Paper Group ANR 371
Gendered Conversation in a Social Game-Streaming Platform. Statistical Pattern Recognition for Driving Styles Based on Bayesian Probability and Kernel Density Estimation. Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions. ECAT: Event Capture Annotation Tool. Variational Gaussian Process Auto-Encoder for Ordinal Predi …
Gendered Conversation in a Social Game-Streaming Platform
| Title | Gendered Conversation in a Social Game-Streaming Platform |
| Authors | Supun Nakandala, Giovanni Luca Ciampaglia, Norman Makoto Su, Yong-Yeol Ahn |
| Abstract | Online social media and games are increasingly replacing offline social activities. Social media is now an indispensable mode of communication; online gaming is not only a genuine social activity but also a popular spectator sport. With support for anonymity and larger audiences, online interaction shrinks social and geographical barriers. Despite such benefits, social disparities such as gender inequality persist in online social media. In particular, online gaming communities have been criticized for persistent gender disparities and objectification. As gaming evolves into a social platform, persistence of gender disparity is a pressing question. Yet, there are few large-scale, systematic studies of gender inequality and objectification in social gaming platforms. Here we analyze more than one billion chat messages from Twitch, a social game-streaming platform, to study how the gender of streamers is associated with the nature of conversation. Using a combination of computational text analysis methods, we show that gendered conversation and objectification is prevalent in chats. Female streamers receive significantly more objectifying comments while male streamers receive more game-related comments. This difference is more pronounced for popular streamers. There also exists a large number of users who post only on female or male streams. Employing a neural vector-space embedding (paragraph vector) method, we analyze gendered chat messages and create prediction models that (i) identify the gender of streamers based on messages posted in the channel and (ii) identify the gender a viewer prefers to watch based on their chat messages. Our findings suggest that disparities in social game-streaming platforms is a nuanced phenomenon that involves the gender of streamers as well as those who produce gendered and game-related conversation. |
| Tasks | |
| Published | 2016-11-20 |
| URL | http://arxiv.org/abs/1611.06459v2 |
| http://arxiv.org/pdf/1611.06459v2.pdf | |
| PWC | https://paperswithcode.com/paper/gendered-conversation-in-a-social-game |
| Repo | |
| Framework | |
Statistical Pattern Recognition for Driving Styles Based on Bayesian Probability and Kernel Density Estimation
| Title | Statistical Pattern Recognition for Driving Styles Based on Bayesian Probability and Kernel Density Estimation |
| Authors | Wenshuo Wang, Junqiang Xi, Xiaohan Li |
| Abstract | Driving styles have a great influence on vehicle fuel economy, active safety, and drivability. To recognize driving styles of path-tracking behaviors for different divers, a statistical pattern-recognition method is developed to deal with the uncertainty of driving styles or characteristics based on probability density estimation. First, to describe driver path-tracking styles, vehicle speed and throttle opening are selected as the discriminative parameters, and a conditional kernel density function of vehicle speed and throttle opening is built, respectively, to describe the uncertainty and probability of two representative driving styles, e.g., aggressive and normal. Meanwhile, a posterior probability of each element in feature vector is obtained using full Bayesian theory. Second, a Euclidean distance method is involved to decide to which class the driver should be subject instead of calculating the complex covariance between every two elements of feature vectors. By comparing the Euclidean distance between every elements in feature vector, driving styles are classified into seven levels ranging from low normal to high aggressive. Subsequently, to show benefits of the proposed pattern-recognition method, a cross-validated method is used, compared with a fuzzy logic-based pattern-recognition method. The experiment results show that the proposed statistical pattern-recognition method for driving styles based on kernel density estimation is more efficient and stable than the fuzzy logic-based method. |
| Tasks | Density Estimation |
| Published | 2016-06-03 |
| URL | http://arxiv.org/abs/1606.01284v1 |
| http://arxiv.org/pdf/1606.01284v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-pattern-recognition-for-driving |
| Repo | |
| Framework | |
Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
| Title | Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions |
| Authors | Qiyang Zhao, Lewis D Griffin |
