Paper Group ANR 670
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition. A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification. Personalized Influence Estimation Technique. Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates. Te …
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
| Title | Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition |
| Authors | Chaolong Li, Zhen Cui, Wenming Zheng, Chunyan Xu, Jian Yang |
| Abstract | Variations of human body skeletons may be considered as dynamic graphs, which are generic data representation for numerous real-world applications. In this paper, we propose a spatio-temporal graph convolution (STGC) approach for assembling the successes of local convolutional filtering and sequence learning ability of autoregressive moving average. To encode dynamic graphs, the constructed multi-scale local graph convolution filters, consisting of matrices of local receptive fields and signal mappings, are recursively performed on structured graph data of temporal and spatial domain. The proposed model is generic and principled as it can be generalized into other dynamic models. We theoretically prove the stability of STGC and provide an upper-bound of the signal transformation to be learnt. Further, the proposed recursive model can be stacked into a multi-layer architecture. To evaluate our model, we conduct extensive experiments on four benchmark skeleton-based action datasets, including the large-scale challenging NTU RGB+D. The experimental results demonstrate the effectiveness of our proposed model and the improvement over the state-of-the-art. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09834v1 |
| http://arxiv.org/pdf/1802.09834v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-graph-convolution-for |
| Repo | |
| Framework | |
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
| Title | A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification |
| Authors | Mounica Maddela, Wei Xu |
| Abstract | Current lexical simplification approaches rely heavily on heuristics and corpus level features that do not always align with human judgment. We create a human-rated word-complexity lexicon of 15,000 English words and propose a novel neural readability ranking model with a Gaussian-based feature vectorization layer that utilizes these human ratings to measure the complexity of any given word or phrase. Our model performs better than the state-of-the-art systems for different lexical simplification tasks and evaluation datasets. Additionally, we also produce SimplePPDB++, a lexical resource of over 10 million simplifying paraphrase rules, by applying our model to the Paraphrase Database (PPDB). |
| Tasks | Lexical Simplification |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05754v1 |
| http://arxiv.org/pdf/1810.05754v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-word-complexity-lexicon-and-a-neural |
| Repo | |
| Framework | |
Personalized Influence Estimation Technique
| Title | Personalized Influence Estimation Technique |
| Authors | Kumarjit Pathak, Jitin Kapila, Aasheesh Barvey |
| Abstract | Customer Satisfaction is the most important factors in the industry irrespective of domain. Key Driver Analysis is a common practice in data science to help the business to evaluate the same. Understanding key features, which influence the outcome or dependent feature, is highly important in statistical model building. This helps to eliminate not so important factors from the model to minimize noise coming from the features, which does not contribute significantly enough to explain the behavior of the dependent feature, which we want to predict. Personalized Influence Estimation is a technique introduced in this paper, which can estimate key factor influence for individual observations, which contribute most for each observations behavior pattern based on the dependent class or estimate. Observations can come from multiple business problem i.e. customers related to satisfaction study, customer related to Fraud Detection, network devices for Fault detection etc. It is highly important to understand the cause of issue at each observation level to take appropriate Individualized action at customer level or device level etc. This technique is based on joint behavior of the feature dimension for the specific observation, and relative importance of the feature to estimate impact. The technique mentioned in this paper is aimed to help organizations to understand each respondents or observations individual key contributing factor of Influence. Result of the experiment is really encouraging and able to justify key reasons for churn for majority of the sample appropriately |
| Tasks | Fault Detection, Fraud Detection |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10940v1 |
| http://arxiv.org/pdf/1805.10940v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-influence-estimation-technique |
| Repo | |
| Framework | |
Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates
| Title | Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates |
| Authors | Joo-Kyung Kim, Young-Bum Kim |
