Paper Group ANR 1358
Identifying Linear Models in Multi-Resolution Population Data using Minimum Description Length Principle to Predict Household Income. RWF-2000: An Open Large Scale Video Database for Violence Detection. Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow. Discriminative Few-Shot Learning Based on Directional St …
Identifying Linear Models in Multi-Resolution Population Data using Minimum Description Length Principle to Predict Household Income
| Title | Identifying Linear Models in Multi-Resolution Population Data using Minimum Description Length Principle to Predict Household Income |
| Authors | Chainarong Amornbunchornvej, Navaporn Surasvadi, Anon Plangprasopchok, Suttipong Thajchayapong |
| Abstract | One shirt size cannot fit everybody, while we cannot make a unique shirt that fits perfectly for everyone because of resource limitation. This analogy is true for the policy making. Policy makers cannot establish a single policy to solve all problems for all regions because each region has its own unique issue. In the other extreme, policy makers also cannot create a policy for each small village due to the resource limitation. Would it be better if we can find a set of largest regions such that the population of each region within this set has common issues and we can establish a single policy for them? In this work, we propose a framework using regression analysis and minimum description length (MDL) to find a set of largest areas that have common indicators, which can be used to predict household incomes efficiently. Given a set of household features, and a multi-resolution partition that represents administrative divisions, our framework reports a set C* of largest subdivisions that have a common model for population-income prediction. We formalize a problem of finding C* and propose the algorithm as a solution. We use both simulation datasets as well as a real-world dataset of Thailand’s population household information to demonstrate our framework performance and application. The results show that our framework performance is better than the baseline methods. We show the results of our method can be used to find indicators of income prediction for many areas in Thailand. By increasing these indicator values, we expect people in these areas to gain more incomes. Hence, the policy makers can plan to establish the policies by using these indicators in our results as a guideline to solve low-income issues. Our framework can be used to support policy makers to establish policies regarding any other dependent variable beyond incomes in order to combat poverty and other issues. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.05234v1 |
| https://arxiv.org/pdf/1907.05234v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-linear-models-in-multi-resolution |
| Repo | |
| Framework | |
RWF-2000: An Open Large Scale Video Database for Violence Detection
| Title | RWF-2000: An Open Large Scale Video Database for Violence Detection |
| Authors | Ming Cheng, Kunjing Cai, Ming Li |
| Abstract | In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices. Usually, these cameras provide cues and evidence after crimes conducted, while they are rarely used to prevent or stop criminal activities in time. It is both time and labor consuming to manually monitor a large amount of video data from surveillance cameras. Therefore, automatically recognizing violent behaviors from video signals becomes essential. In this paper, we summarize several existing video datasets for violence detection and propose a new video dataset with more than 2,000 videos captured by surveillance cameras in real-world scenes. Also, we present a new method that utilizes both the merits of 3D-CNNs and optical flow, namely Flow Gated Network. The proposed approach obtains an accuracy of 86.75% on the test set of our proposed RWF-2000 database. |
| Tasks | Optical Flow Estimation |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05913v1 |
| https://arxiv.org/pdf/1911.05913v1.pdf | |
| PWC | https://paperswithcode.com/paper/rwf-2000-an-open-large-scale-video-database |
| Repo | |
| Framework | |
Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow
| Title | Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow |
| Authors | Thomas Vandal, Ramakrishna Nemani |
| Abstract | Applications of satellite data in areas such as weather tracking and modeling, ecosystem monitoring, wildfire detection, and land-cover change are heavily dependent on the trade-offs to spatial, spectral and temporal resolutions of observations. In weather tracking, high-frequency temporal observations are critical and used to improve forecasts, study severe events, and extract atmospheric motion, among others. However, while the current generation of geostationary satellites have hemispheric coverage at 10-15 minute intervals, higher temporal frequency observations are ideal for studying mesoscale severe weather events. In this work, we apply a task specific optical flow approach to temporal up-sampling using deep convolutional neural networks. We apply this technique to 16-bands of GOES-R/Advanced Baseline Imager mesoscale dataset to temporally enhance full disk hemispheric snapshots of different spatial resolutions from 15 minutes to 1 minute. Experiments show the effectiveness of task specific optical flow and multi-scale blocks for interpolating high-frequency severe weather events relative to bilinear and global optical flow baselines. Lastly, we demonstrate strong performance in capturing variability during a convective precipitation events. |
| Tasks | Optical Flow Estimation |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12013v3 |
