Paper Group NANR 180
Privacy-Aware Text Rewriting. Learning Image and Video Compression Through Spatial-Temporal Energy Compaction. How to Parse Low-Resource Languages: Cross-Lingual Parsing, Target Language Annotation, or Both?. Dependency Parser for Bengali-English Code-Mixed Data enhanced with a Synthetic Treebank. A Surface-Syntactic UD Treebank for Naija. Weakly S …
Privacy-Aware Text Rewriting
| Title | Privacy-Aware Text Rewriting |
| Authors | Qiongkai Xu, Lizhen Qu, Chenchen Xu, Ran Cui |
| Abstract | Biased decisions made by automatic systems have led to growing concerns in research communities. Recent work from the NLP community focuses on building systems that make fair decisions based on text. Instead of relying on unknown decision systems or human decision-makers, we argue that a better way to protect data providers is to remove the trails of sensitive information before publishing the data. In light of this, we propose a new privacy-aware text rewriting task and explore two privacy-aware back-translation methods for the task, based on adversarial training and approximate fairness risk. Our extensive experiments on three real-world datasets with varying demographical attributes show that our methods are effective in obfuscating sensitive attributes. We have also observed that the fairness risk method retains better semantics and fluency, while the adversarial training method tends to leak less sensitive information. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8633/ |
| https://www.aclweb.org/anthology/W19-8633 | |
| PWC | https://paperswithcode.com/paper/privacy-aware-text-rewriting |
| Repo | |
| Framework | |
Learning Image and Video Compression Through Spatial-Temporal Energy Compaction
| Title | Learning Image and Video Compression Through Spatial-Temporal Energy Compaction |
| Authors | Zhengxue Cheng, Heming Sun, Masaru Takeuchi, Jiro Katto |
| Abstract | Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning based image and video compression. Inspired from related works, in this paper, we present an image compression architecture using a convolutional autoencoder, and then generalize image compression to video compression, by adding an interpolation loop into both encoder and decoder sides. Our basic idea is to realize spatial-temporal energy compaction in learning image and video compression. Thereby, we propose to add a spatial energy compaction-based penalty into loss function, to achieve higher image compression performance. Furthermore, based on temporal energy distribution, we propose to select the number of frames in one interpolation loop, adapting to the motion characteristics of video contents. Experimental results demonstrate that our proposed image compression outperforms the latest image compression standard with MS-SSIM quality metric, and provides higher performance compared with state-of-the-art learning compression methods at high bit rates, which benefits from our spatial energy compaction approach. Meanwhile, our proposed video compression approach with temporal energy compaction can significantly outperform MPEG-4, and is competitive with commonly used H.264. Both our image and video compression can produce more visually pleasant results than traditional standards. |
| Tasks | Image Compression, Video Compression |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Cheng_Learning_Image_and_Video_Compression_Through_Spatial-Temporal_Energy_Compaction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Cheng_Learning_Image_and_Video_Compression_Through_Spatial-Temporal_Energy_Compaction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-image-and-video-compression-through |
| Repo | |
| Framework | |
How to Parse Low-Resource Languages: Cross-Lingual Parsing, Target Language Annotation, or Both?
