Paper Group ANR 1487
A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization. Prediction of Compression Index of Fine-Grained Soils Using a Gene Expression Programming Model. Multiple Document Representations from News Alerts for Automated Bio-surveillance Event Detection. Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective S …
A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization
| Title | A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization |
| Authors | Isaak Lim, Moritz Ibing, Leif Kobbelt |
| Abstract | Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of quality that deep learning synthesis approaches for images provide. In this work we present a method for a convolutional point cloud decoder/generator that makes use of recent advances in the domain of image synthesis. Namely, we use Adaptive Instance Normalization and offer an intuition on why it can improve training. Furthermore, we propose extensions to the minimization of the commonly used Chamfer distance for auto-encoding point clouds. In addition, we show that careful sampling is important both for the input geometry and in our point cloud generation process to improve results. The results are evaluated in an auto-encoding setup to offer both qualitative and quantitative analysis. The proposed decoder is validated by an extensive ablation study and is able to outperform current state of the art results in a number of experiments. We show the applicability of our method in the fields of point cloud upsampling, single view reconstruction, and shape synthesis. |
| Tasks | Image Generation, Point Cloud Generation |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11478v1 |
| https://arxiv.org/pdf/1906.11478v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-convolutional-decoder-for-point-clouds |
| Repo | |
| Framework | |
Prediction of Compression Index of Fine-Grained Soils Using a Gene Expression Programming Model
| Title | Prediction of Compression Index of Fine-Grained Soils Using a Gene Expression Programming Model |
| Authors | Danial Mohammadzadeh, Seyed-Farzan Kazemi, Amir Mosavi, Ehsan Nasseralshariati, Joseph H. M. Tah |
| Abstract | In construction projects, estimation of the settlement of fine-grained soils is of critical importance, and yet is a challenging task. The coefficient of consolidation for the compression index (Cc) is a key parameter in modeling the settlement of fine-grained soil layers. However, the estimation of this parameter is costly, time-consuming, and requires skilled technicians. To overcome these drawbacks, we aimed to predict Cc through other soil parameters, i.e., the liquid limit (LL), plastic limit (PL), and initial void ratio (e0). Using these parameters is more convenient and requires substantially less time and cost compared to the conventional tests to estimate Cc. This study presents a novel prediction model for the Cc of fine-grained soils using gene expression programming (GEP). A database consisting of 108 different data points was used to develop the model. A closed-form equation solution was derived to estimate Cc based on LL, PL, and e0. The performance of the developed GEP-based model was evaluated through the coefficient of determination (R2), the root mean squared error (RMSE), and the mean average error (MAE). The proposed model performed better in terms of R2, RMSE, and MAE compared to the other models. |
| Tasks | |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1907.04913v1 |
| https://arxiv.org/pdf/1907.04913v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-compression-index-of-fine |
| Repo | |
| Framework | |
Multiple Document Representations from News Alerts for Automated Bio-surveillance Event Detection
| Title | Multiple Document Representations from News Alerts for Automated Bio-surveillance Event Detection |
| Authors | Aaron Tuor, Fnu Anubhav, Lauren Charles |
| Abstract | Due to globalization, geographic boundaries no longer serve as effective shields for the spread of infectious diseases. In order to aid bio-surveillance analysts in disease tracking, recent research has been devoted to developing information retrieval and analysis methods utilizing the vast corpora of publicly available documents on the internet. In this work, we present methods for the automated retrieval and classification of documents related to active public health events. We demonstrate classification performance on an auto-generated corpus, using recurrent neural network, TF-IDF, and Naive Bayes log count ratio document representations. By jointly modeling the title and description of a document, we achieve 97% recall and 93.3% accuracy with our best performing bio-surveillance event classification model: logistic regression on the combined output from a pair of bidirectional recurrent neural networks. |