| https://arxiv.org/pdf/1907.12013v3.pdf | |
| PWC | https://paperswithcode.com/paper/optical-flow-for-intermediate-frame |
| Repo | |
| Framework | |
Discriminative Few-Shot Learning Based on Directional Statistics
| Title | Discriminative Few-Shot Learning Based on Directional Statistics |
| Authors | Junyoung Park, Subin Yi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim |
| Abstract | Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorithm to generate class representatives for few-shot classification tasks. As a probabilistic model for learned features of inputs, we consider a mixture of von Mises-Fisher distributions which is known to be more expressive than Gaussian in a high dimensional space. Then, from a discriminative classifier perspective, we get a better class representative considering inter-class correlation which has not been addressed by conventional few-shot learning algorithms. We apply our method to \emph{mini}ImageNet and \emph{tiered}ImageNet datasets, and show that the proposed approach outperforms other comparable methods in few-shot classification tasks. |
| Tasks | Few-Shot Learning |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01819v1 |
| https://arxiv.org/pdf/1906.01819v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-few-shot-learning-based-on |
| Repo | |
| Framework | |
Scalable and Generalizable Social Bot Detection through Data Selection
| Title | Scalable and Generalizable Social Bot Detection through Data Selection |
| Authors | Kai-Cheng Yang, Onur Varol, Pik-Mai Hui, Filippo Menczer |
| Abstract | Efficient and reliable social bot classification is crucial for detecting information manipulation on social media. Despite rapid development, state-of-the-art bot detection models still face generalization and scalability challenges, which greatly limit their applications. In this paper we propose a framework that uses minimal account metadata, enabling efficient analysis that scales up to handle the full stream of public tweets of Twitter in real time. To ensure model accuracy, we build a rich collection of labeled datasets for training and validation. We deploy a strict validation system so that model performance on unseen datasets is also optimized, in addition to traditional cross-validation. We find that strategically selecting a subset of training data yields better model accuracy and generalization than exhaustively training on all available data. Thanks to the simplicity of the proposed model, its logic can be interpreted to provide insights into social bot characteristics. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09179v1 |
| https://arxiv.org/pdf/1911.09179v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-and-generalizable-social-bot |
| Repo | |
| Framework | |
Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study
| Title | Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study |
| Authors | Satoshi Tsutsui, Dian Zhi, Md Alimoor Reza, David Crandall, Chen Yu |
| Abstract | Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data’ that they receive. We conduct a follow-up study that investigates two additional directions. First, given that infants can quickly learn to recognize a new object without much supervision (i.e. few-shot learning), we limit the number of training images. Second, we investigate how children control the supervision signals they receive during learning based on hand manipulation of objects. Our experimental results suggest that supervision with hand manipulation is better than without hands, and the trend is consistent even when a small number of images is available. | |
| Tasks | Few-Shot Learning |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01415v1 |
| https://arxiv.org/pdf/1906.01415v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-object-manipulation-facilitates-visual |
| Repo | |
| Framework | |
Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks
| Title | Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks |
| Authors | Evyatar Illouz, Eli David, Nathan S. Netanyahu |
| Abstract | Handwriting-based gender classification is a well-researched problem that has been approached mainly by traditional machine learning techniques. In this paper, we propose a novel deep learning-based approach for this task. Specifically, we present a convolutional neural network (CNN), which performs automatic feature extraction from a given handwritten image, followed by classification of the writer’s gender. Also, we introduce a new dataset of labeled handwritten samples, in Hebrew and English, of 405 participants. Comparing the gender classification accuracy on this dataset against human examiners, our results show that the proposed deep learning-based approach is substantially more accurate than that of humans. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01816v1 |
| https://arxiv.org/pdf/1912.01816v1.pdf | |
| PWC | https://paperswithcode.com/paper/handwriting-based-gender-classification-using |
| Repo | |
| Framework | |
FutureMapping 2: Gaussian Belief Propagation for Spatial AI
| Title | FutureMapping 2: Gaussian Belief Propagation for Spatial AI |
| Authors | Andrew J. Davison, Joseph Ortiz |
| Abstract | We argue the case for Gaussian Belief Propagation (GBP) as a strong algorithmic framework for the distributed, generic and incremental probabilistic estimation we need in Spatial AI as we aim at high performance smart robots and devices which operate within the constraints of real products. Processor hardware is changing rapidly, and GBP has the right character to take advantage of highly distributed processing and storage while estimating global quantities, as well as great flexibility. We present a detailed tutorial on GBP, relating to the standard factor graph formulation used in robotics and computer vision, and give several simulation examples with code which demonstrate its properties. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.14139v1 |
