Paper Group ANR 228
Variational Bayesian Inference for Hidden Markov Models With Multivariate Gaussian Output Distributions. On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis. Proceedings of the Workshop on Brain Analysis using COnnectivity Networks - BACON 2016. Deep Image Category Discovery using a Transferred Similarity Function. Enabling Medi …
Variational Bayesian Inference for Hidden Markov Models With Multivariate Gaussian Output Distributions
| Title | Variational Bayesian Inference for Hidden Markov Models With Multivariate Gaussian Output Distributions |
| Authors | Christian Gruhl, Bernhard Sick |
| Abstract | Hidden Markov Models (HMM) have been used for several years in many time series analysis or pattern recognitions tasks. HMM are often trained by means of the Baum-Welch algorithm which can be seen as a special variant of an expectation maximization (EM) algorithm. Second-order training techniques such as Variational Bayesian Inference (VI) for probabilistic models regard the parameters of the probabilistic models as random variables and define distributions over these distribution parameters, hence the name of this technique. VI can also bee regarded as a special case of an EM algorithm. In this article, we bring both together and train HMM with multivariate Gaussian output distributions with VI. The article defines the new training technique for HMM. An evaluation based on some case studies and a comparison to related approaches is part of our ongoing work. |
| Tasks | Bayesian Inference, Time Series, Time Series Analysis |
| Published | 2016-05-27 |
| URL | http://arxiv.org/abs/1605.08618v1 |
| http://arxiv.org/pdf/1605.08618v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-bayesian-inference-for-hidden |
| Repo | |
| Framework | |
On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis
| Title | On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis |
| Authors | James Foulds, Joseph Geumlek, Max Welling, Kamalika Chaudhuri |
| Abstract | Bayesian inference has great promise for the privacy-preserving analysis of sensitive data, as posterior sampling automatically preserves differential privacy, an algorithmic notion of data privacy, under certain conditions (Dimitrakakis et al., 2014; Wang et al., 2015). While this one posterior sample (OPS) approach elegantly provides privacy “for free,” it is data inefficient in the sense of asymptotic relative efficiency (ARE). We show that a simple alternative based on the Laplace mechanism, the workhorse of differential privacy, is as asymptotically efficient as non-private posterior inference, under general assumptions. This technique also has practical advantages including efficient use of the privacy budget for MCMC. We demonstrate the practicality of our approach on a time-series analysis of sensitive military records from the Afghanistan and Iraq wars disclosed by the Wikileaks organization. |
| Tasks | Bayesian Inference, Time Series, Time Series Analysis |
| Published | 2016-03-23 |
| URL | http://arxiv.org/abs/1603.07294v2 |
| http://arxiv.org/pdf/1603.07294v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-theory-and-practice-of-privacy |
| Repo | |
| Framework | |
Proceedings of the Workshop on Brain Analysis using COnnectivity Networks - BACON 2016
| Title | Proceedings of the Workshop on Brain Analysis using COnnectivity Networks - BACON 2016 |
| Authors | Sarah Parisot, Jonathan Passerat-Palmbach, Markus D. Schirmer, Boris Gutman |
| Abstract | Understanding brain connectivity in a network-theoretic context has shown much promise in recent years. This type of analysis identifies brain organisational principles, bringing a new perspective to neuroscience. At the same time, large public databases of connectomic data are now available. However, connectome analysis is still an emerging field and there is a crucial need for robust computational methods to fully unravelits potential. This workshop provides a platform to discuss the development of new analytic techniques; methods for evaluating and validating commonly used approaches; as well as the effects of variations in pre-processing steps. |
| Tasks | |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03363v3 |
| http://arxiv.org/pdf/1611.03363v3.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-brain-analysis |
| Repo | |
| Framework | |
Deep Image Category Discovery using a Transferred Similarity Function
| Title | Deep Image Category Discovery using a Transferred Similarity Function |
| Authors | Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira |
| Abstract | Automatically discovering image categories in unlabeled natural images is one of the important goals of unsupervised learning. However, the task is challenging and even human beings define visual categories based on a large amount of prior knowledge. In this paper, we similarly utilize prior knowledge to facilitate the discovery of image categories. We present a novel end-to-end network to map unlabeled images to categories as a clustering network. We propose that this network can be learned with contrastive loss which is only based on weak binary pair-wise constraints. Such binary constraints can be learned from datasets in other domains as transferred similarity functions, which mimic a simple knowledge transfer. We first evaluate our experiments on the MNIST dataset as a proof of concept, based on predicted similarities trained on Omniglot, showing a 99% accuracy which significantly outperforms clustering based approaches. Then we evaluate the discovery performance on Cifar-10, STL-10, and ImageNet, which achieves both state-of-the-art accuracy and shows it can be scalable to various large natural images. |
