_Example_Mining_for_Deep_Metric_Learning_CVPR_2019_paper.pdf
PWC	https://paperswithcode.com/paper/stochastic-class-based-hard-example-mining
Repo
Framework

Word order variation in Mby'a Guaran'\i


Title	Word order variation in Mby'a Guaran'\i
Authors	Angelika Kiss, Guillaume Thomas
Abstract
Tasks
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-7714/
PDF	https://www.aclweb.org/anthology/W19-7714
PWC	https://paperswithcode.com/paper/word-order-variation-in-mbya-guarani
Repo
Framework

Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan


Title	Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan
Authors	Faisal Alshargi, Shahd Dibas, Sakhar Alkhereyf, Reem Faraj, Basmah Abdulkareem, Sane Yagi, Ouafaa Kacha, Nizar Habash, Owen Rambow
Abstract	We present a collection of morphologically annotated corpora for seven Arabic dialects: Taizi Yemeni, Sanaani Yemeni, Najdi, Jordanian, Syrian, Iraqi and Moroccan Arabic. The corpora collectively cover over 200,000 words, and are all manually annotated in a common set of standards for orthography, diacritized lemmas, tokenization, morphological units and English glosses. These corpora will be publicly available to serve as benchmarks for training and evaluating systems for Arabic dialect morphological analysis and disambiguation.
Tasks	Morphological Analysis, Tokenization
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-4615/
PDF	https://www.aclweb.org/anthology/W19-4615
PWC	https://paperswithcode.com/paper/morphologically-annotated-corpora-for-seven
Repo
Framework

Turn a Silicon Camera Into an InGaAs Camera


Title	Turn a Silicon Camera Into an InGaAs Camera
Authors	Feifan Lv, Yinqiang Zheng, Bohan Zhang, Feng Lu
Abstract	Short-wave infrared (SWIR) imaging has a wide range of applications for both industry and civilian. However, the InGaAs sensors commonly used for SWIR imaging suffer from a variety of drawbacks, including high price, low resolution, unstable quality, and so on. In this paper, we propose a novel solution for SWIR imaging using a common Silicon sensor, which has cheaper price, higher resolution and better technical maturity compared with the specialized InGaAs sensor. Our key idea is to approximate the response of the InGaAs sensor by exploiting the largely ignored sensitivity of a Silicon sensor, weak as it is, in the SWIR range. To this end, we build a multi-channel optical system to collect a new SWIR dataset and present a physically meaningful three-stage image processing algorithm on the basis of CNN. Both qualitative and quantitative experiments show promising experimental results, which demonstrate the effectiveness of the proposed method.
Tasks
Published	2019-06-01
URL	http://openaccess.thecvf.com/content_CVPR_2019/html/Lv_Turn_a_Silicon_Camera_Into_an_InGaAs_Camera_CVPR_2019_paper.html
PDF	http://openaccess.thecvf.com/content_CVPR_2019/papers/Lv_Turn_a_Silicon_Camera_Into_an_InGaAs_Camera_CVPR_2019_paper.pdf
PWC	https://paperswithcode.com/paper/turn-a-silicon-camera-into-an-ingaas-camera
Repo
Framework

Semantic Stereo Matching With Pyramid Cost Volumes


Title	Semantic Stereo Matching With Pyramid Cost Volumes
Authors	Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju
Abstract	The accuracy of stereo matching has been greatly improved by using deep learning with convolutional neural networks. To further capture the details of disparity maps, in this paper, we propose a novel semantic stereo network named SSPCV-Net, which includes newly designed pyramid cost volumes for describing semantic and spatial information on multiple levels. The semantic features are inferred by a semantic segmentation subnetwork while the spatial features are derived by hierarchical spatial pooling. In the end, we design a 3D multi-cost aggregation module to integrate the extracted multilevel features and perform regression for accurate disparity maps. We conduct comprehensive experiments and comparisons with some recent stereo matching networks on Scene Flow, KITTI 2015 and 2012, and Cityscapes benchmark datasets, and the results show that the proposed SSPCV-Net significantly promotes the state-of-the-art stereo-matching performance.
Tasks	Semantic Segmentation, Stereo Matching
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Semantic_Stereo_Matching_With_Pyramid_Cost_Volumes_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Semantic_Stereo_Matching_With_Pyramid_Cost_Volumes_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/semantic-stereo-matching-with-pyramid-cost
Repo
Framework