| https://arxiv.org/pdf/1910.14139v1.pdf | |
| PWC | https://paperswithcode.com/paper/futuremapping-2-gaussian-belief-propagation |
| Repo | |
| Framework | |
Voice Pathology Detection Using Deep Learning: a Preliminary Study
| Title | Voice Pathology Detection Using Deep Learning: a Preliminary Study |
| Authors | Pavol Harar, Jesus B. Alonso-Hernandez, Jiri Mekyska, Zoltan Galaz, Radim Burget, Zdenek Smekal |
| Abstract | This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN). We used voice recordings of sustained vowel /a/ produced at normal pitch from German corpus Saarbruecken Voice Database (SVD). This corpus contains voice recordings and electroglottograph signals of more than 2 000 speakers. The idea behind this experiment is the use of convolutional layers in combination with recurrent Long-Short-Term-Memory (LSTM) layers on raw audio signal. Each recording was split into 64 ms Hamming windowed segments with 30 ms overlap. Our trained model achieved 71.36% accuracy with 65.04% sensitivity and 77.67% specificity on 206 validation files and 68.08% accuracy with 66.75% sensitivity and 77.89% specificity on 874 testing files. This is a promising result in favor of this approach because it is comparable to similar previously published experiment that used different methodology. Further investigation is needed to achieve the state-of-the-art results. |
| Tasks | |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05905v1 |
| https://arxiv.org/pdf/1907.05905v1.pdf | |
| PWC | https://paperswithcode.com/paper/voice-pathology-detection-using-deep-learning |
| Repo | |
| Framework | |
NeuNetS: An Automated Synthesis Engine for Neural Network Design
| Title | NeuNetS: An Automated Synthesis Engine for Neural Network Design |
| Authors | Atin Sood, Benjamin Elder, Benjamin Herta, Chao Xue, Costas Bekas, A. Cristiano I. Malossi, Debashish Saha, Florian Scheidegger, Ganesh Venkataraman, Gegi Thomas, Giovanni Mariani, Hendrik Strobelt, Horst Samulowitz, Martin Wistuba, Matteo Manica, Mihir Choudhury, Rong Yan, Roxana Istrate, Ruchir Puri, Tejaswini Pedapati |
| Abstract | Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through APIs or capability to custom train pre-built neural network architectures with customer data has made the consumption of AI by developers much simpler and resulted in broad adoption of these complex AI models. While prebuilt network models exist for certain scenarios, to try and meet the constraints that are unique to each application, AI teams need to think about developing custom neural network architectures that can meet the tradeoff between accuracy and memory footprint to achieve the tight constraints of their unique use-cases. However, only a small proportion of data science teams have the skills and experience needed to create a neural network from scratch, and the demand far exceeds the supply. In this paper, we present NeuNetS : An automated Neural Network Synthesis engine for custom neural network design that is available as part of IBM’s AI OpenScale’s product. NeuNetS is available for both Text and Image domains and can build neural networks for specific tasks in a fraction of the time it takes today with human effort, and with accuracy similar to that of human-designed AI models. |
| Tasks | |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.06261v1 |
| http://arxiv.org/pdf/1901.06261v1.pdf | |
| PWC | https://paperswithcode.com/paper/neunets-an-automated-synthesis-engine-for |
| Repo | |
| Framework | |
On Certifying Non-uniform Bound against Adversarial Attacks
| Title | On Certifying Non-uniform Bound against Adversarial Attacks |
| Authors | Chen Liu, Ryota Tomioka, Volkan Cevher |
| Abstract | This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded uniformly along all input features, we consider non-uniform bounds and use it to study the decision boundary of neural network models. We formulate our target as an optimization problem with nonlinear constraints. Then, a framework applicable for general feedforward neural networks is proposed to bound the output logits so that the relaxed problem can be solved by the augmented Lagrangian method. Our experiments show the non-uniform bounds have larger volumes than uniform ones and the geometric similarity of the non-uniform bounds gives a quantitative, data-agnostic metric of input features’ robustness. Further, compared with normal models, the robust models have even larger non-uniform bounds and better interpretability. |
| Tasks | |
| Published | 2019-03-15 |
| URL | https://arxiv.org/abs/1903.06603v3 |
| https://arxiv.org/pdf/1903.06603v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-certifying-non-uniform-bound-against |
| Repo | |
| Framework | |
Use of Artificial Intelligence to Analyse Risk in Legal Documents for a Better Decision Support
| Title | Use of Artificial Intelligence to Analyse Risk in Legal Documents for a Better Decision Support |
| Authors | Dipankar Chakrabarti, Neelam Patodia, Udayan Bhattacharya, Indranil Mitra, Satyaki Roy, Jayanta Mandi, Nandini Roy, Prasun Nandy |