| Tasks | Omniglot, Transfer Learning |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01253v1 |
| http://arxiv.org/pdf/1612.01253v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-image-category-discovery-using-a |
| Repo | |
| Framework | |
Enabling Medical Translation for Low-Resource Languages
| Title | Enabling Medical Translation for Low-Resource Languages |
| Authors | Ahmad Musleh, Nadir Durrani, Irina Temnikova, Preslav Nakov, Stephan Vogel, Osama Alsaad |
| Abstract | We present research towards bridging the language gap between migrant workers in Qatar and medical staff. In particular, we present the first steps towards the development of a real-world Hindi-English machine translation system for doctor-patient communication. As this is a low-resource language pair, especially for speech and for the medical domain, our initial focus has been on gathering suitable training data from various sources. We applied a variety of methods ranging from fully automatic extraction from the Web to manual annotation of test data. Moreover, we developed a method for automatically augmenting the training data with synthetically generated variants, which yielded a very sizable improvement of more than 3 BLEU points absolute. |
| Tasks | Machine Translation |
| Published | 2016-10-09 |
| URL | http://arxiv.org/abs/1610.02633v1 |
| http://arxiv.org/pdf/1610.02633v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-medical-translation-for-low-resource |
| Repo | |
| Framework | |
Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches
| Title | Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches |
| Authors | Yonatan Vaizman, Katherine Ellis, Gert Lanckriet |
| Abstract | The ability to automatically recognize a person’s behavioral context can contribute to health monitoring, aging care and many other domains. Validating context recognition in-the-wild is crucial to promote practical applications that work in real-life settings. We collected over 300k minutes of sensor data with context labels from 60 subjects. Unlike previous studies, our subjects used their own personal phone, in any way that was convenient to them, and engaged in their routine in their natural environments. Unscripted behavior and unconstrained phone usage resulted in situations that are harder to recognize. We demonstrate how fusion of multi-modal sensors is important for resolving such cases. We present a baseline system, and encourage researchers to use our public dataset to compare methods and improve context recognition in-the-wild. |
| Tasks | |
| Published | 2016-09-20 |
| URL | http://arxiv.org/abs/1609.06354v4 |
| http://arxiv.org/pdf/1609.06354v4.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-detailed-human-context-in-the |
| Repo | |
| Framework | |
Overlay Text Extraction From TV News Broadcast
| Title | Overlay Text Extraction From TV News Broadcast |
| Authors | Raghvendra Kannao, Prithwijit Guha |
| Abstract | The text data present in overlaid bands convey brief descriptions of news events in broadcast videos. The process of text extraction becomes challenging as overlay text is presented in widely varying formats and often with animation effects. We note that existing edge density based methods are well suited for our application on account of their simplicity and speed of operation. However, these methods are sensitive to thresholds and have high false positive rates. In this paper, we present a contrast enhancement based preprocessing stage for overlay text detection and a parameter free edge density based scheme for efficient text band detection. The second contribution of this paper is a novel approach for multiple text region tracking with a formal identification of all possible detection failure cases. The tracking stage enables us to establish the temporal presence of text bands and their linking over time. The third contribution is the adoption of Tesseract OCR for the specific task of overlay text recognition using web news articles. The proposed approach is tested and found superior on news videos acquired from three Indian English television news channels along with benchmark datasets. |
| Tasks | Optical Character Recognition |
| Published | 2016-04-02 |
| URL | http://arxiv.org/abs/1604.00470v1 |
| http://arxiv.org/pdf/1604.00470v1.pdf | |
| PWC | https://paperswithcode.com/paper/overlay-text-extraction-from-tv-news |
| Repo | |
| Framework | |
Single Image Action Recognition using Semantic Body Part Actions
| Title | Single Image Action Recognition using Semantic Body Part Actions |
| Authors | Zhichen Zhao, Huimin Ma, Shaodi You |
