Paper Group ANR 360
How Impersonators Exploit Instagram to Generate Fake Engagement?. Defense-PointNet: Protecting PointNet Against Adversarial Attacks. YOLOff: You Only Learn Offsets for robust 6DoF object pose estimation. A Fixed point view: A Model-Based Clustering Framework. Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art. Exploring a …
How Impersonators Exploit Instagram to Generate Fake Engagement?
| Title | How Impersonators Exploit Instagram to Generate Fake Engagement? |
| Authors | Koosha Zarei, Reza Farahbakhsh, Noel Crespi |
| Abstract | Impersonators on Online Social Networks such as Instagram are playing an important role in the propagation of the content. These entities are the type of nefarious fake accounts that intend to disguise a legitimate account by making similar profiles. In addition to having impersonated profiles, we observed a considerable engagement from these entities to the published posts of verified accounts. Toward that end, we concentrate on the engagement of impersonators in terms of active and passive engagements which is studied in three major communities including Politician'', News agency’', and ``Sports star’’ on Instagram. Inside each community, four verified accounts have been selected. Based on the implemented approach in our previous studies, we have collected 4.8K comments, and 2.6K likes across 566 posts created from 3.8K impersonators during 7 months. Our study shed light into this interesting phenomena and provides a surprising observation that can help us to understand better how impersonators engaging themselves inside Instagram in terms of writing Comments and leaving Likes. | |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.07173v1 |
| https://arxiv.org/pdf/2002.07173v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-impersonators-exploit-instagram-to |
| Repo | |
| Framework | |
Defense-PointNet: Protecting PointNet Against Adversarial Attacks
| Title | Defense-PointNet: Protecting PointNet Against Adversarial Attacks |
| Authors | Yu Zhang, Gongbo Liang, Tawfiq Salem, Nathan Jacobs |
| Abstract | Despite remarkable performance across a broad range of tasks, neural networks have been shown to be vulnerable to adversarial attacks. Many works focus on adversarial attacks and defenses on 2D images, but few focus on 3D point clouds. In this paper, our goal is to enhance the adversarial robustness of PointNet, which is one of the most widely used models for 3D point clouds. We apply the fast gradient sign attack method (FGSM) on 3D point clouds and find that FGSM can be used to generate not only adversarial images but also adversarial point clouds. To minimize the vulnerability of PointNet to adversarial attacks, we propose Defense-PointNet. We compare our model with two baseline approaches and show that Defense-PointNet significantly improves the robustness of the network against adversarial samples. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.11881v1 |
| https://arxiv.org/pdf/2002.11881v1.pdf | |
| PWC | https://paperswithcode.com/paper/defense-pointnet-protecting-pointnet-against |
| Repo | |
| Framework | |
YOLOff: You Only Learn Offsets for robust 6DoF object pose estimation
| Title | YOLOff: You Only Learn Offsets for robust 6DoF object pose estimation |
| Authors | Mathieu Gonzalez, Amine Kacete, Albert Murienne, Eric Marchand |
| Abstract | Estimating the 3D translation and orientation of an object is a challenging task that can be considered within augmented reality or robotic applications. In this paper, we propose a novel approach to perform 6 DoF object pose estimation from a single RGB-D image in cluttered scenes. We adopt an hybrid pipeline in two stages: data-driven and geometric respectively. The first data-driven step consists of a classification CNN to estimate the object 2D location in the image from local patches, followed by a regression CNN trained to predict the 3D location of a set of keypoints in the camera coordinate system. We robustly perform local voting to recover the location of each keypoint in the camera coordinate system. To extract the pose information, the geometric step consists in aligning the 3D points in the camera coordinate system with the corresponding 3D points in world coordinate system by minimizing a registration error, thus computing the pose. Our experiments on the standard dataset LineMod show that our approach more robust and accurate than state-of-the-art methods. |
| Tasks | Pose Estimation |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00911v3 |
| https://arxiv.org/pdf/2002.00911v3.pdf | |
| PWC | https://paperswithcode.com/paper/yoloff-you-only-learn-offsets-for-robust-6dof |
| Repo | |
| Framework | |
A Fixed point view: A Model-Based Clustering Framework
| Title | A Fixed point view: A Model-Based Clustering Framework |
| Authors | Jianhao Ding, Lansheng Han |
| Abstract | With the inflation of the data, clustering analysis, as a branch of unsupervised learning, lacks unified understanding and application of its mathematical law. Based on the view of fixed point, this paper restates the model-based clustering and proposes a unified clustering framework. In order to find fixed points as cluster centers, the framework iteratively constructs the contraction map, which strongly reveals the convergence mechanism and interconnections among algorithms. By specifying a contraction map, Gaussian mixture model (GMM) can be mapped to the framework as an application. We hope the fixed point framework will help the design of future clustering algorithms. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08032v1 |
