Paper Group ANR 848
Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization. Loss Surface Modality of Feed-Forward Neural Network Architectures. Confirmatory Aspect-based Opinion Mining Processes. Non-Local ConvLSTM for Video Compression Artifact Reduction. Predicting Algorithm Classes for Programming Word Problems. …
Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization
| Title | Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization |
| Authors | Yingchi Liu, Quanzhi Li, Marika Cifor, Xiaozhong Liu, Qiong Zhang, Luo Si |
| Abstract | The number of personal stories about sexual harassment shared online has increased exponentially in recent years. This is in part inspired by the #MeToo and #TimesUp movements. Safecity is an online forum for people who experienced or witnessed sexual harassment to share their personal experiences. It has collected \textgreater 10,000 stories so far. Sexual harassment occurred in a variety of situations, and categorization of the stories and extraction of their key elements will provide great help for the related parties to understand and address sexual harassment. In this study, we manually annotated those stories with labels in the dimensions of location, time, and harassers’ characteristics, and marked the key elements related to these dimensions. Furthermore, we applied natural language processing technologies with joint learning schemes to automatically categorize these stories in those dimensions and extract key elements at the same time. We also uncovered significant patterns from the categorized sexual harassment stories. We believe our annotated data set, proposed algorithms, and analysis will help people who have been harassed, authorities, researchers and other related parties in various ways, such as automatically filling reports, enlightening the public in order to prevent future harassment, and enabling more effective, faster action to be taken. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00547v1 |
| https://arxiv.org/pdf/1911.00547v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncover-sexual-harassment-patterns-from-1 |
| Repo | |
| Framework | |
Loss Surface Modality of Feed-Forward Neural Network Architectures
| Title | Loss Surface Modality of Feed-Forward Neural Network Architectures |
| Authors | Anna Sergeevna Bosman, Andries Engelbrecht, Mardé Helbig |
| Abstract | It has been argued in the past that high-dimensional neural networks do not exhibit local minima capable of trapping an optimisation algorithm. However, the relationship between loss surface modality and the neural architecture parameters, such as the number of hidden neurons per layer and the number of hidden layers, remains poorly understood. This study employs fitness landscape analysis to study the modality of neural network loss surfaces under various feed-forward architecture settings. An increase in the problem dimensionality is shown to yield a more searchable and more exploitable loss surface. An increase in the hidden layer width is shown to effectively reduce the number of local minima, and simplify the shape of the global attractor. An increase in the architecture depth is shown to sharpen the global attractor, thus making it more exploitable. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10268v2 |
| https://arxiv.org/pdf/1905.10268v2.pdf | |
| PWC | https://paperswithcode.com/paper/loss-surface-modality-of-feed-forward-neural |
| Repo | |
| Framework | |
Confirmatory Aspect-based Opinion Mining Processes
| Title | Confirmatory Aspect-based Opinion Mining Processes |
| Authors | Jongho Im, Taikgun Song, Youngsu Lee, Jewoo Kim |
| Abstract | A new opinion extraction method is proposed to summarize unstructured, user-generated content (i.e., online customer reviews) in the fixed topic domains. To differentiate the current approach from other opinion extraction approaches, which are often exposed to a sparsity problem and lack of sentiment scores, a confirmatory aspect-based opinion mining framework is introduced along with its practical algorithm called DiSSBUS. In this procedure, 1) each customer review is disintegrated into a set of clauses; 2) each clause is summarized to bi-terms-a topic word and an evaluation word-using a part-of-speech (POS) tagger; and 3) each bi-term is matched to a pre-specified topic relevant to a specific domain. The proposed processes have two primary advantages over existing methods: 1) they can decompose a single review into a set of bi-terms related to pre-specified topics in the domain of interest and, therefore, 2) allow identification of the reviewer’s opinions on the topics via evaluation words within the set of bi-terms. The proposed aspect-based opinion mining is applied to customer reviews of restaurants in Hawaii obtained from TripAdvisor, and the empirical findings validate the effectiveness of the method. Keywords: Clause-based sentiment analysis, Customer review, Opinion mining, Topic modeling, User-generate-contents. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12850v1 |
| https://arxiv.org/pdf/1907.12850v1.pdf | |
| PWC | https://paperswithcode.com/paper/confirmatory-aspect-based-opinion-mining |
| Repo | |
| Framework | |
Non-Local ConvLSTM for Video Compression Artifact Reduction
| Title | Non-Local ConvLSTM for Video Compression Artifact Reduction |
| Authors | Yi Xu, Longwen Gao, Kai Tian, Shuigeng Zhou, Huyang Sun |
| Abstract | Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target frame) for this task. Furthermore, as frames of high quality overall may contain low-quality patches, and high-quality patches may exist in frames of low quality overall, current methods focusing on nearby peak-quality frames (PQFs) may miss high-quality details in low-quality frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following frames of the target frame to generate a residual, from which a higher quality frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods. |