| Tasks | Information Retrieval |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.06231v1 |
| http://arxiv.org/pdf/1902.06231v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-document-representations-from-news |
| Repo | |
| Framework | |
Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory
| Title | Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory |
| Authors | Saket Singh, Debdoot Sheet, Mithun Dasgupta |
| Abstract | The simple approach of retrieving a closest match of a query image from one in the gallery, compares an image pair using sum of absolute difference in pixel or feature space. The process is computationally expensive, ill-posed to illumination, background composition, pose variation, as well as inefficient to be deployed on gallery sets with more than 1000 elements. Hashing is a faster alternative which involves representing images in reduced dimensional simple feature spaces. Encoding images into binary hash codes enables similarity comparison in an image-pair using the Hamming distance measure. The challenge, however, lies in encoding the images using a semantic hashing scheme that lets subjective neighbors lie within the tolerable Hamming radius. This work presents a solution employing adversarial learning of a deep neural semantic hashing network for fashion inventory retrieval. It consists of a feature extracting convolutional neural network (CNN) learned to (i) minimize error in classifying type of clothing, (ii) minimize hamming distance between semantic neighbors and maximize distance between semantically dissimilar images, (iii) maximally scramble a discriminator’s ability to identify the corresponding hash code-image pair when processing a semantically similar query-gallery image pair. Experimental validation for fashion inventory search yields a mean average precision (mAP) of 90.65% in finding the closest match as compared to 53.26% obtained by the prior art of deep Cauchy hashing for hamming space retrieval. |
| Tasks | |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00382v1 |
| https://arxiv.org/pdf/1907.00382v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarially-trained-deep-neural-semantic |
| Repo | |
| Framework | |
A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data
| Title | A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data |
| Authors | Zijian Zhao, Su Zhu, Kai Yu |
| Abstract | Spoken language understanding (SLU) systems can be trained on two types of labelled data: aligned or unaligned. Unaligned data do not require word by word annotation and is easier to be obtained. In the paper, we focus on spoken language understanding from unaligned data whose annotation is a set of act-slot-value triples. Previous works usually focus on improve slot-value pair prediction and estimate dialogue act types separately, which ignores the hierarchical structure of the act-slot-value triples. Here, we propose a novel hierarchical decoding model which dynamically parses act, slot and value in a structured way and employs pointer network to handle out-of-vocabulary (OOV) values. Experiments on DSTC2 dataset, a benchmark unaligned dataset, show that the proposed model not only outperforms previous state-of-the-art model, but also can be generalized effectively and efficiently to unseen act-slot type pairs and OOV values. |
| Tasks | Spoken Language Understanding |
| Published | 2019-04-09 |
| URL | http://arxiv.org/abs/1904.04498v1 |
| http://arxiv.org/pdf/1904.04498v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-decoding-model-for-spoken |
| Repo | |
| Framework | |
Simulating CRF with CNN for CNN
| Title | Simulating CRF with CNN for CNN |
| Authors | Lena Gorelick, Olga Veksler |
| Abstract | Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired. In this paper, we propose a novel simple approach to CNN+CRF combination. In particular, we propose to simulate a CRF regularizer with a trainable module that has standard CNN architecture. We call this module a CRF Simulator. We can automatically generate an unlimited amount of ground truth for training such CRF Simulator without any user interaction, provided we have an efficient algorithm for optimization of the actual CRF regularizer. After our CRF Simulator is trained, it can be directly incorporated as part of any larger CNN architecture, enabling a seamless end-to-end training. In particular, the other modules can learn parameters that are more attuned to the performance of the CRF Simulator module. We demonstrate the effectiveness of our approach on the task of salient object segmentation regularized with the standard binary CRF energy. In contrast to previous work we do not need to develop and implement the complex mechanics of optimizing a specific CRF as part of CNN. In fact, our approach can be easily extended to other CRF energies, including multi-label. To the best of our knowledge we are the first to study the question of whether the output of CNNs can have regularization properties of CRFs. |