First-order methods almost always avoid saddle points: The case of vanishing step-sizes


Title	First-order methods almost always avoid saddle points: The case of vanishing step-sizes
Authors	Ioannis Panageas, Georgios Piliouras, Xiao Wang
Abstract	In a series of papers [Lee et al 2016], [Panageas and Piliouras 2017], [Lee et al 2019], it was established that some of the most commonly used first order methods almost surely (under random initializations) and with step-size being small enough, avoid strict saddle points, as long as the objective function $f$ is $C^2$ and has Lipschitz gradient. The key observation was that first order methods can be studied from a dynamical systems perspective, in which instantiations of Center-Stable manifold theorem allow for a global analysis. The results of the aforementioned papers were limited to the case where the step-size $\alpha$ is constant, i.e., does not depend on time (and typically bounded from the inverse of the Lipschitz constant of the gradient of $f$). It remains an open question whether or not the results still hold when the step-size is time dependent and vanishes with time. In this paper, we resolve this question on the affirmative for gradient descent, mirror descent, manifold descent and proximal point. The main technical challenge is that the induced (from each first order method) dynamical system is time non-homogeneous and the stable manifold theorem is not applicable in its classic form. By exploiting the dynamical systems structure of the aforementioned first order methods, we are able to prove a stable manifold theorem that is applicable to time non-homogeneous dynamical systems and generalize the results in [Lee et al 2019] for time dependent step-sizes.
Tasks
Published	2019-12-01
URL	http://papers.nips.cc/paper/8875-first-order-methods-almost-always-avoid-saddle-points-the-case-of-vanishing-step-sizes
PDF	http://papers.nips.cc/paper/8875-first-order-methods-almost-always-avoid-saddle-points-the-case-of-vanishing-step-sizes.pdf
PWC	https://paperswithcode.com/paper/first-order-methods-almost-always-avoid-1
Repo
Framework

RDoC Task at BioNLP-OST 2019


Title	RDoC Task at BioNLP-OST 2019
Authors	Mohammad Anani, Nazmul Kazi, Matthew Kuntz, Kah, Indika a
Abstract	BioNLP Open Shared Tasks (BioNLP-OST) is an international competition organized to facilitate development and sharing of computational tasks of biomedical text mining and solutions to them. For BioNLP-OST 2019, we introduced a new mental health informatics task called {``}RDoC Task{''}, which is composed of two subtasks: information retrieval and sentence extraction through National Institutes of Mental Health{'}s Research Domain Criteria framework. Five and four teams around the world participated in the two tasks, respectively. According to the performance on the two tasks, we observe that there is room for improvement for text mining on brain research and mental illness. \|
Tasks	Information Retrieval
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-5729/
PDF	https://www.aclweb.org/anthology/D19-5729
PWC	https://paperswithcode.com/paper/rdoc-task-at-bionlp-ost-2019
Repo
Framework

Predicting Word Concreteness and Imagery


Title	Predicting Word Concreteness and Imagery
Authors	Jean Charbonnier, Christian Wartena
Abstract	Concreteness of words has been studied extensively in psycholinguistic literature. A number of datasets have been created with average values for perceived concreteness of words. We show that we can train a regression model on these data, using word embeddings and morphological features, that can predict these concreteness values with high accuracy. We evaluate the model on 7 publicly available datasets. Only for a few small subsets of these datasets prediction of concreteness values are found in the literature. Our results clearly outperform the reported results for these datasets.
Tasks	Word Embeddings
Published	2019-05-01
URL	https://www.aclweb.org/anthology/W19-0415/
PDF	https://www.aclweb.org/anthology/W19-0415
PWC	https://paperswithcode.com/paper/predicting-word-concreteness-and-imagery
Repo
Framework

Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference


Title	Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference
Authors	Ahmadreza Mosallanezhad, Ghazaleh Beigi, Huan Liu
Abstract	User-generated textual data is rich in content and has been used in many user behavioral modeling tasks. However, it could also leak user private-attribute information that they may not want to disclose such as age and location. User{'}s privacy concerns mandate data publishers to protect privacy. One effective way is to anonymize the textual data. In this paper, we study the problem of textual data anonymization and propose a novel Reinforcement Learning-based Text Anonymizor, RLTA, which addresses the problem of private-attribute leakage while preserving the utility of textual data. Our approach first extracts a latent representation of the original text w.r.t. a given task, then leverages deep reinforcement learning to automatically learn an optimal strategy for manipulating text representations w.r.t. the received privacy and utility feedback. Experiments show the effectiveness of this approach in terms of preserving both privacy and utility.
Tasks
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-1240/
PDF	https://www.aclweb.org/anthology/D19-1240
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-based-text
Repo
Framework