| https://arxiv.org/pdf/2002.08032v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fixed-point-view-a-model-based-clustering |
| Repo | |
| Framework | |
Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art
| Title | Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art |
| Authors | Mohammad Braei, Sebastian Wagner |
| Abstract | Anomaly detection for time-series data has been an important research field for a long time. Seminal work on anomaly detection methods has been focussing on statistical approaches. In recent years an increasing number of machine learning algorithms have been developed to detect anomalies on time-series. Subsequently, researchers tried to improve these techniques using (deep) neural networks. In the light of the increasing number of anomaly detection methods, the body of research lacks a broad comparative evaluation of statistical, machine learning and deep learning methods. This paper studies 20 univariate anomaly detection methods from the all three categories. The evaluation is conducted on publicly available datasets, which serve as benchmarks for time-series anomaly detection. By analyzing the accuracy of each method as well as the computation time of the algorithms, we provide a thorough insight about the performance of these anomaly detection approaches, alongside some general notion of which method is suited for a certain type of data. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2020-04-01 |
| URL | https://arxiv.org/abs/2004.00433v1 |
| https://arxiv.org/pdf/2004.00433v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-univariate-time-series-a |
| Repo | |
| Framework | |
Exploring and Distilling Cross-Modal Information for Image Captioning
| Title | Exploring and Distilling Cross-Modal Information for Image Captioning |
| Authors | Fenglin Liu, Xuancheng Ren, Yuanxin Liu, Kai Lei, Xu Sun |
| Abstract | Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image understanding. In this work, we argue that such understanding requires visual attention to correlated image regions and semantic attention to coherent attributes of interest. Based on the Transformer, to perform effective attention, we explore image captioning from a cross-modal perspective and propose the Global-and-Local Information Exploring-and-Distilling approach that explores and distills the source information in vision and language. It globally provides the aspect vector, a spatial and relational representation of images based on caption contexts, through the extraction of salient region groupings and attribute collocations, and locally extracts the fine-grained regions and attributes in reference to the aspect vector for word selection. Our Transformer-based model achieves a CIDEr score of 129.3 in offline COCO evaluation on the COCO testing set with remarkable efficiency in terms of accuracy, speed, and parameter budget. |
| Tasks | Image Captioning |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2002.12585v2 |
| https://arxiv.org/pdf/2002.12585v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-and-distilling-cross-modal |
| Repo | |
| Framework | |
Constructing a Highlight Classifier with an Attention Based LSTM Neural Network
| Title | Constructing a Highlight Classifier with an Attention Based LSTM Neural Network |
| Authors | Michael Kuehne, Marius Radu |
| Abstract | Data is being produced in larger quantities than ever before in human history. It’s only natural to expect a rise in demand for technology that aids humans in sifting through and analyzing this inexhaustible supply of information. This need exists in the market research industry, where large amounts of consumer research data is collected through video recordings. At present, the standard method for analyzing video data is human labor. Market researchers manually review the vast majority of consumer research video in order to identify relevant portions - highlights. The industry state of the art turnaround ratio is 2.2 - for every hour of video content 2.2 hours of manpower are required. In this study we present a novel approach for NLP-based highlight identification and extraction based on a supervised learning model that aides market researchers in sifting through their data. Our approach hinges on a manually curated user-generated highlight clips constructed from long and short-form video data. The problem is best suited for an NLP approach due to the availability of video transcription. We evaluate multiple classes of models, from gradient boosting to recurrent neural networks, comparing their performance in extraction and identification of highlights. The best performing models are then evaluated using four sampling methods designed to analyze documents much larger than the maximum input length of the classifiers. We report very high performances for the standalone classifiers, ROC AUC scores in the range 0.93-0.94, but observe a significant drop in effectiveness when evaluated on large documents. Based on our results we suggest combinations of models/sampling algorithms for various use cases. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.04608v1 |
| https://arxiv.org/pdf/2002.04608v1.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-a-highlight-classifier-with-an |
| Repo | |
| Framework | |
A Distributional Framework for Data Valuation
