Paper Group NANR 154
Proceedings of the 13th International Conference on Computational Semantics - Long Papers. Pluto: A Deep Learning Based Watchdog for Anti Money Laundering. A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery. Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise. Segmented convolutional gated recurren …
Proceedings of the 13th International Conference on Computational Semantics - Long Papers
| Title | Proceedings of the 13th International Conference on Computational Semantics - Long Papers |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0400/ |
| https://www.aclweb.org/anthology/W19-0400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-international-4 |
| Repo | |
| Framework | |
Pluto: A Deep Learning Based Watchdog for Anti Money Laundering
| Title | Pluto: A Deep Learning Based Watchdog for Anti Money Laundering |
| Authors | Hao-Yuan Chen, Shang-Xuan Zou, Cheng-Lung Sung |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5515/ |
| https://www.aclweb.org/anthology/W19-5515 | |
| PWC | https://paperswithcode.com/paper/pluto-a-deep-learning-based-watchdog-for-anti |
| Repo | |
| Framework | |
A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery
| Title | A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery |
| Authors | Ali Mousavi, Gautam Dasarathy, Richard G. Baraniuk |
| Abstract | In this paper, we focus on two challenges which offset the promise of sparse signal representation, sensing, and recovery. First, real-world signals can seldom be described as perfectly sparse vectors in a known basis, and traditionally used random measurement schemes are seldom optimal for sensing them. Second, existing signal recovery algorithms are usually not fast enough to make them applicable to real-time problems. In this paper, we address these two challenges by presenting a novel framework based on deep learning. For the first challenge, we cast the problem of finding informative measurements by using a maximum likelihood (ML) formulation and show how we can build a data-driven dimensionality reduction protocol for sensing signals using convolutional architectures. For the second challenge, we discuss and analyze a novel parallelization scheme and show it significantly speeds-up the signal recovery process. We demonstrate the significant improvement our method obtains over competing methods through a series of experiments. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1xVTjCqKQ |
| https://openreview.net/pdf?id=B1xVTjCqKQ | |
| PWC | https://paperswithcode.com/paper/a-data-driven-and-distributed-approach-to |
| Repo | |
| Framework | |
Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise
| Title | Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise |
| Authors | Wei Wang, Xin Chen, Cheng Yang, Xiang Li, Xuemei Hu, Tao Yue |
| Abstract | Enhancing low light videos, which consists of denoising and brightness adjustment, is an intriguing but knotty problem. Under low light condition, due to high sensitivity camera setting, commonly negligible noises become obvious and severely deteriorate the captured videos. To recover high quality videos, a mass of image/video denoising/enhancing algorithms are proposed, most of which follow a set of simple assumptions about the statistic characters of camera noise, e.g., independent and identically distributed(i.i.d.), white, additive, Gaussian, Poisson or mixture noises. However, the practical noise under high sensitivity setting in real captured videos is complex and inaccurate to model with these assumptions. In this paper, we explore the physical origins of the practical high sensitivity noise in digital cameras, model them mathematically, and propose to enhance the low light videos based on the noise model by using an LSTM-based neural network. Specifically, we generate the training data with the proposed noise model and train the network with the dark noisy video as input and clear-bright video as output. Extensive comparisons on both synthetic and real captured low light videos with the state-of-the-art methods are conducted to demonstrate the effectiveness of the proposed method. |
| Tasks | Denoising, Video Denoising |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Enhancing_Low_Light_Videos_by_Exploring_High_Sensitivity_Camera_Noise_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Enhancing_Low_Light_Videos_by_Exploring_High_Sensitivity_Camera_Noise_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-low-light-videos-by-exploring-high |
| Repo | |
| Framework | |
Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar
| Title | Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar |
| Authors | Hao Du, Tian Jin, Yuan He, Yongping Song, Yongpeng Dai |
| Abstract | The automatic detection and recognition of human activities are valuable for physical security, gaming, and intelligent interface. Compared to an optical recognition system, radar is more robust to variations in lighting conditions and occlusions. The centimeter-wave ultra-wideband radar can even track human motion when the target is fully occluded from it. In this work, we propose a neural network architecture, namely segmented convolutional gated recurrent neural network (SCGRNN), to recognize human activities based on micro-Doppler spectrograms measured by the ultra-wideband radar. Unlike most existing approaches which treat the micro-Doppler spectrograms the same way as natural images, we extract segmented features of spectrograms via convolution operation and encode the feature maps along the time axis with gated recurrent units. Taking advantage of regularities in both the time and Doppler frequency domains in this way, our model can detect activities with arbitrary lengths. The experiments show that our method outperforms existing models in fine temporal resolution, noise robustness, and generalization performance. The radar system can thus recognize human behavior when visible light is blocked by opaque objects. Keywords: Micro-Doppler spectrograms, Human activity recognition, Deep learning, Convolutional neural network, Recurrent neural network |