| Tasks | Semantic Segmentation |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02163v1 |
| https://arxiv.org/pdf/1905.02163v1.pdf | |
| PWC | https://paperswithcode.com/paper/simulating-crf-with-cnn-for-cnn |
| Repo | |
| Framework | |
A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR)
| Title | A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR) |
| Authors | Michael Regan, Pushpendre Rastogi, Arpit Gupta, Lambert Mathias |
| Abstract | We present Contextual Query Rewrite (CQR) a dataset for multi-domain task-oriented spoken dialogue systems that is an extension of the Stanford dialog corpus (Eric et al., 2017a). While previous approaches have addressed the issue of diverse schemas by learning candidate transformations (Naik et al., 2018), we instead model the reference resolution task as a user query reformulation task, where the dialog state is serialized into a natural language query that can be executed by the downstream spoken language understanding system. In this paper, we describe our methodology for creating the query reformulation extension to the dialog corpus, and present an initial set of experiments to establish a baseline for the CQR task. We have released the corpus to the public [1] to support further research in this area. |
| Tasks | Spoken Dialogue Systems, Spoken Language Understanding |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.11783v3 |
| http://arxiv.org/pdf/1903.11783v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-dataset-for-resolving-referring-expressions |
| Repo | |
| Framework | |
Machine Learning Tips and Tricks for Power Line Communications
| Title | Machine Learning Tips and Tricks for Power Line Communications |
| Authors | Andrea M. Tonello, Nunzio A. Letizia, Davide Righini, Francesco Marcuzzi |
| Abstract | A great deal of attention has been recently given to Machine Learning (ML) techniques in many different application fields. This paper provides a vision of what ML can do in Power Line Communications (PLC). We firstly and briefly describe classical formulations of ML, and distinguish deterministic from statistical learning models with relevance to communications. We then discuss ML applications in PLC for each layer, namely, for characterization and modeling, for the development of physical layer algorithms, for media access control and networking. Finally, other applications of PLC that can benefit from the usage of ML, as grid diagnostics, are analyzed. Illustrative numerical examples are reported to serve the purpose of validating the ideas and motivate future research endeavors in this stimulating signal/data processing field. |
| Tasks | |
| Published | 2019-04-24 |
| URL | https://arxiv.org/abs/1904.11949v2 |
| https://arxiv.org/pdf/1904.11949v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-tips-and-tricks-for-power |
| Repo | |
| Framework | |
Hierarchical Clustering-guided re-ID with Triplet loss
| Title | Hierarchical Clustering-guided re-ID with Triplet loss |
| Authors | Kaiwei Zeng |
| Abstract | For most unsupervised person re-identification (re-ID), people often adopt unsupervised domain adaptation (UDA) method. UDA often train on the labeled source dataset and evaluate on the target dataset, which often focuses on learning differences between the source dataset and the target dataset to improve the generalization of the model. Base on these, we explore how to make use of the similarity of samples to conduct a fully unsupervised method which just trains on the unlabeled target dataset. Concretely, we propose a hierarchical clustering-guided re-ID (HCR) method. We use hierarchical clustering to generate pseudo labels and use these pseudo labels as monitors to conduct the training. In order to exclude hard examples and promote the convergence of the model, We use PK sampling in each iteration, which randomly selects a fixed number of samples from each cluster for training. We evaluate our model on Market-1501, DukeMTMC-reID and MSMT17. Results show that HCR gets the state-of-the-arts and achieves 55.3% mAP on Market-1501 and 46.8% mAP on DukeMTMC-reID. Our code will be released soon. |
| Tasks | Domain Adaptation, Person Re-Identification, Unsupervised Domain Adaptation, Unsupervised Person Re-Identification |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12278v1 |
| https://arxiv.org/pdf/1910.12278v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-clustering-guided-re-id-with |
| Repo | |
| Framework | |