| Abstract | Many deep Convolutional Neural Networks (CNN) make incorrect predictions on adversarial samples obtained by imperceptible perturbations of clean samples. We hypothesize that this is caused by a failure to suppress unusual signals within network layers. As remedy we propose the use of Symmetric Activation Functions (SAF) in non-linear signal transducer units. These units suppress signals of exceptional magnitude. We prove that SAF networks can perform classification tasks to arbitrary precision in a simplified situation. In practice, rather than use SAFs alone, we add them into CNNs to improve their robustness. The modified CNNs can be easily trained using popular strategies with the moderate training load. Our experiments on MNIST and CIFAR-10 show that the modified CNNs perform similarly to plain ones on clean samples, and are remarkably more robust against adversarial and nonsense samples. |
| Tasks | |
| Published | 2016-03-16 |
| URL | http://arxiv.org/abs/1603.05145v1 |
| http://arxiv.org/pdf/1603.05145v1.pdf | |
| PWC | https://paperswithcode.com/paper/suppressing-the-unusual-towards-robust-cnns |
| Repo | |
| Framework | |
ECAT: Event Capture Annotation Tool
| Title | ECAT: Event Capture Annotation Tool |
| Authors | Tuan Do, Nikhil Krishnaswamy, James Pustejovsky |
| Abstract | This paper introduces the Event Capture Annotation Tool (ECAT), a user-friendly, open-source interface tool for annotating events and their participants in video, capable of extracting the 3D positions and orientations of objects in video captured by Microsoft’s Kinect(R) hardware. The modeling language VoxML (Pustejovsky and Krishnaswamy, 2016) underlies ECAT’s object, program, and attribute representations, although ECAT uses its own spec for explicit labeling of motion instances. The demonstration will show the tool’s workflow and the options available for capturing event-participant relations and browsing visual data. Mapping ECAT’s output to VoxML will also be addressed. |
| Tasks | |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01247v1 |
| http://arxiv.org/pdf/1610.01247v1.pdf | |
| PWC | https://paperswithcode.com/paper/ecat-event-capture-annotation-tool |
| Repo | |
| Framework | |
Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units
| Title | Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units |
| Authors | Stefanos Eleftheriadis, Ognjen Rudovic, Marc P. Deisenroth, Maja Pantic |
| Abstract | We address the task of simultaneous feature fusion and modeling of discrete ordinal outputs. We propose a novel Gaussian process(GP) auto-encoder modeling approach. In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the original features. Inference is performed in a novel variational framework, where the recovered latent representations are further constrained by the ordinal output labels. In this way, we seamlessly integrate the ordinal structure in the learned manifold, while attaining robust fusion of the input features. We demonstrate the representation abilities of our model on benchmark datasets from machine learning and affect analysis. We further evaluate the model on the tasks of feature fusion and joint ordinal prediction of facial action units. Our experiments demonstrate the benefits of the proposed approach compared to the state of the art. |
| Tasks | |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04664v2 |
| http://arxiv.org/pdf/1608.04664v2.pdf | |
| PWC | https://paperswithcode.com/paper/variational-gaussian-process-auto-encoder-for |
| Repo | |
| Framework | |
Feature Selection for Regression Problems Based on the Morisita Estimator of Intrinsic Dimension
| Title | Feature Selection for Regression Problems Based on the Morisita Estimator of Intrinsic Dimension |
| Authors | Jean Golay, Michael Leuenberger, Mikhail Kanevski |
| Abstract | Data acquisition, storage and management have been improved, while the key factors of many phenomena are not well known. Consequently, irrelevant and redundant features artificially increase the size of datasets, which complicates learning tasks, such as regression. To address this problem, feature selection methods have been proposed. This paper introduces a new supervised filter based on the Morisita estimator of intrinsic dimension. It can identify relevant features and distinguish between redundant and irrelevant information. Besides, it offers a clear graphical representation of the results, and it can be easily implemented in different programming languages. Comprehensive numerical experiments are conducted using simulated datasets characterized by different levels of complexity, sample size and noise. The suggested algorithm is also successfully tested on a selection of real world applications and compared with RReliefF using extreme learning machine. In addition, a new measure of feature relevance is presented and discussed. |
| Tasks | Feature Selection |
| Published | 2016-01-31 |
| URL | http://arxiv.org/abs/1602.00216v6 |
| http://arxiv.org/pdf/1602.00216v6.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selection-for-regression-problems |