| Tasks | Activity Recognition, Human Activity Recognition, RF-based Action Recognition, RF-based Pose Estimation |
| Published | 2019-04-27 |
| URL | https://doi.org/10.1016/j.neucom.2018.11.109 |
| https://sci-hub.se/10.1016/j.neucom.2018.11.109 | |
| PWC | https://paperswithcode.com/paper/segmented-convolutional-gated-recurrent |
| Repo | |
| Framework | |
Literary Event Detection
| Title | Literary Event Detection |
| Authors | Matthew Sims, Jong Ho Park, David Bamman |
| Abstract | In this work we present a new dataset of literary events{—}events that are depicted as taking place within the imagined space of a novel. While previous work has focused on event detection in the domain of contemporary news, literature poses a number of complications for existing systems, including complex narration, the depiction of a broad array of mental states, and a strong emphasis on figurative language. We outline the annotation decisions of this new dataset and compare several models for predicting events; the best performing model, a bidirectional LSTM with BERT token representations, achieves an F1 score of 73.9. We then apply this model to a corpus of novels split across two dimensions{—}prestige and popularity{—}and demonstrate that there are statistically significant differences in the distribution of events for prestige. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1353/ |
| https://www.aclweb.org/anthology/P19-1353 | |
| PWC | https://paperswithcode.com/paper/literary-event-detection |
| Repo | |
| Framework | |
Some classes of sets of structures definable without quantifiers
| Title | Some classes of sets of structures definable without quantifiers |
| Authors | James Rogers, Dakotah Lambert |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5706/ |
| https://www.aclweb.org/anthology/W19-5706 | |
| PWC | https://paperswithcode.com/paper/some-classes-of-sets-of-structures-definable |
| Repo | |
| Framework | |
Interpretable Continual Learning
| Title | Interpretable Continual Learning |
| Authors | Tameem Adel, Cuong V. Nguyen, Richard E. Turner, Zoubin Ghahramani, Adrian Weller |
| Abstract | We present a framework for interpretable continual learning (ICL). We show that explanations of previously performed tasks can be used to improve performance on future tasks. ICL generates a good explanation of a finished task, then uses this to focus attention on what is important when facing a new task. The ICL idea is general and may be applied to many continual learning approaches. Here we focus on the variational continual learning framework to take advantage of its flexibility and efficacy in overcoming catastrophic forgetting. We use saliency maps to provide explanations of performed tasks and propose a new metric to assess their quality. Experiments show that ICL achieves state-of-the-art results in terms of overall continual learning performance as measured by average classification accuracy, and also in terms of its explanations, which are assessed qualitatively and quantitatively using the proposed metric. |
| Tasks | Continual Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1g9N2A5FX |
| https://openreview.net/pdf?id=S1g9N2A5FX | |
| PWC | https://paperswithcode.com/paper/interpretable-continual-learning |
| Repo | |
| Framework | |
Generating Text from Anonymised Structures
| Title | Generating Text from Anonymised Structures |
| Authors | Emilie Colin, Claire Gardent |
| Abstract | Surface realisation (SR) consists in generating a text from a meaning representations (MR). In this paper, we introduce a new parallel dataset of deep meaning representations (MR) and French sentences and we present a novel method for MR-to-text generation which seeks to generalise by abstracting away from lexical content. Most current work on natural language generation focuses on generating text that matches a reference using BLEU as evaluation criteria. In this paper, we additionally consider the model{'}s ability to reintroduce the function words that are absent from the deep input meaning representations. We show that our approach increases both BLEU score and the scores used to assess function words generation. |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8614/ |
| https://www.aclweb.org/anthology/W19-8614 | |
| PWC | https://paperswithcode.com/paper/generating-text-from-anonymised-structures |
| Repo | |
| Framework | |
Automatic Alignment and Annotation Projection for Literary Texts
| Title | Automatic Alignment and Annotation Projection for Literary Texts |
| Authors | Uli Steinbach, Ines Rehbein |
| Abstract | This paper presents a modular NLP pipeline for the creation of a parallel literature corpus, followed by annotation transfer from the source to the target language. The test case we use to evaluate our pipeline is the automatic transfer of quote and speaker mention annotations from English to German. We evaluate the different components of the pipeline and discuss challenges specific to literary texts. Our experiments show that after applying a reasonable amount of semi-automatic postprocessing we can obtain high-quality aligned and annotated resources for a new language. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2505/ |
| https://www.aclweb.org/anthology/W19-2505 | |
| PWC | https://paperswithcode.com/paper/automatic-alignment-and-annotation-projection |
| Repo | |
| Framework | |
Strand-Accurate Multi-View Hair Capture
| Title | Strand-Accurate Multi-View Hair Capture |
| Authors | Giljoo Nam, Chenglei Wu, Min H. Kim, Yaser Sheikh |