| Title | How to Parse Low-Resource Languages: Cross-Lingual Parsing, Target Language Annotation, or Both? |
| Authors | Ailsa Meechan-Maddon, Joakim Nivre |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7713/ |
| https://www.aclweb.org/anthology/W19-7713 | |
| PWC | https://paperswithcode.com/paper/how-to-parse-low-resource-languages-cross |
| Repo | |
| Framework | |
Dependency Parser for Bengali-English Code-Mixed Data enhanced with a Synthetic Treebank
| Title | Dependency Parser for Bengali-English Code-Mixed Data enhanced with a Synthetic Treebank |
| Authors | Urmi Ghosh, Dipti Sharma, Simran Khanuja |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7810/ |
| https://www.aclweb.org/anthology/W19-7810 | |
| PWC | https://paperswithcode.com/paper/dependency-parser-for-bengali-english-code |
| Repo | |
| Framework | |
A Surface-Syntactic UD Treebank for Naija
| Title | A Surface-Syntactic UD Treebank for Naija |
| Authors | Bernard Caron, Marine Courtin, Kim Gerdes, Sylvain Kahane |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7803/ |
| https://www.aclweb.org/anthology/W19-7803 | |
| PWC | https://paperswithcode.com/paper/a-surface-syntactic-ud-treebank-for-naija |
| Repo | |
| Framework | |
Weakly Supervised Image Classification Through Noise Regularization
| Title | Weakly Supervised Image Classification Through Noise Regularization |
| Authors | Mengying Hu, Hu Han, Shiguang Shan, Xilin Chen |
| Abstract | Weakly supervised learning is an essential problem in computer vision tasks, such as image classification, object recognition, etc., because it is expected to work in the scenarios where a large dataset with clean labels is not available. While there are a number of studies on weakly supervised image classification, they usually limited to either single-label or multi-label scenarios. In this work, we propose an effective approach for weakly supervised image classification utilizing massive noisy labeled data with only a small set of clean labels (e.g., 5%). The proposed approach consists of a clean net and a residual net, which aim to learn a mapping from feature space to clean label space and a residual mapping from feature space to the residual between clean labels and noisy labels, respectively, in a multi-task learning manner. Thus, the residual net works as a regularization term to improve the clean net training. We evaluate the proposed approach on two multi-label datasets (OpenImage and MS COCO2014) and a single-label dataset (Clothing1M). Experimental results show that the proposed approach outperforms the state-of-the-art methods, and generalizes well to both single-label and multi-label scenarios. |
| Tasks | Image Classification, Multi-Task Learning, Object Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hu_Weakly_Supervised_Image_Classification_Through_Noise_Regularization_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hu_Weakly_Supervised_Image_Classification_Through_Noise_Regularization_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-image-classification |
| Repo | |
| Framework | |
ODE-Inspired Network Design for Single Image Super-Resolution
| Title | ODE-Inspired Network Design for Single Image Super-Resolution |
| Authors | Xiangyu He, Zitao Mo, Peisong Wang, Yang Liu, Mingyuan Yang, Jian Cheng |
| Abstract | Single image super-resolution, as a high dimensional structured prediction problem, aims to characterize fine-grain information given a low-resolution sample. Recent advances in convolutional neural networks are introduced into super-resolution and push forward progress in this field. Current studies have achieved impressive performance by manually designing deep residual neural networks but overly relies on practical experience. In this paper, we propose to adopt an ordinary differential equation (ODE)-inspired design scheme for single image super-resolution, which have brought us a new understanding of ResNet in classification problems. Not only is it interpretable for super-resolution but it provides a reliable guideline on network designs. By casting the numerical schemes in ODE as blueprints, we derive two types of network structures: LF-block and RK-block, which correspond to the Leapfrog method and Runge-Kutta method in numerical ordinary differential equations. We evaluate our models on benchmark datasets, and the results show that our methods surpass the state-of-the-arts while keeping comparable parameters and operations. |
| Tasks | Image Super-Resolution, Structured Prediction, Super-Resolution |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/He_ODE-Inspired_Network_Design_for_Single_Image_Super-Resolution_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/He_ODE-Inspired_Network_Design_for_Single_Image_Super-Resolution_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ode-inspired-network-design-for-single-image |
| Repo | |