| Tasks | Video Compression |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12286v1 |
| https://arxiv.org/pdf/1910.12286v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-local-convlstm-for-video-compression-1 |
| Repo | |
| Framework | |
Predicting Algorithm Classes for Programming Word Problems
| Title | Predicting Algorithm Classes for Programming Word Problems |
| Authors | Vinayak Athavale, Aayush Naik, Rajas Vanjape, Manish Shrivastava |
| Abstract | We introduce the task of algorithm class prediction for programming word problems. A programming word problem is a problem written in natural language, which can be solved using an algorithm or a program. We define classes of various programming word problems which correspond to the class of algorithms required to solve the problem. We present four new datasets for this task, two multiclass datasets with 550 and 1159 problems each and two multilabel datasets having 3737 and 3960 problems each. We pose the problem as a text classification problem and train neural network and non-neural network-based models on this task. Our best performing classifier gets an accuracy of 62.7 percent for the multiclass case on the five class classification dataset, Codeforces Multiclass-5 (CFMC5). We also do some human-level analysis and compare human performance with that of our text classification models. Our best classifier has an accuracy only 9 percent lower than that of a human on this task. To the best of our knowledge, these are the first reported results on such a task. We make our code and datasets publicly available. |
| Tasks | Text Classification |
| Published | 2019-03-03 |
| URL | http://arxiv.org/abs/1903.00830v2 |
| http://arxiv.org/pdf/1903.00830v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-algorithm-classes-for-programming |
| Repo | |
| Framework | |
Constraint-Aware Neural Networks for Riemann Problems
| Title | Constraint-Aware Neural Networks for Riemann Problems |
| Authors | Jim Magiera, Deep Ray, Jan S. Hesthaven, Christian Rohde |
| Abstract | Neural networks are increasingly used in complex (data-driven) simulations as surrogates or for accelerating the computation of classical surrogates. In many applications physical constraints, such as mass or energy conservation, must be satisfied to obtain reliable results. However, standard machine learning algorithms are generally not tailored to respect such constraints. We propose two different strategies to generate constraint-aware neural networks. We test their performance in the context of front-capturing schemes for strongly nonlinear wave motion in compressible fluid flow. Precisely, in this context so-called Riemann problems have to be solved as surrogates. Their solution describes the local dynamics of the captured wave front in numerical simulations. Three model problems are considered: a cubic flux model problem, an isothermal two-phase flow model, and the Euler equations. We demonstrate that a decrease in the constraint deviation correlates with low discretization errors for all model problems, in addition to the structural advantage of fulfilling the constraint. |
| Tasks | |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12794v1 |
| http://arxiv.org/pdf/1904.12794v1.pdf | |
| PWC | https://paperswithcode.com/paper/constraint-aware-neural-networks-for-riemann |
| Repo | |
| Framework | |
Detecting motorcycle helmet use with deep learning
| Title | Detecting motorcycle helmet use with deep learning |
| Authors | Felix Wilhelm Siebert, Hanhe Lin |
| Abstract | The continuous motorization of traffic has led to a sustained increase in the global number of road related fatalities and injuries. To counter this, governments are focusing on enforcing safe and law-abiding behavior in traffic. However, especially in developing countries where the motorcycle is the main form of transportation, there is a lack of comprehensive data on the safety-critical behavioral metric of motorcycle helmet use. This lack of data prohibits targeted enforcement and education campaigns which are crucial for injury prevention. Hence, we have developed an algorithm for the automated registration of motorcycle helmet usage from video data, using a deep learning approach. Based on 91,000 annotated frames of video data, collected at multiple observation sites in 7 cities across the country of Myanmar, we trained our algorithm to detect active motorcycles, the number and position of riders on the motorcycle, as well as their helmet use. An analysis of the algorithm’s accuracy on an annotated test data set, and a comparison to available human-registered helmet use data reveals a high accuracy of our approach. Our algorithm registers motorcycle helmet use rates with an accuracy of -4.4% and +2.1% in comparison to a human observer, with minimal training for individual observation sites. Without observation site specific training, the accuracy of helmet use detection decreases slightly, depending on a number of factors. Our approach can be implemented in existing roadside traffic surveillance infrastructure and can facilitate targeted data-driven injury prevention campaigns with real-time speed. Implications of the proposed method, as well as measures that can further improve detection accuracy are discussed. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13232v1 |
| https://arxiv.org/pdf/1910.13232v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-motorcycle-helmet-use-with-deep |
| Repo | |