| Abstract | In this paper, we propose a novel single image action recognition algorithm which is based on the idea of semantic body part actions. Unlike existing bottom up methods, we argue that the human action is a combination of meaningful body part actions. In detail, we divide human body into five parts: head, torso, arms, hands and legs. And for each of the body parts, we define several semantic body part actions, e.g., hand holding, hand waving. These semantic body part actions are strongly related to the body actions, e.g., writing, and jogging. Based on the idea, we propose a deep neural network based system: first, body parts are localized by a Semi-FCN network. Second, for each body parts, a Part Action Res-Net is used to predict semantic body part actions. And finally, we use SVM to fuse the body part actions and predict the entire body action. Experiments on two dataset: PASCAL VOC 2012 and Stanford-40 report mAP improvement from the state-of-the-art by 3.8% and 2.6% respectively. |
| Tasks | Temporal Action Localization |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04520v1 |
| http://arxiv.org/pdf/1612.04520v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-action-recognition-using |
| Repo | |
| Framework | |
Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art
| Title | Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art |
| Authors | David Hall, Pietro Perona |
| Abstract | A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded “in-the-wild” from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes), sex (2 classes), weight (3 classes) and clothing style (4 classes). There are a total of 27,454 bounding box and pose labels across 4222 tracks. This dataset is designed to train and test algorithms for fine-grained categorisation of people, it is also useful for benchmarking tracking, detection and pose estimation of pedestrians. State-of-the-art algorithms for fine-grained classification and pose estimation were tested using the dataset and the results are reported as a useful performance baseline. |
| Tasks | Pose Estimation |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06177v1 |
| http://arxiv.org/pdf/1605.06177v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-classification-of-pedestrians-in |
| Repo | |
| Framework | |
Facial Expression Classification Using Rotation Slepian-based Moment Invariants
| Title | Facial Expression Classification Using Rotation Slepian-based Moment Invariants |
| Authors | Cuiming Zou, Kit Ian Kou |
| Abstract | Rotation moment invariants have been of great interest in image processing and pattern recognition. This paper presents a novel kind of rotation moment invariants based on the Slepian functions, which were originally introduced in the method of separation of variables for Helmholtz equations. They were first proposed for time series by Slepian and his coworkers in the 1960s. Recent studies have shown that these functions have an good performance in local approximation compared to other approximation basis. Motivated by the good approximation performance, we construct the Slepian-based moments and derive the rotation invariant. We not only theoretically prove the invariance, but also discuss the experiments on real data. The proposed rotation invariants are robust to noise and yield decent performance in facial expression classification. |
| Tasks | Time Series |
| Published | 2016-06-28 |
| URL | http://arxiv.org/abs/1607.01040v1 |
| http://arxiv.org/pdf/1607.01040v1.pdf | |
| PWC | https://paperswithcode.com/paper/facial-expression-classification-using |
| Repo | |
| Framework | |
Sequential Ensemble Learning for Outlier Detection: A Bias-Variance Perspective
| Title | Sequential Ensemble Learning for Outlier Detection: A Bias-Variance Perspective |
| Authors | Shebuti Rayana, Wen Zhong, Leman Akoglu |
| Abstract | Ensemble methods for classification and clustering have been effectively used for decades, while ensemble learning for outlier detection has only been studied recently. In this work, we design a new ensemble approach for outlier detection in multi-dimensional point data, which provides improved accuracy by reducing error through both bias and variance. Although classification and outlier detection appear as different problems, their theoretical underpinnings are quite similar in terms of the bias-variance trade-off [1], where outlier detection is considered as a binary classification task with unobserved labels but a similar bias-variance decomposition of error. In this paper, we propose a sequential ensemble approach called CARE that employs a two-phase aggregation of the intermediate results in each iteration to reach the final outcome. Unlike existing outlier ensembles which solely incorporate a parallel framework by aggregating the outcomes of independent base detectors to reduce variance, our ensemble incorporates both the parallel and sequential building blocks to reduce bias as well as variance by ($i$) successively eliminating outliers from the original dataset to build a better data model on which outlierness is estimated (sequentially), and ($ii$) combining the results from individual base detectors and across iterations (parallelly). Through extensive experiments on sixteen real-world datasets mainly from the UCI machine learning repository [2], we show that CARE performs significantly better than or at least similar to the individual baselines. We also compare CARE with the state-of-the-art outlier ensembles where it also provides significant improvement when it is the winner and remains close otherwise. |
| Tasks | Outlier Detection, outlier ensembles |
| Published | 2016-09-18 |
| URL | http://arxiv.org/abs/1609.05528v1 |
| http://arxiv.org/pdf/1609.05528v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-ensemble-learning-for-outlier |