| Framework | |
Regular transductions with MCFG input syntax
| Title | Regular transductions with MCFG input syntax |
| Authors | Mark-Jan Nederhof, Heiko Vogler |
| Abstract | We show that regular transductions for which the input part is generated by some multiple context-free grammar can be simulated by synchronous multiple context-free grammars. We prove that synchronous multiple context-free grammars are strictly more powerful than this combination of regular transductions and multiple context-free grammars. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3109/ |
| https://www.aclweb.org/anthology/W19-3109 | |
| PWC | https://paperswithcode.com/paper/regular-transductions-with-mcfg-input-syntax |
| Repo | |
| Framework | |
MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction
| Title | MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction |
| Authors | Hongwei Yi, Chen Li, Qiong Cao, Xiaoyong Shen, Sheng Li, Guoping Wang, Yu-Wing Tai |
| Abstract | We propose to address the face reconstruction in the wild by using a multi-metric regression network, MMFace, to align a 3D face morphable model (3DMM) to an input image. The key idea is to utilize a volumetric sub-network to estimate an intermediate geometry representation, and a parametric sub-network to regress the 3DMM parameters. Our parametric sub-network consists of identity loss, expression loss, and pose loss which greatly improves the aligned geometry details by incorporating high level loss functions directly defined in the 3DMM parametric spaces. Our high-quality reconstruction is robust under large variations of expressions, poses, illumination conditions, and even with large partial occlusions. We evaluate our method by comparing the performance with state-of-the-art approaches on latest 3D face dataset LS3D-W and Florence. We achieve significant improvements both quantitatively and qualitatively. Due to our high-quality reconstruction, our method can be easily extended to generate high-quality geometry sequences for video inputs. |
| Tasks | Face Reconstruction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yi_MMFace_A_Multi-Metric_Regression_Network_for_Unconstrained_Face_Reconstruction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yi_MMFace_A_Multi-Metric_Regression_Network_for_Unconstrained_Face_Reconstruction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mmface-a-multi-metric-regression-network-for |
| Repo | |
| Framework | |
A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization
| Title | A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization |
| Authors | Sulaiman Alghunaim, Kun Yuan, Ali H. Sayed |
| Abstract | Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based proximal decentralized methods are known to converge to the optimal solution with sublinear rates, and it remains unclear whether this family of methods can achieve global linear convergence. To tackle this problem, this work assumes the non-smooth regularization term is common across all networked agents, which is the case for many machine learning problems. Under this condition, we design a proximal gradient decentralized algorithm whose fixed point coincides with the desired minimizer. We then provide a concise proof that establishes its linear convergence. In the absence of the non-smooth term, our analysis technique covers the well known EXTRA algorithm and provides useful bounds on the convergence rate and step-size. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8551-a-linearly-convergent-proximal-gradient-algorithm-for-decentralized-optimization |
| http://papers.nips.cc/paper/8551-a-linearly-convergent-proximal-gradient-algorithm-for-decentralized-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/a-linearly-convergent-proximal-gradient |
| Repo | |
| Framework | |
Hyperspectral Image Super-Resolution With Optimized RGB Guidance
| Title | Hyperspectral Image Super-Resolution With Optimized RGB Guidance |
| Authors | Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang |
| Abstract | To overcome the limitations of existing hyperspectral cameras on spatial/temporal resolution, fusing a low resolution hyperspectral image (HSI) with a high resolution RGB (or multispectral) image into a high resolution HSI has been prevalent. Previous methods for this fusion task usually employ hand-crafted priors to model the underlying structure of the latent high resolution HSI, and the effect of the camera spectral response (CSR) of the RGB camera on super-resolution accuracy has rarely been investigated. In this paper, we first present a simple and efficient convolutional neural network (CNN) based method for HSI super-resolution in an unsupervised way, without any prior training. Later, we append a CSR optimization layer onto the HSI super-resolution network, either to automatically select the best CSR in a given CSR dataset, or to design the optimal CSR under some physical restrictions. Experimental results show our method outperforms the state-of-the-arts, and the CSR optimization can further boost the accuracy of HSI super-resolution. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Fu_Hyperspectral_Image_Super-Resolution_With_Optimized_RGB_Guidance_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Fu_Hyperspectral_Image_Super-Resolution_With_Optimized_RGB_Guidance_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-super-resolution-with |