| Framework | |
Online Learning with Continuous Ranked Probability Score
| Title | Online Learning with Continuous Ranked Probability Score |
| Authors | Vladimir V’yugin, Vladimir Trunov |
| Abstract | Probabilistic forecasts in the form of probability distributions over future events have become popular in several fields of statistical science. The dissimilarity between a probability forecast and an outcome is measured by a loss function (scoring rule). Popular example of scoring rule for continuous outcomes is the continuous ranked probability score (CRPS). We consider the case where several competing methods produce online predictions in the form of probability distribution functions. In this paper, the problem of combining probabilistic forecasts is considered in the prediction with expert advice framework. We show that CRPS is a mixable loss function and then the time independent upper bound for the regret of the Vovk’s aggregating algorithm using CRPS as a loss function can be obtained. We present the results of numerical experiments illustrating the proposed methods. |
| Tasks | |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.10173v2 |
| https://arxiv.org/pdf/1902.10173v2.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-with-continuous-ranked |
| Repo | |
| Framework | |
Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval
| Title | Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval |
| Authors | Veeru Talreja, Fariborz Taherkhani, Matthew C. Valenti, Nasser M. Nasrabadi |
| Abstract | With benefits of fast query speed and low storage cost, hashing-based image retrieval approaches have garnered considerable attention from the research community. In this paper, we propose a novel Error-Corrected Deep Cross Modal Hashing (CMH-ECC) method which uses a bitmap specifying the presence of certain facial attributes as an input query to retrieve relevant face images from the database. In this architecture, we generate compact hash codes using an end-to-end deep learning module, which effectively captures the inherent relationships between the face and attribute modality. We also integrate our deep learning module with forward error correction codes to further reduce the distance between different modalities of the same subject. Specifically, the properties of deep hashing and forward error correction codes are exploited to design a cross modal hashing framework with high retrieval performance. Experimental results using two standard datasets with facial attributes-image modalities indicate that our CMH-ECC face image retrieval model outperforms most of the current attribute-based face image retrieval approaches. |
| Tasks | Face Image Retrieval, Image Retrieval |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.04139v1 |
| http://arxiv.org/pdf/1902.04139v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-deep-cross-modal-hashing-and-error |
| Repo | |
| Framework | |
Towards Effective Rebuttal: Listening Comprehension using Corpus-Wide Claim Mining
| Title | Towards Effective Rebuttal: Listening Comprehension using Corpus-Wide Claim Mining |
| Authors | Tamar Lavee, Matan Orbach, Lili Kotlerman, Yoav Kantor, Shai Gretz, Lena Dankin, Shachar Mirkin, Michal Jacovi, Yonatan Bilu, Ranit Aharonov, Noam Slonim |
| Abstract | Engaging in a live debate requires, among other things, the ability to effectively rebut arguments claimed by your opponent. In particular, this requires identifying these arguments. Here, we suggest doing so by automatically mining claims from a corpus of news articles containing billions of sentences, and searching for them in a given speech. This raises the question of whether such claims indeed correspond to those made in spoken speeches. To this end, we collected a large dataset of $400$ speeches in English discussing $200$ controversial topics, mined claims for each topic, and asked annotators to identify the mined claims mentioned in each speech. Results show that in the vast majority of speeches debaters indeed make use of such claims. In addition, we present several baselines for the automatic detection of mined claims in speeches, forming the basis for future work. All collected data is freely available for research. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11889v1 |
| https://arxiv.org/pdf/1907.11889v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-effective-rebuttal-listening-1 |
| Repo | |
| Framework | |
Expression Conditional GAN for Facial Expression-to-Expression Translation
| Title | Expression Conditional GAN for Facial Expression-to-Expression Translation |
| Authors | Hao Tang, Wei Wang, Songsong Wu, Xinya Chen, Dan Xu, Nicu Sebe, Yan Yan |
| Abstract | In this paper, we focus on the facial expression translation task and propose a novel Expression Conditional GAN (ECGAN) which can learn the mapping from one image domain to another one based on an additional expression attribute. The proposed ECGAN is a generic framework and is applicable to different expression generation tasks where specific facial expression can be easily controlled by the conditional attribute label. Besides, we introduce a novel face mask loss to reduce the influence of background changing. Moreover, we propose an entire framework for facial expression generation and recognition in the wild, which consists of two modules, i.e., generation and recognition. Finally, we evaluate our framework on several public face datasets in which the subjects have different races, illumination, occlusion, pose, color, content and background conditions. Even though these datasets are very diverse, both the qualitative and quantitative results demonstrate that our approach is able to generate facial expressions accurately and robustly. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05416v1 |