| Repo | |
| Framework | |
Online semi-parametric learning for inverse dynamics modeling
| Title | Online semi-parametric learning for inverse dynamics modeling |
| Authors | Diego Romeres, Mattia Zorzi, Raffaello Camoriano, Alessandro Chiuso |
| Abstract | This paper presents a semi-parametric algorithm for online learning of a robot inverse dynamics model. It combines the strength of the parametric and non-parametric modeling. The former exploits the rigid body dynamics equa- tion, while the latter exploits a suitable kernel function. We provide an extensive comparison with other methods from the literature using real data from the iCub humanoid robot. In doing so we also compare two different techniques, namely cross validation and marginal likelihood optimization, for estimating the hyperparameters of the kernel function. |
| Tasks | |
| Published | 2016-03-17 |
| URL | http://arxiv.org/abs/1603.05412v2 |
| http://arxiv.org/pdf/1603.05412v2.pdf | |
| PWC | https://paperswithcode.com/paper/online-semi-parametric-learning-for-inverse |
| Repo | |
| Framework | |
Crowd-sourcing NLG Data: Pictures Elicit Better Data
| Title | Crowd-sourcing NLG Data: Pictures Elicit Better Data |
| Authors | Jekaterina Novikova, Oliver Lemon, Verena Rieser |
| Abstract | Recent advances in corpus-based Natural Language Generation (NLG) hold the promise of being easily portable across domains, but require costly training data, consisting of meaning representations (MRs) paired with Natural Language (NL) utterances. In this work, we propose a novel framework for crowdsourcing high quality NLG training data, using automatic quality control measures and evaluating different MRs with which to elicit data. We show that pictorial MRs result in better NL data being collected than logic-based MRs: utterances elicited by pictorial MRs are judged as significantly more natural, more informative, and better phrased, with a significant increase in average quality ratings (around 0.5 points on a 6-point scale), compared to using the logical MRs. As the MR becomes more complex, the benefits of pictorial stimuli increase. The collected data will be released as part of this submission. |
| Tasks | Text Generation |
| Published | 2016-08-01 |
| URL | http://arxiv.org/abs/1608.00339v1 |
| http://arxiv.org/pdf/1608.00339v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-sourcing-nlg-data-pictures-elicit-1 |
| Repo | |
| Framework | |
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
| Title | Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics |
| Authors | Xin Li, Fuxin Li |
| Abstract | Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on detecting those adversarial examples by analyzing whether they come from the same distribution as the normal examples. Instead of directly training a deep neural network to detect adversarials, a much simpler approach was proposed based on statistics on outputs from convolutional layers. A cascade classifier was designed to efficiently detect adversarials. Furthermore, trained from one particular adversarial generating mechanism, the resulting classifier can successfully detect adversarials from a completely different mechanism as well. The resulting classifier is non-subdifferentiable, hence creates a difficulty for adversaries to attack by using the gradient of the classifier. After detecting adversarial examples, we show that many of them can be recovered by simply performing a small average filter on the image. Those findings should lead to more insights about the classification mechanisms in deep convolutional neural networks. |
| Tasks | |
| Published | 2016-12-22 |
| URL | http://arxiv.org/abs/1612.07767v2 |
| http://arxiv.org/pdf/1612.07767v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-detection-in-deep |
| Repo | |
| Framework | |
Big IoT and social networking data for smart cities: Algorithmic improvements on Big Data Analysis in the context of RADICAL city applications
| Title | Big IoT and social networking data for smart cities: Algorithmic improvements on Big Data Analysis in the context of RADICAL city applications |
| Authors | Evangelos Psomakelis, Fotis Aisopos, Antonios Litke, Konstantinos Tserpes, Magdalini Kardara, Pablo Martínez Campo |
| Abstract | In this paper we present a SOA (Service Oriented Architecture)-based platform, enabling the retrieval and analysis of big datasets stemming from social networking (SN) sites and Internet of Things (IoT) devices, collected by smart city applications and socially-aware data aggregation services. A large set of city applications in the areas of Participating Urbanism, Augmented Reality and Sound-Mapping throughout participating cities is being applied, resulting into produced sets of millions of user-generated events and online SN reports fed into the RADICAL platform. Moreover, we study the application of data analytics such as sentiment analysis to the combined IoT and SN data saved into an SQL database, further investigating algorithmic and configurations to minimize delays in dataset processing and results retrieval. |
| Tasks | Sentiment Analysis |
| Published | 2016-07-02 |
| URL | http://arxiv.org/abs/1607.00509v1 |
| http://arxiv.org/pdf/1607.00509v1.pdf | |
| PWC | https://paperswithcode.com/paper/big-iot-and-social-networking-data-for-smart |
| Repo | |
| Framework | |