| Title | A Distributional Framework for Data Valuation |
| Authors | Amirata Ghorbani, Michael P. Kim, James Zou |
| Abstract | Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its foundational role, a key limitation of the data Shapley framework is that it only provides valuations for points within a fixed data set. It does not account for statistical aspects of the data and does not give a way to reason about points outside the data set. To address these limitations, we propose a novel framework – distributional Shapley – where the value of a point is defined in the context of an underlying data distribution. We prove that distributional Shapley has several desirable statistical properties; for example, the values are stable under perturbations to the data points themselves and to the underlying data distribution. We leverage these properties to develop a new algorithm for estimating values from data, which comes with formal guarantees and runs two orders of magnitude faster than state-of-the-art algorithms for computing the (non-distributional) data Shapley values. We apply distributional Shapley to diverse data sets and demonstrate its utility in a data market setting. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12334v1 |
| https://arxiv.org/pdf/2002.12334v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributional-framework-for-data-valuation |
| Repo | |
| Framework | |
Anomaly Detection by Latent Regularized Dual Adversarial Networks
| Title | Anomaly Detection by Latent Regularized Dual Adversarial Networks |
| Authors | Chengwei Chen, Pan Chen, Haichuan Song, Yiqing Tao, Yuan Xie, Shouhong Ding, Lizhuang Ma |
| Abstract | Anomaly detection is a fundamental problem in computer vision area with many real-world applications. Given a wide range of images belonging to the normal class, emerging from some distribution, the objective of this task is to construct the model to detect out-of-distribution images belonging to abnormal instances. Semi-supervised Generative Adversarial Networks (GAN)-based methods have been gaining popularity in anomaly detection task recently. However, the training process of GAN is still unstable and challenging. To solve these issues, a novel adversarial dual autoencoder network is proposed, in which the underlying structure of training data is not only captured in latent feature space, but also can be further restricted in the space of latent representation in a discriminant manner, leading to a more accurate detector. In addition, the auxiliary autoencoder regarded as a discriminator could obtain an more stable training process. Experiments show that our model achieves the state-of-the-art results on MNIST and CIFAR10 datasets as well as GTSRB stop signs dataset. |
| Tasks | Anomaly Detection |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01607v1 |
| https://arxiv.org/pdf/2002.01607v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-by-latent-regularized-dual |
| Repo | |
| Framework | |
A Graduated Filter Method for Large Scale Robust Estimation
| Title | A Graduated Filter Method for Large Scale Robust Estimation |
| Authors | Huu Le, Christopher Zach |
| Abstract | Due to the highly non-convex nature of large-scale robust parameter estimation, avoiding poor local minima is challenging in real-world applications where input data is contaminated by a large or unknown fraction of outliers. In this paper, we introduce a novel solver for robust estimation that possesses a strong ability to escape poor local minima. Our algorithm is built upon the class of traditional graduated optimization techniques, which are considered state-of-the-art local methods to solve problems having many poor minima. The novelty of our work lies in the introduction of an adaptive kernel (or residual) scaling scheme, which allows us to achieve faster convergence rates. Like other existing methods that aim to return good local minima for robust estimation tasks, our method relaxes the original robust problem but adapts a filter framework from non-linear constrained optimization to automatically choose the level of relaxation. Experimental results on real large-scale datasets such as bundle adjustment instances demonstrate that our proposed method achieves competitive results. |
| Tasks | |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09080v1 |
| https://arxiv.org/pdf/2003.09080v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-graduated-filter-method-for-large-scale |
| Repo | |
| Framework | |
Scalable Learning Paradigms for Data-Driven Wireless Communication
| Title | Scalable Learning Paradigms for Data-Driven Wireless Communication |
| Authors | Yue Xu, Feng Yin, Wenjun Xu, Chia-Han Lee, Jiaru Lin, Shuguang Cui |
| Abstract | The marriage of wireless big data and machine learning techniques revolutionizes the wireless system by the data-driven philosophy. However, the ever exploding data volume and model complexity will limit centralized solutions to learn and respond within a reasonable time. Therefore, scalability becomes a critical issue to be solved. In this article, we aim to provide a systematic discussion on the building blocks of scalable data-driven wireless networks. On one hand, we discuss the forward-looking architecture and computing framework of scalable data-driven systems from a global perspective. On the other hand, we discuss the learning algorithms and model training strategies performed at each individual node from a local perspective. We also highlight several promising research directions in the context of scalable data-driven wireless communications to inspire future research. |