| Abstract | In domain classification for spoken dialog systems, correct detection of out-of-domain (OOD) utterances is crucial because it reduces confusion and unnecessary interaction costs between users and the systems. Previous work usually utilizes OOD detectors that are trained separately from in-domain (IND) classifiers, and confidence thresholding for OOD detection given target evaluation scores. In this paper, we introduce a neural joint learning model for domain classification and OOD detection, where dynamic class weighting is used during the model training to satisfice a given OOD false acceptance rate (FAR) while maximizing the domain classification accuracy. Evaluating on two domain classification tasks for the utterances from a large spoken dialogue system, we show that our approach significantly improves the domain classification performance with satisficing given target FARs. |
| Tasks | |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1807.00072v1 |
| http://arxiv.org/pdf/1807.00072v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-learning-of-domain-classification-and |
| Repo | |
| Framework | |
Testing Identity of Multidimensional Histograms
| Title | Testing Identity of Multidimensional Histograms |
| Authors | Ilias Diakonikolas, Daniel M. Kane, John Peebles |
| Abstract | We investigate the problem of identity testing for multidimensional histogram distributions. A distribution $p: D \rightarrow \mathbb{R}_+$, where $D \subseteq \mathbb{R}^d$, is called a $k$-histogram if there exists a partition of the domain into $k$ axis-aligned rectangles such that $p$ is constant within each such rectangle. Histograms are one of the most fundamental nonparametric families of distributions and have been extensively studied in computer science and statistics. We give the first identity tester for this problem with {\em sub-learning} sample complexity in any fixed dimension and a nearly-matching sample complexity lower bound. In more detail, let $q$ be an unknown $d$-dimensional $k$-histogram distribution in fixed dimension $d$, and $p$ be an explicitly given $d$-dimensional $k$-histogram. We want to correctly distinguish, with probability at least $2/3$, between the case that $p = q$ versus $\p-q_1 \geq \epsilon$. We design an algorithm for this hypothesis testing problem with sample complexity $O((\sqrt{k}/\epsilon^2) 2^{d/2} \log^{2.5 d}(k/\epsilon))$ that runs in sample-polynomial time. Our algorithm is robust to model misspecification, i.e., succeeds even if $q$ is only promised to be {\em close} to a $k$-histogram. Moreover, for $k = 2^{\Omega(d)}$, we show a sample complexity lower bound of $(\sqrt{k}/\epsilon^2) \cdot \Omega(\log(k)/d)^{d-1}$ when $d\geq 2$. That is, for any fixed dimension $d$, our upper and lower bounds are nearly matching. Prior to our work, the sample complexity of the $d=1$ case was well-understood, but no algorithm with sub-learning sample complexity was known, even for $d=2$. Our new upper and lower bounds have interesting conceptual implications regarding the relation between learning and testing in this setting. |
| Tasks | |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.03636v2 |
| http://arxiv.org/pdf/1804.03636v2.pdf | |
| PWC | https://paperswithcode.com/paper/testing-identity-of-multidimensional |
| Repo | |
| Framework | |
Opinion Fraud Detection via Neural Autoencoder Decision Forest
| Title | Opinion Fraud Detection via Neural Autoencoder Decision Forest |
| Authors | Manqing Dong, Lina Yao, Xianzhi Wang, Boualem Benatallah, Chaoran Huang, Xiaodong Ning |
| Abstract | Online reviews play an important role in influencing buyers’ daily purchase decisions. However, fake and meaningless reviews, which cannot reflect users’ genuine purchase experience and opinions, widely exist on the Web and pose great challenges for users to make right choices. Therefore,it is desirable to build a fair model that evaluates the quality of products by distinguishing spamming reviews. We present an end-to-end trainable unified model to leverage the appealing properties from Autoencoder and random forest. A stochastic decision tree model is implemented to guide the global parameter learning process. Extensive experiments were conducted on a large Amazon review dataset. The proposed model consistently outperforms a series of compared methods. |
| Tasks | Fraud Detection |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03379v1 |
| http://arxiv.org/pdf/1805.03379v1.pdf | |
| PWC | https://paperswithcode.com/paper/opinion-fraud-detection-via-neural |
| Repo | |
| Framework | |
Streaming Active Learning Strategies for Real-Life Credit Card Fraud Detection: Assessment and Visualization
| Title | Streaming Active Learning Strategies for Real-Life Credit Card Fraud Detection: Assessment and Visualization |
| Authors | Fabirzio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, Gianluca Bontempi |
| Abstract | Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data is peculiar because they are obtained in a streaming fashion, they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated to the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature. |
| Tasks | Active Learning, Fraud Detection |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1804.07481v1 |
| http://arxiv.org/pdf/1804.07481v1.pdf | |
| PWC | https://paperswithcode.com/paper/streaming-active-learning-strategies-for-real |
| Repo | |
| Framework | |
Image Segmentation using Unsupervised Watershed Algorithm with an Over-segmentation Reduction Technique
| Title | Image Segmentation using Unsupervised Watershed Algorithm with an Over-segmentation Reduction Technique |
| Authors | Ravimal Bandara |