Combating Fake News: A Survey on Identification and Mitigation Techniques
| Title | Combating Fake News: A Survey on Identification and Mitigation Techniques |
| Authors | Karishma Sharma, Feng Qian, He Jiang, Natali Ruchansky, Ming Zhang, Yan Liu |
| Abstract | The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news, and mitigation of its widespread impact on public opinion. While much of the earlier research was focused on identification of fake news based on its contents or by exploiting users’ engagements with the news on social media, there has been a rising interest in proactive intervention strategies to counter the spread of misinformation and its impact on society. In this survey, we describe the modern-day problem of fake news and, in particular, highlight the technical challenges associated with it. We discuss existing methods and techniques applicable to both identification and mitigation, with a focus on the significant advances in each method and their advantages and limitations. In addition, research has often been limited by the quality of existing datasets and their specific application contexts. To alleviate this problem, we comprehensively compile and summarize characteristic features of available datasets. Furthermore, we outline new directions of research to facilitate future development of effective and interdisciplinary solutions. |
| Tasks | |
| Published | 2019-01-18 |
| URL | http://arxiv.org/abs/1901.06437v1 |
| http://arxiv.org/pdf/1901.06437v1.pdf | |
| PWC | https://paperswithcode.com/paper/combating-fake-news-a-survey-on |
| Repo | |
| Framework | |
Truly Proximal Policy Optimization
| Title | Truly Proximal Policy Optimization |
| Authors | Yuhui Wang, Hao He, Chao Wen, Xiaoyang Tan |
| Abstract | Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from being fully understood. In this paper, we show that PPO could neither strictly restrict the likelihood ratio as it attempts to do nor enforce a well-defined trust region constraint, which means that it may still suffer from the risk of performance instability. To address this issue, we present an enhanced PPO method, named Truly PPO. Two critical improvements are made in our method: 1) it adopts a new clipping function to support a rollback behavior to restrict the difference between the new policy and the old one; 2) the triggering condition for clipping is replaced with a trust region-based one, such that optimizing the resulted surrogate objective function provides guaranteed monotonic improvement of the ultimate policy performance. It seems, by adhering more truly to making the algorithm proximal - confining the policy within the trust region, the new algorithm improves the original PPO on both sample efficiency and performance. |
| Tasks | |
| Published | 2019-03-19 |
| URL | https://arxiv.org/abs/1903.07940v2 |
| https://arxiv.org/pdf/1903.07940v2.pdf | |
| PWC | https://paperswithcode.com/paper/truly-proximal-policy-optimization |
| Repo | |
| Framework | |
Additive Bayesian Network Modelling with the R Package abn
| Title | Additive Bayesian Network Modelling with the R Package abn |
| Authors | Gilles Kratzer, Fraser Iain Lewis, Arianna Comin, Marta Pittavino, Reinhard Furrer |
| Abstract | The R package abn is designed to fit additive Bayesian models to observational datasets. It contains routines to score Bayesian networks based on Bayesian or information theoretic formulations of generalized linear models. It is equipped with exact search and greedy search algorithms to select the best network. It supports a possible blend of continuous, discrete and count data and input of prior knowledge at a structural level. The Bayesian implementation supports random effects to control for one-layer clustering. In this paper, we give an overview of the methodology and illustrate the package’s functionalities using a veterinary dataset about respiratory diseases in commercial swine production. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09006v1 |
| https://arxiv.org/pdf/1911.09006v1.pdf | |
| PWC | https://paperswithcode.com/paper/additive-bayesian-network-modelling-with-the |
| Repo | |
| Framework | |
Cross-Platform Modeling of Users’ Behavior on Social Media
| Title | Cross-Platform Modeling of Users’ Behavior on Social Media |
| Authors | Haiqian Gu, Jie Wang, Ziwen Wang, Bojin Zhuang, Wenhao Bian, Fei Su |