| Repo | |
| Framework | |
Resource Allocation with Population Dynamics
| Title | Resource Allocation with Population Dynamics |
| Authors | Jonathan Epperlein, Jakub Marecek |
| Abstract | Many analyses of resource-allocation problems employ simplistic models of the population. Using the example of a resource-allocation problem of Marecek et al. [arXiv:1406.7639], we introduce rather a general behavioural model, where the evolution of a heterogeneous population of agents is governed by a Markov chain. Still, we are able to show that the distribution of agents across resources converges in distribution, for suitable means of information provision, under certain assumptions. The model and proof techniques may have wider applicability. |
| Tasks | |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03458v1 |
| http://arxiv.org/pdf/1604.03458v1.pdf | |
| PWC | https://paperswithcode.com/paper/resource-allocation-with-population-dynamics |
| Repo | |
| Framework | |
Detecting Affordances by Visuomotor Simulation
| Title | Detecting Affordances by Visuomotor Simulation |
| Authors | Wolfram Schenck, Hendrik Hasenbein, Ralf Möller |
| Abstract | The term “affordance” denotes the behavioral meaning of objects. We propose a cognitive architecture for the detection of affordances in the visual modality. This model is based on the internal simulation of movement sequences. For each movement step, the resulting sensory state is predicted by a forward model, which in turn triggers the generation of a new (simulated) motor command by an inverse model. Thus, a series of mental images in the sensory and in the motor domain is evoked. Starting from a real sensory state, a large number of such sequences is simulated in parallel. Final affordance detection is based on the generated motor commands. We apply this model to a real-world mobile robot which is faced with obstacle arrangements some of which are passable (corridor) and some of which are not (dead ends). The robot’s task is to detect the right affordance (“pass-through-able” or “non-pass-through-able”). The required internal models are acquired in a hierarchical training process. Afterwards, the robotic agent is able to distinguish reliably between corridors and dead ends. This real-world result enhances the validity of the proposed mental simulation approach. In addition, we compare several key factors in the simulation process regarding performance and efficiency. |
| Tasks | |
| Published | 2016-11-01 |
| URL | http://arxiv.org/abs/1611.00274v1 |
| http://arxiv.org/pdf/1611.00274v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-affordances-by-visuomotor |
| Repo | |
| Framework | |
dMath: Distributed Linear Algebra for DL
| Title | dMath: Distributed Linear Algebra for DL |
| Authors | Steven Eliuk, Cameron Upright, Hars Vardhan, Stephen Walsh, Trevor Gale |
| Abstract | The paper presents a parallel math library, dMath, that demonstrates leading scaling when using intranode, internode, and hybrid-parallelism for deep learning (DL). dMath provides easy-to-use distributed primitives and a variety of domain-specific algorithms including matrix multiplication, convolutions, and others allowing for rapid development of scalable applications like deep neural networks (DNNs). Persistent data stored in GPU memory and advanced memory management techniques avoid costly transfers between host and device. dMath delivers performance, portability, and productivity to its specific domain of support. |
| Tasks | |
| Published | 2016-11-19 |
| URL | http://arxiv.org/abs/1611.07819v1 |
| http://arxiv.org/pdf/1611.07819v1.pdf | |
| PWC | https://paperswithcode.com/paper/dmath-distributed-linear-algebra-for-dl |
| Repo | |
| Framework | |
Dual Teaching: A Practical Semi-supervised Wrapper Method
| Title | Dual Teaching: A Practical Semi-supervised Wrapper Method |
| Authors | Fuqaing Liu, Chenwei Deng, Fukun Bi, Yiding Yang |
| Abstract | Semi-supervised wrapper methods are concerned with building effective supervised classifiers from partially labeled data. Though previous works have succeeded in some fields, it is still difficult to apply semi-supervised wrapper methods to practice because the assumptions those methods rely on tend to be unrealistic in practice. For practical use, this paper proposes a novel semi-supervised wrapper method, Dual Teaching, whose assumptions are easy to set up. Dual Teaching adopts two external classifiers to estimate the false positives and false negatives of the base learner. Only if the recall of every external classifier is greater than zero and the sum of the precision is greater than one, Dual Teaching will train a base learner from partially labeled data as effectively as the fully-labeled-data-trained classifier. The effectiveness of Dual Teaching is proved in both theory and practice. |
| Tasks | |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.03981v1 |