| https://arxiv.org/pdf/1905.05416v1.pdf | |
| PWC | https://paperswithcode.com/paper/expression-conditional-gan-for-facial |
| Repo | |
| Framework | |
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
| Title | Where is the Bottleneck of Adversarial Learning with Unlabeled Data? |
| Authors | Jingfeng Zhang, Bo Han, Gang Niu, Tongliang Liu, Masashi Sugiyama |
| Abstract | Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled data. However, it is quite expensive to annotate large-scale data well. To compensate for this shortage, several seminal works are utilizing large-scale unlabeled data. In this paper, we observe that seminal works do not perform well, since the quality of pseudo labels on unlabeled data is quite poor, especially when the amount of unlabeled data is significantly larger than that of labeled data. We believe that the quality of pseudo labels is the bottleneck of adversarial learning with unlabeled data. To tackle this bottleneck, we leverage deep co-training, which trains two deep networks and encourages two networks diverged by exploiting peer’s adversarial examples. Based on deep co-training, we propose robust co-training (RCT) for adversarial learning with unlabeled data. We conduct comprehensive experiments on CIFAR-10 and SVHN datasets. Empirical results demonstrate that our RCT can significantly outperform baselines (e.g., robust self-training (RST)) in both standard test accuracy and robust test accuracy w.r.t. different datasets, different network structures, and different types of adversarial training. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08696v1 |
| https://arxiv.org/pdf/1911.08696v1.pdf | |
| PWC | https://paperswithcode.com/paper/where-is-the-bottleneck-of-adversarial |
| Repo | |
| Framework | |
Rejoinder on: Minimal penalties and the slope heuristics: a survey
| Title | Rejoinder on: Minimal penalties and the slope heuristics: a survey |
| Authors | Sylvain Arlot |
| Abstract | This text is the rejoinder following the discussion of a survey paper about minimal penalties and the slope heuristics (Arlot, 2019. Minimal penalties and the slope heuristics: a survey. Journal de la SFDS). While commenting on the remarks made by the discussants, it provides two new results about the slope heuristics for model selection among a collection of projection estimators in least-squares fixed-design regression. First, we prove that the slope heuristics works even when all models are significantly biased. Second, when the noise is Gaussian with a general dependence structure, we compute expectations of key quantities, showing that the slope heuristics certainly is valid in this setting also. |
| Tasks | Model Selection |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13499v1 |
| https://arxiv.org/pdf/1909.13499v1.pdf | |
| PWC | https://paperswithcode.com/paper/rejoinder-on-minimal-penalties-and-the-slope |
| Repo | |
| Framework | |
Relighting Humans: Occlusion-Aware Inverse Rendering for Full-Body Human Images
| Title | Relighting Humans: Occlusion-Aware Inverse Rendering for Full-Body Human Images |
| Authors | Yoshihiro Kanamori, Yuki Endo |
| Abstract | Relighting of human images has various applications in image synthesis. For relighting, we must infer albedo, shape, and illumination from a human portrait. Previous techniques rely on human faces for this inference, based on spherical harmonics (SH) lighting. However, because they often ignore light occlusion, inferred shapes are biased and relit images are unnaturally bright particularly at hollowed regions such as armpits, crotches, or garment wrinkles. This paper introduces the first attempt to infer light occlusion in the SH formulation directly. Based on supervised learning using convolutional neural networks (CNNs), we infer not only an albedo map, illumination but also a light transport map that encodes occlusion as nine SH coefficients per pixel. The main difficulty in this inference is the lack of training datasets compared to unlimited variations of human portraits. Surprisingly, geometric information including occlusion can be inferred plausibly even with a small dataset of synthesized human figures, by carefully preparing the dataset so that the CNNs can exploit the data coherency. Our method accomplishes more realistic relighting than the occlusion-ignored formulation. |
| Tasks | Image Generation |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02714v1 |
| https://arxiv.org/pdf/1908.02714v1.pdf | |
| PWC | https://paperswithcode.com/paper/relighting-humans-occlusion-aware-inverse |
| Repo | |
| Framework | |
A Tangent Distance Preserving Dimensionality Reduction Algorithm
| Title | A Tangent Distance Preserving Dimensionality Reduction Algorithm |
| Authors | Xu Zhao, Zongli Jiang |
| Abstract | This paper considers the problem of nonlinear dimensionality reduction. Unlike existing methods, such as LLE, ISOMAP, which attempt to unfold the true manifold in the low dimensional space, our algorithm tries to preserve the nonlinear structure of the manifold, and shows how the manifold is folded in the high dimensional space. We call this method Tangent Distance Preserving Mapping (TDPM). TDPM uses tangent distance instead of geodesic distance, and then applies MDS to the tangent distance matrix to map the manifold into a low dimensional space in which we can get its nonlinear structure. |
| Tasks | Dimensionality Reduction |
| Published | 2019-02-04 |
| URL | http://arxiv.org/abs/1902.05373v1 |
| http://arxiv.org/pdf/1902.05373v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tangent-distance-preserving-dimensionality |
| Repo | |
| Framework | |