| Repo | |
| Framework | |
FinDSE@FinTOC-2019 Shared Task
| Title | FinDSE@FinTOC-2019 Shared Task |
| Authors | Carla Abreu, Henrique Cardoso, Eug{'e}nio Oliveira |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6410/ |
| https://www.aclweb.org/anthology/W19-6410 | |
| PWC | https://paperswithcode.com/paper/findsefintoc-2019-shared-task |
| Repo | |
| Framework | |
Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint
| Title | Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint |
| Authors | Uday Kamal, Thamidul Islam Tonmoy, Sowmitra Das, and Md. Kamrul Hasan |
| Abstract | Traffic sign detection is a central part of autonomous vehicle technology. Recent advances in deep learning algorithms have motivated researchers to use neural networks to perform this task. In this paper, we look at traffic sign detection as an image segmentation problem and propose a deep convolutional neural network-based approach to solve it. To this end, we propose a new network, the SegU-Net, which we form by merging the state-of-the-art segmentation architectures–SegNet and U-Net to detect traffic signs from video sequences. For training the network, we use the Tversky loss function constrained by an L1 term instead of the intersection over union loss traditionally used to train segmentation networks. We use a separate network, inspired by the VGG-16 architecture, to classify the detected signs. The networks are trained on the challenge free sequences of the CURE TSD dataset. Our proposed network outperforms the state-of-the-art object detection networks, such as the Faster R-CNN inception Resnet V2 and R-FCN Resnet 101, by a large margin and obtains a precision and recall of 94.60% and 80.21%, respectively, which is the current state of the art on this part of the dataset. In addition, the network is tested on the German Traffic Sign Detection Benchmark (GTSDB) dataset, where it achieves a precision and recall of 95.29% and 89.01%, respectively. This is on a par with the performance of the aforementioned object detection networks. These results prove the generalizability of the proposed architecture and its suitability for robust traffic sign detection in autonomous vehicles. |
| Tasks | Autonomous Vehicles, Object Detection, Semantic Segmentation |
| Published | 2019-04-26 |
| URL | https://ieeexplore.ieee.org/document/8700606 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8700606 | |
| PWC | https://paperswithcode.com/paper/automatic-traffic-sign-detection-and |
| Repo | |
| Framework | |
Anglicized Words and Misspelled Cognates in Native Language Identification
| Title | Anglicized Words and Misspelled Cognates in Native Language Identification |
| Authors | Ilia Markov, Vivi Nastase, Carlo Strapparava |
| Abstract | In this paper, we present experiments that estimate the impact of specific lexical choices of people writing in a second language (L2). In particular, we look at misspelled words that indicate lexical uncertainty on the part of the author, and separate them into three categories: misspelled cognates, {``}L2-ed{''} (in our case, anglicized) words, and all other spelling errors. We test the assumption that such errors contain clues about the native language of an essay{'}s author through the task of native language identification. The results of the experiments show that the information brought by each of these categories is complementary. We also note that while the distribution of such features changes with the proficiency level of the writer, their contribution towards native language identification remains significant at all levels. | |
| Tasks | Language Identification, Native Language Identification |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4429/ |
| https://www.aclweb.org/anthology/W19-4429 | |
| PWC | https://paperswithcode.com/paper/anglicized-words-and-misspelled-cognates-in |
| Repo | |
| Framework | |
Dependency Length Minimization vs. Word Order Constraints: An Empirical Study On 55 Treebanks
| Title | Dependency Length Minimization vs. Word Order Constraints: An Empirical Study On 55 Treebanks |
| Authors | Xiang Yu, Agnieszka Falenska, Jonas Kuhn |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7911/ |
| https://www.aclweb.org/anthology/W19-7911 | |
| PWC | https://paperswithcode.com/paper/dependency-length-minimization-vs-word-order |
| Repo | |
| Framework | |