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations


Title	Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations
Authors
Abstract
Tasks
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-3000/
PDF	https://www.aclweb.org/anthology/D19-3000
PWC	https://paperswithcode.com/paper/proceedings-of-the-2019-conference-on-1
Repo
Framework

Instance-Guided Context Rendering for Cross-Domain Person Re-Identification


Title	Instance-Guided Context Rendering for Cross-Domain Person Re-Identification
Authors	Yanbei Chen, Xiatian Zhu, Shaogang Gong
Abstract	Existing person re-identification (re-id) methods mostly assume the availability of large-scale identity labels for model learning in any target domain deployment. This greatly limits their scalability in practice. To tackle this limitation, we propose a novel Instance-Guided Context Rendering scheme, which transfers the source person identities into diverse target domain contexts to enable supervised re-id model learning in the unlabelled target domain. Unlike previous image synthesis methods that transform the source person images into limited fixed target styles, our approach produces more visually plausible, and diverse synthetic training data. Specifically, we formulate a dual conditional generative adversarial network that augments each source person image with rich contextual variations. To explicitly achieve diverse rendering effects, we leverage abundant unlabelled target instances as contextual guidance for image generation. Extensive experiments on Market-1501, DukeMTMC-reID and CUHK03 benchmarks show that the re-id performance can be significantly improved when using our synthetic data in cross-domain re-id model learning.
Tasks	Image Generation, Person Re-Identification
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Instance-Guided_Context_Rendering_for_Cross-Domain_Person_Re-Identification_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Instance-Guided_Context_Rendering_for_Cross-Domain_Person_Re-Identification_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/instance-guided-context-rendering-for-cross
Repo
Framework

Manifold Alignment via Feature Correspondence


Title	Manifold Alignment via Feature Correspondence
Authors	Jay S. Stanley III, Guy Wolf, Smita Krishnaswamy
Abstract	We propose a novel framework for combining datasets via alignment of their associated intrinsic dimensions. Our approach assumes that the two datasets are sampled from a common latent space, i.e., they measure equivalent systems. Thus, we expect there to exist a natural (albeit unknown) alignment of the data manifolds associated with the intrinsic geometry of these datasets, which are perturbed by measurement artifacts in the sampling process. Importantly, we do not assume any individual correspondence (partial or complete) between data points. Instead, we rely on our assumption that a subset of data features have correspondence across datasets. We leverage this assumption to estimate relations between intrinsic manifold dimensions, which are given by diffusion map coordinates over each of the datasets. We compute a correlation matrix between diffusion coordinates of the datasets by considering graph (or manifold) Fourier coefficients of corresponding data features. We then orthogonalize this correlation matrix to form an isometric transformation between the diffusion maps of the datasets. Finally, we apply this transformation to the diffusion coordinates and construct a unified diffusion geometry of the datasets together. We show that this approach successfully corrects misalignment artifacts, and allows for integrated data.
Tasks
Published	2019-05-01
URL	https://openreview.net/forum?id=SkGNrnC9FQ
PDF	https://openreview.net/pdf?id=SkGNrnC9FQ
PWC	https://paperswithcode.com/paper/manifold-alignment-via-feature-correspondence
Repo
Framework

Variational Few-Shot Learning


Title	Variational Few-Shot Learning
Authors	Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang
Abstract	We propose a variational Bayesian framework for enhancing few-shot learning performance. This idea is motivated by the fact that single point based metric learning approaches are inherently noise-vulnerable and easy-to-be-biased. In a nutshell, stochastic variational inference is invoked to approximate bias-eliminated class specific sample distributions. In the meantime, a classifier-free prediction is attained by leveraging the distribution statistics on novel samples. Extensive experimental results on several benchmarks well demonstrate the effectiveness of our distribution-driven few-shot learning framework over previous point estimates based methods, in terms of superior classification accuracy and robustness.
Tasks	Few-Shot Learning, Metric Learning
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Variational_Few-Shot_Learning_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Variational_Few-Shot_Learning_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/variational-few-shot-learning
Repo
Framework