| Abstract | Assessing risk for voluminous legal documents such as request for proposal; contracts is tedious and error prone. We have developed “risk-o-meter”, a framework, based on machine learning and natural language processing to review and assess risks of any legal document. Our framework uses Paragraph Vector, an unsupervised model to generate vector representation of text. This enables the framework to learn contextual relations of legal terms and generate sensible context aware embedding. The framework then feeds the vector space into a supervised classification algorithm to predict whether a paragraph belongs to a per-defined risk category or not. The framework thus extracts risk prone paragraphs. This technique efficiently overcomes the limitations of keyword-based search. We have achieved an accuracy of 91% for the risk category having the largest training dataset. This framework will help organizations optimize effort to identify risk from large document base with minimal human intervention and thus will help to have risk mitigated sustainable growth. Its machine learning capability makes it scalable to uncover relevant information from any type of document apart from legal documents, provided the library is per-populated and rich. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1912.01111v1 |
| https://arxiv.org/pdf/1912.01111v1.pdf | |
| PWC | https://paperswithcode.com/paper/use-of-artificial-intelligence-to-analyse |
| Repo | |
| Framework | |
XFake: Explainable Fake News Detector with Visualizations
| Title | XFake: Explainable Fake News Detector with Visualizations |
| Authors | Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia Hu |
| Abstract | In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility. To effectively detect and interpret the fakeness of news items, we jointly consider both attributes (e.g., speaker) and statements. Specifically, MIMIC, ATTN and PERT frameworks are designed, where MIMIC is built for attribute analysis, ATTN is for statement semantic analysis and PERT is for statement linguistic analysis. Beyond the explanations extracted from the designed frameworks, relevant supporting examples as well as visualization are further provided to facilitate the interpretation. Our implemented system is demonstrated on a real-world dataset crawled from PolitiFact, where thousands of verified political news have been collected. |
| Tasks | |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.07757v1 |
| https://arxiv.org/pdf/1907.07757v1.pdf | |
| PWC | https://paperswithcode.com/paper/xfake-explainable-fake-news-detector-with |
| Repo | |
| Framework | |
Constrained R-CNN: A general image manipulation detection model
| Title | Constrained R-CNN: A general image manipulation detection model |
| Authors | Chao Yang, Huizhou Li, Fangting Lin, Bin Jiang, Hao Zhao |
| Abstract | Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on manipulation localization and overlook manipulation classification. To address these issues, we propose a coarse-to-fine architecture named Constrained R-CNN for complete and accurate image forensics. First, the learnable manipulation feature extractor learns a unified feature representation directly from data. Second, the attention region proposal network effectively discriminates manipulated regions for the next manipulation classification and coarse localization. Then, the skip structure fuses low-level and high-level information to refine the global manipulation features. Finally, the coarse localization information guides the model to further learn the finer local features and segment out the tampered region. Experimental results show that our model achieves state-of-the-art performance. Especially, the F1 score is increased by 28.4%, 73.2%, 13.3% on the NIST16, COVERAGE, and Columbia dataset. |
| Tasks | Image Manipulation Detection |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08217v3 |
| https://arxiv.org/pdf/1911.08217v3.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-r-cnn-a-general-image |
| Repo | |
| Framework | |
Who’s responsible? Jointly quantifying the contribution of the learning algorithm and training data
| Title | Who’s responsible? Jointly quantifying the contribution of the learning algorithm and training data |
| Authors | Gal Yona, Amirata Ghorbani, James Zou |
| Abstract | A fancy learning algorithm $A$ outperforms a baseline method $B$ when they are both trained on the same data. Should $A$ get all of the credit for the improved performance or does the training data also deserve some credit? When deployed in a new setting from a different domain, however, $A$ makes more mistakes than $B$. How much of the blame should go to the learning algorithm or the training data? Such questions are becoming increasingly important and prevalent as we aim to make ML more accountable. Their answers would also help us allocate resources between algorithm design and data collection. In this paper, we formalize these questions and provide a principled Extended Shapley framework to jointly quantify the contribution of the learning algorithm and training data. Extended Shapley uniquely satisfies several natural properties that ensure equitable treatment of data and algorithm. Through experiments and theoretical analysis, we demonstrate that Extended Shapley has several important applications: 1) it provides a new metric of ML performance improvement that disentangles the influence of the data regime and the algorithm; 2) it facilitates ML accountability by properly assigning responsibility for mistakes; 3) it provides more robustness to manipulation by the ML designer. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04214v1 |
| https://arxiv.org/pdf/1910.04214v1.pdf | |
| PWC | https://paperswithcode.com/paper/whos-responsible-jointly-quantifying-the |
| Repo | |
| Framework | |