| Abstract | Hair is one of the most challenging objects to reconstruct due to its micro-scale structure and a large number of repeated strands with heavy occlusions. In this paper, we present the first method to capture high-fidelity hair geometry with strand-level accuracy. Our method takes three stages to achieve this. In the first stage, a new multi-view stereo method with a slanted support line is proposed to solve the hair correspondences between different views. In detail, we contribute a novel cost function consisting of both photo-consistency term and geometric term that reconstructs each hair pixel as a 3D line. By merging all the depth maps, a point cloud, as well as local line directions for each point, is obtained. Thus, in the second stage, we feature a novel strand reconstruction method with the mean-shift to convert the noisy point data to a set of strands. Lastly, we grow the hair strands with multi-view geometric constraints to elongate the short strands and recover the missing strands, thus significantly increasing the reconstruction completeness. We evaluate our method on both synthetic data and real captured data, showing that our method can reconstruct hair strands with sub-millimeter accuracy. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Nam_Strand-Accurate_Multi-View_Hair_Capture_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Nam_Strand-Accurate_Multi-View_Hair_Capture_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/strand-accurate-multi-view-hair-capture |
| Repo | |
| Framework | |
Self-Adaptive Scaling for Learnable Residual Structure
| Title | Self-Adaptive Scaling for Learnable Residual Structure |
| Authors | Fenglin Liu, Meng Gao, Yuanxin Liu, Kai Lei |
| Abstract | Residual has been widely applied to build deep neural networks with enhanced feature propagation and improved accuracy. In the literature, multiple variants of residual structure are proposed. However, most of them are manually designed for particular tasks and datasets and the combination of existing residual structures has not been well studied. In this work, we propose the Self-Adaptive Scaling (SAS) approach that automatically learns the design of residual structure from data. The proposed approach makes the best of various residual structures, resulting in a general architecture covering several existing ones. In this manner, we construct a learnable residual structure which can be easily integrated into a wide range of residual-based models. We evaluate our approach on various tasks concerning different modalities, including machine translation (IWSLT-2015 EN-VI and WMT-2014 EN-DE, EN-FR), image classification (CIFAR-10 and CIFAR-100), and image captioning (MSCOCO). Empirical results show that the proposed approach consistently improves the residual-based models and exhibits desirable generalization ability. In particular, by incorporating the proposed approach to the Transformer model, we establish new state-of-the-arts on the IWSLT-2015 EN-VI low-resource machine translation dataset. |
| Tasks | Image Captioning, Image Classification, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1080/ |
| https://www.aclweb.org/anthology/K19-1080 | |
| PWC | https://paperswithcode.com/paper/self-adaptive-scaling-for-learnable-residual |
| Repo | |
| Framework | |
Micro-Baseline Structured Light
| Title | Micro-Baseline Structured Light |
| Authors | Vishwanath Saragadam, Jian Wang, Mohit Gupta, Shree Nayar |
| Abstract | We propose Micro-baseline Structured Light (MSL), a novel 3D imaging approach designed for small form-factor devices such as cell-phones and miniature robots. MSL operates with small projector-camera baseline and low-cost projection hardware, and can recover scene depths with computationally lightweight algorithms. The main observation is that a small baseline leads to small disparities, enabling a first-order approximation of the non-linear SL image formation model. This leads to the key theoretical result of the paper: the MSL equation, a linearized version of SL image formation. MSL equation is under-constrained due to two unknowns (depth and albedo) at each pixel, but can be efficiently solved using a local least squares approach. We analyze the performance of MSL in terms of various system parameters such as projected pattern and baseline, and provide guidelines for optimizing performance. Armed with these insights, we build a prototype to experimentally examine the theory and its practicality. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Saragadam_Micro-Baseline_Structured_Light_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Saragadam_Micro-Baseline_Structured_Light_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/micro-baseline-structured-light |
| Repo | |
| Framework | |
The limits of Spanglish?
| Title | The limits of Spanglish? |
| Authors | Barbara Bullock, Wally Guzm{'a}n, Almeida Jacqueline Toribio |
| Abstract | Linguistic code-switching (C-S) is common in oral bilingual vernacular speech. When used in literature, C-S becomes an artistic choice that can mirror the patterns of bilingual interactions. But it can also potentially exceed them. What are the limits of C-S? We model features of C-S in corpora of contemporary U.S. Spanish-English literary and conversational data to analyze why some critics view the {`}Spanglish{'} texts of Ilan Stavans as deviating from a C-S norm. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2515/ |
| https://www.aclweb.org/anthology/W19-2515 | |
| PWC | https://paperswithcode.com/paper/the-limits-of-spanglish |
| Repo | |
| Framework | |
CONTROLLING COVARIATE SHIFT USING EQUILIBRIUM NORMALIZATION OF WEIGHTS
| Title | CONTROLLING COVARIATE SHIFT USING EQUILIBRIUM NORMALIZATION OF WEIGHTS |
| Authors | Aaron Defazio |
| Abstract | We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative weights to the layer output in equilibrium. We validate our method on a set of standard benchmarks including CIFAR-10/100, SVHN and ILSVRC 2012 ImageNet. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryGDEjCcK7 |
| https://openreview.net/pdf?id=ryGDEjCcK7 | |
| PWC | https://paperswithcode.com/paper/controlling-covariate-shift-using-equilibrium-1 |
| Repo | |
| Framework | |