| Abstract | Image segmentation is the process of partitioning an image into meaningful segments. The meaning of the segments is subjective due to the definition of homogeneity is varied based on the users perspective hence the automation of the segmentation is challenging. Watershed is a popular segmentation technique which assumes topographic map in an image, with the brightness of each pixel representing its height, and finds the lines that run along the tops of ridges. The results from the algorithm typically suffer from over segmentation due to the lack of knowledge of the objects being classified. This paper presents an approach to reduce the over segmentation of watershed algorithm by assuming that the different adjacent segments of an object have similar color distribution. The approach demonstrates an improvement over conventional watershed algorithm. |
| Tasks | Semantic Segmentation |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.03908v1 |
| http://arxiv.org/pdf/1810.03908v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-segmentation-using-unsupervised |
| Repo | |
| Framework | |
Inferring Missing Categorical Information in Noisy and Sparse Web Markup
| Title | Inferring Missing Categorical Information in Noisy and Sparse Web Markup |
| Authors | Nicolas Tempelmeier, Elena Demidova, Stefan Dietze |
| Abstract | Embedded markup of Web pages has seen widespread adoption throughout the past years driven by standards such as RDFa and Microdata and initiatives such as schema.org, where recent studies show an adoption by 39% of all Web pages already in 2016. While this constitutes an important information source for tasks such as Web search, Web page classification or knowledge graph augmentation, individual markup nodes are usually sparsely described and often lack essential information. For instance, from 26 million nodes describing events within the Common Crawl in 2016, 59% of nodes provide less than six statements and only 257,000 nodes (0.96%) are typed with more specific event subtypes. Nevertheless, given the scale and diversity of Web markup data, nodes that provide missing information can be obtained from the Web in large quantities, in particular for categorical properties. Such data constitutes potential training data for inferring missing information to significantly augment sparsely described nodes. In this work, we introduce a supervised approach for inferring missing categorical properties in Web markup. Our experiments, conducted on properties of events and movies, show a performance of 79% and 83% F1 score correspondingly, significantly outperforming existing baselines. |
| Tasks | |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00446v1 |
| http://arxiv.org/pdf/1803.00446v1.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-missing-categorical-information-in |
| Repo | |
| Framework | |
Kiki Kills: Identifying Dangerous Challenge Videos from Social Media
| Title | Kiki Kills: Identifying Dangerous Challenge Videos from Social Media |
| Authors | Nupur Baghel, Yaman Kumar, Paavini Nanda, Rajiv Ratn Shah, Debanjan Mahata, Roger Zimmermann |
| Abstract | There has been upsurge in the number of people participating in challenges made popular through social media channels. One of the examples of such a challenge is the Kiki Challenge, in which people step out of their moving cars and dance to the tunes of the song, ‘Kiki, Do you love me?'. Such an action makes the people taking the challenge prone to accidents and can also create nuisance for the others traveling on the road. In this work, we introduce the prevalence of such challenges in social media and show how the machine learning community can aid in preventing dangerous situations triggered by them by developing models that can distinguish between dangerous and non-dangerous challenge videos. Towards this objective, we release a new dataset namely MIDAS-KIKI dataset, consisting of manually annotated dangerous and non-dangerous Kiki challenge videos. Further, we train a deep learning model to identify dangerous and non-dangerous videos, and report our results. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00399v2 |
| http://arxiv.org/pdf/1812.00399v2.pdf | |
| PWC | https://paperswithcode.com/paper/kiki-kills-identifying-dangerous-challenge |
| Repo | |
| Framework | |
First Experiments with a Flexible Infrastructure for Normative Reasoning
| Title | First Experiments with a Flexible Infrastructure for Normative Reasoning |
| Authors | Christoph Benzmüller, Xavier Parent |
| Abstract | A flexible infrastructure for normative reasoning is outlined. A small-scale demonstrator version of the envisioned system has been implemented in the proof assistant Isabelle/HOL by utilising the first authors universal logical reasoning approach based on shallow semantical embeddings in meta-logic HOL. The need for such a flexible reasoning infrastructure is motivated and illustrated with a contrary-to-duty example scenario selected from the General Data Protection Regulation. |
| Tasks | |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.02929v1 |
| http://arxiv.org/pdf/1804.02929v1.pdf | |
| PWC | https://paperswithcode.com/paper/first-experiments-with-a-flexible |
| Repo | |
| Framework | |
Fast inference of deep neural networks in FPGAs for particle physics
| Title | Fast inference of deep neural networks in FPGAs for particle physics |
| Authors | Javier Duarte, Song Han, Philip Harris, Sergo Jindariani, Edward Kreinar, Benjamin Kreis, Jennifer Ngadiuba, Maurizio Pierini, Ryan Rivera, Nhan Tran, Zhenbin Wu |
| Abstract | Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA hardware has only just begun. FPGA-based trigger and data acquisition (DAQ) systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. We develop a package based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns. |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.06913v3 |