| Tasks | |
| Published | 2020-03-01 |
| URL | https://arxiv.org/abs/2003.00474v1 |
| https://arxiv.org/pdf/2003.00474v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-learning-paradigms-for-data-driven |
| Repo | |
| Framework | |
Neural Network Tracking of Moving Objects with Unknown Equations of Motion
| Title | Neural Network Tracking of Moving Objects with Unknown Equations of Motion |
| Authors | Boaz Fish, Ben Zion Bobrovsky |
| Abstract | In this paper we present a Neural Network design that can be used to track the location of a moving object within a given range based on the object’s noisy coordinates measurement. A function commonly performed by the KLMn filter, our goal is to show that our method outperforms the Kalman filter in certain scenarios. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.08362v1 |
| https://arxiv.org/pdf/2003.08362v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-tracking-of-moving-objects |
| Repo | |
| Framework | |
Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
| Title | Anomaly Detection in Video Data Based on Probabilistic Latent Space Models |
| Authors | Giulia Slavic, Damian Campo, Mohamad Baydoun, Pablo Marin, David Martin, Lucio Marcenaro, Carlo Regazzoni |
| Abstract | This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment. |
| Tasks | Anomaly Detection, Autonomous Vehicles |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.07623v1 |
| https://arxiv.org/pdf/2003.07623v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-video-data-based-on |
| Repo | |
| Framework | |
A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image
| Title | A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image |
| Authors | Yuyu Guo, Lei Bi, Euijoon Ahn, Dagan Feng, Qian Wang, Jinman Kim |
| Abstract | Dynamic medical imaging is usually limited in application due to the large radiation doses and longer image scanning and reconstruction times. Existing methods attempt to reduce the dynamic sequence by interpolating the volumes between the acquired image volumes. However, these methods are limited to either 2D images and/or are unable to support large variations in the motion between the image volume sequences. In this paper, we present a spatiotemporal volumetric interpolation network (SVIN) designed for 4D dynamic medical images. SVIN introduces dual networks: first is the spatiotemporal motion network that leverages the 3D convolutional neural network (CNN) for unsupervised parametric volumetric registration to derive spatiotemporal motion field from two-image volumes; the second is the sequential volumetric interpolation network, which uses the derived motion field to interpolate image volumes, together with a new regression-based module to characterize the periodic motion cycles in functional organ structures. We also introduce an adaptive multi-scale architecture to capture the volumetric large anatomy motions. Experimental results demonstrated that our SVIN outperformed state-of-the-art temporal medical interpolation methods and natural video interpolation methods that have been extended to support volumetric images. Our ablation study further exemplified that our motion network was able to better represent the large functional motion compared with the state-of-the-art unsupervised medical registration methods. |
| Tasks | |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2002.12680v1 |
| https://arxiv.org/pdf/2002.12680v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-spatiotemporal-volumetric-interpolation |
| Repo | |
| Framework | |
Deep Bayesian Network for Visual Question Generation
| Title | Deep Bayesian Network for Visual Question Generation |
| Authors | Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri |
| Abstract | Generating natural questions from an image is a semantic task that requires using vision and language modalities to learn multimodal representations. Images can have multiple visual and language cues such as places, captions, and tags. In this paper, we propose a principled deep Bayesian learning framework that combines these cues to produce natural questions. We observe that with the addition of more cues and by minimizing uncertainty in the among cues, the Bayesian network becomes more confident. We propose a Minimizing Uncertainty of Mixture of Cues (MUMC), that minimizes uncertainty present in a mixture of cues experts for generating probabilistic questions. This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study. We observe that with the addition of more cues and by minimizing uncertainty among the cues, the Bayesian framework becomes more confident. Ablation studies of our model indicate that a subset of cues is inferior at this task and hence the principled fusion of cues is preferred. Further, we observe that the proposed approach substantially improves over state-of-the-art benchmarks on the quantitative metrics (BLEU-n, METEOR, ROUGE, and CIDEr). Here we provide project link for Deep Bayesian VQG \url{https://delta-lab-iitk.github.io/BVQG/} |
| Tasks | Question Generation |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08779v1 |
| https://arxiv.org/pdf/2001.08779v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-bayesian-network-for-visual-question |
| Repo | |
| Framework | |