| Abstract | With the booming development and popularity of mobile applications, different verticals accumulate abundant data of user information and social behavior, which are spontaneous, genuine and diversified. However, each platform describes user’s portraits in only certain aspect, resulting in difficult combination of those internet footprints together. In our research, we proposed a modeling approach to analyze user’s online behavior across different social media platforms. Structured and unstructured data of same users shared by NetEase Music and Sina Weibo have been collected for cross-platform analysis of correlations between music preference and other users’ characteristics. Based on music tags of genre and mood, genre cluster of five groups and mood cluster of four groups have been formed by computing their collected song lists with K-means method. Moreover, with the help of user data of Weibo, correlations between music preference (i.e. genre, mood) and Big Five personalities (BFPs) and basic information (e.g. gender, resident region, tags) have been comprehensively studied, building up full-scale user portraits with finer grain. Our findings indicate that people’s music preference could be linked with their real social activities. For instance, people living in mountainous areas generally prefer folk music, while those in urban areas like pop music more. Interestingly, dog lovers could love sad music more than cat lovers. Moreover, our proposed cross-platform modeling approach could be adapted to other verticals, providing an online automatic way for profiling users in a more precise and comprehensive way. |
| Tasks | |
| Published | 2019-06-23 |
| URL | https://arxiv.org/abs/1906.12324v1 |
| https://arxiv.org/pdf/1906.12324v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-platform-modeling-of-users-behavior-on |
| Repo | |
| Framework | |
Tree-wise Distribution Sensitive hashing: Efficient Maximum likelihood Classification by joint dimensionality reduction in known probabilistic settings
| Title | Tree-wise Distribution Sensitive hashing: Efficient Maximum likelihood Classification by joint dimensionality reduction in known probabilistic settings |
| Authors | Arash Gholami Davoodi, Anubhav Baweja, Hosein Mohimani |
| Abstract | We consider the problem of maximum likelihood classification of a high dimensional data point y to billions of classes $x_1,…,x_N$, where the conditional probability p(yx) is known. In the most general case, the complexity of the brute-force method for this classification grows linearly, O(N), with the number of classes N. Efficient multiclass classification methods have been introduced to solve this problem with logarithmic complexity. However, these methods suffer from the curse of dimensionality, i.e., in large dimensions their complexity approaches $O(N)$ per query data point. In the special case where the conditional probability distribution $p(yx)$ is a Gaussian centered at x, i.e., $p(yx) \propto N (x,\sigma)$, the maximum likelihood classification reduces to the nearest neighbor search with the Euclidean norm. Sublinear methods based on locality sensitive hashing (LSH) have been introduced to solve an approximate version of the nearest neighbor search for high dimensional data. Inspired by these advances, here we introduce distribution sensitive hashing (DSH) to solve an approximate version of the maximum likelihood classification problem through joint dimensionality reduction. In the case of discrete probability distributions, we design TreeDSH, a universal family of distribution sensitive hashes based on the decision trees, and show that their complexity grow sub-linearly. Theory and simulation presented in this paper demonstrate that TreeDSH is more efficient than LSH-hamming and Min-Hashing schemes. Finally, we apply TreeDSH to the problem of peptide identification from mass spectrometry data. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.04559v1 |
| https://arxiv.org/pdf/1905.04559v1.pdf | |
| PWC | https://paperswithcode.com/paper/tree-wise-distribution-sensitive-hashing |
| Repo | |
| Framework | |
A simple discriminative training method for machine translation with large-scale features
| Title | A simple discriminative training method for machine translation with large-scale features |
| Authors | Tian Xia, Shaodan Zhai, Shaojun Wang |
| Abstract | Margin infused relaxed algorithms (MIRAs) dominate model tuning in statistical machine translation in the case of large scale features, but also they are famous for the complexity in implementation. We introduce a new method, which regards an N-best list as a permutation and minimizes the Plackett-Luce loss of ground-truth permutations. Experiments with large-scale features demonstrate that, the new method is more robust than MERT; though it is only matchable with MIRAs, it has a comparatively advantage, easier to implement. |
| Tasks | Machine Translation |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.09491v1 |
| https://arxiv.org/pdf/1909.09491v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-discriminative-training-method-for |
| Repo | |
| Framework | |