| http://arxiv.org/pdf/1804.06913v3.pdf | |
| PWC | https://paperswithcode.com/paper/fast-inference-of-deep-neural-networks-in |
| Repo | |
| Framework | |
Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
| Title | Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection |
| Authors | Björn Barz, Erik Rodner, Yanira Guanche Garcia, Joachim Denzler |
| Abstract | Automatic detection of anomalies in space- and time-varying measurements is an important tool in several fields, e.g., fraud detection, climate analysis, or healthcare monitoring. We present an algorithm for detecting anomalous regions in multivariate spatio-temporal time-series, which allows for spotting the interesting parts in large amounts of data, including video and text data. In opposition to existing techniques for detecting isolated anomalous data points, we propose the “Maximally Divergent Intervals” (MDI) framework for unsupervised detection of coherent spatial regions and time intervals characterized by a high Kullback-Leibler divergence compared with all other data given. In this regard, we define an unbiased Kullback-Leibler divergence that allows for ranking regions of different size and show how to enable the algorithm to run on large-scale data sets in reasonable time using an interval proposal technique. Experiments on both synthetic and real data from various domains, such as climate analysis, video surveillance, and text forensics, demonstrate that our method is widely applicable and a valuable tool for finding interesting events in different types of data. |
| Tasks | Anomaly Detection, Fraud Detection, Time Series |
| Published | 2018-04-19 |
| URL | https://arxiv.org/abs/1804.07091v2 |
| https://arxiv.org/pdf/1804.07091v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-regions-of-maximal-divergence-for |
| Repo | |
| Framework | |
Relating Zipf’s law to textual information
| Title | Relating Zipf’s law to textual information |
| Authors | Weibing Deng, Armen E. Allahverdyan |
| Abstract | Zipf’s law is the main regularity of quantitative linguistics. Despite of many works devoted to foundations of this law, it is still unclear whether it is only a statistical regularity, or it has deeper relations with information-carrying structures of the text. This question relates to that of distinguishing a meaningful text (written in an unknown system) from a meaningless set of symbols that mimics statistical features of a text. Here we contribute to resolving these questions by comparing features of the first half of a text (from the beginning to the middle) to its second half. This comparison can uncover hidden effects, because the halves have the same values of many parameters (style, genre, author’s vocabulary {\it etc}). In all studied texts we saw that for the first half Zipf’s law applies from smaller ranks than in the second half, i.e. the law applies better to the first half. Also, words that hold Zipf’s law in the first half are distributed more homogeneously over the text. These features do allow to distinguish a meaningful text from a random sequence of words. Our findings correlate with a number of textual characteristics that hold in most cases we studied: the first half is lexically richer, has longer and less repetitive words, more and shorter sentences, more punctuation signs and more paragraphs. These differences between the halves indicate on a higher hierarchic level of text organization that so far went unnoticed in text linguistics. They relate the validity of Zipf’s law to textual information. A complete description of this effect requires new models, though one existing model can account for some of its aspects. |
| Tasks | |
| Published | 2018-09-22 |
| URL | http://arxiv.org/abs/1809.08399v1 |
| http://arxiv.org/pdf/1809.08399v1.pdf | |
| PWC | https://paperswithcode.com/paper/relating-zipfs-law-to-textual-information |
| Repo | |
| Framework | |
TxPI-u: A Resource for Personality Identification of Undergraduates
| Title | TxPI-u: A Resource for Personality Identification of Undergraduates |
| Authors | Gabriela Ramírez-de-la-Rosa, Esaú Villatoro-Tello, Héctor Jiménez-Salazar |
| Abstract | Resources such as labeled corpora are necessary to train automatic models within the natural language processing (NLP) field. Historically, a large number of resources regarding a broad number of problems are available mostly in English. One of such problems is known as Personality Identification where based on a psychological model (e.g. The Big Five Model), the goal is to find the traits of a subject’s personality given, for instance, a text written by the same subject. In this paper we introduce a new corpus in Spanish called Texts for Personality Identification (TxPI). This corpus will help to develop models to automatically assign a personality trait to an author of a text document. Our corpus, TxPI-u, contains information of 416 Mexican undergraduate students with some demographics information such as, age, gender, and the academic program they are enrolled. Finally, as an additional contribution, we present a set of baselines to provide a comparison scheme for further research. |
| Tasks | |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07977v1 |
| http://arxiv.org/pdf/1806.07977v1.pdf | |
| PWC | https://paperswithcode.com/paper/txpi-u-a-resource-for-personality |
| Repo | |
| Framework | |