| http://arxiv.org/pdf/1611.03981v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-teaching-a-practical-semi-supervised |
| Repo | |
| Framework | |
Adaptive Deep Pyramid Matching for Remote Sensing Scene Classification
| Title | Adaptive Deep Pyramid Matching for Remote Sensing Scene Classification |
| Authors | Qingshan Liu, Renlong Hang, Huihui Song, Fuping Zhu, Javier Plaza, Antonio Plaza |
| Abstract | Convolutional neural networks (CNNs) have attracted increasing attention in the remote sensing community. Most CNNs only take the last fully-connected layers as features for the classification of remotely sensed images, discarding the other convolutional layer features which may also be helpful for classification purposes. In this paper, we propose a new adaptive deep pyramid matching (ADPM) model that takes advantage of the features from all of the convolutional layers for remote sensing image classification. To this end, the optimal fusing weights for different convolutional layers are learned from the data itself. In remotely sensed scenes, the objects of interest exhibit different scales in distinct scenes, and even a single scene may contain objects with different sizes. To address this issue, we select the CNN with spatial pyramid pooling (SPP-net) as the basic deep network, and further construct a multi-scale ADPM model to learn complementary information from multi-scale images. Our experiments have been conducted using two widely used remote sensing image databases, and the results show that the proposed method significantly improves the performance when compared to other state-of-the-art methods. |
| Tasks | Image Classification, Remote Sensing Image Classification, Scene Classification |
| Published | 2016-11-11 |
| URL | http://arxiv.org/abs/1611.03589v1 |
| http://arxiv.org/pdf/1611.03589v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-deep-pyramid-matching-for-remote |
| Repo | |
| Framework | |
Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation
| Title | Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation |
| Authors | Yan Xu, Ran Jia, Lili Mou, Ge Li, Yunchuan Chen, Yangyang Lu, Zhi Jin |
| Abstract | Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolutional neural networks or recurrent networks). They may fail to explore the potential representation space in different abstraction levels. In this paper, we propose deep recurrent neural networks (DRNNs) for relation classification to tackle this challenge. Further, we propose a data augmentation method by leveraging the directionality of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an F1-score of 86.1%, outperforming previous state-of-the-art recorded results. |
| Tasks | Data Augmentation, Relation Classification |
| Published | 2016-01-14 |
| URL | http://arxiv.org/abs/1601.03651v2 |
| http://arxiv.org/pdf/1601.03651v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-relation-classification-by-deep |
| Repo | |
| Framework | |
Collaborative Filtering with Side Information: a Gaussian Process Perspective
| Title | Collaborative Filtering with Side Information: a Gaussian Process Perspective |
| Authors | Hyunjik Kim, Xiaoyu Lu, Seth Flaxman, Yee Whye Teh |
| Abstract | We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explicitly model user-item similarities, we formulate the GP in a way that allows the incorporation of low-rank matrix factorisation, arriving at our model, the Tucker Gaussian Process (TGP). Consequently, TGP generalises classical Bayesian matrix factorisation models, and goes beyond them to give a natural and elegant method for incorporating side information, giving enhanced predictive performance for CF problems. Moreover we show that it is a novel model for regression, especially well-suited to grid-structured data and problems where the dependence on covariates is close to being separable. |
| Tasks | |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07025v3 |
| http://arxiv.org/pdf/1605.07025v3.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-filtering-with-side-information |
| Repo | |
| Framework | |
General models for rational cameras and the case of two-slit projections
| Title | General models for rational cameras and the case of two-slit projections |
| Authors | Matthew Trager, Bernd Sturmfels, John Canny, Martial Hebert, Jean Ponce |
| Abstract | The rational camera model recently introduced in [19] provides a general methodology for studying abstract nonlinear imaging systems and their multi-view geometry. This paper builds on this framework to study “physical realizations” of rational cameras. More precisely, we give an explicit account of the mapping between between physical visual rays and image points (missing in the original description), which allows us to give simple analytical expressions for direct and inverse projections. We also consider “primitive” camera models, that are orbits under the action of various projective transformations, and lead to a general notion of intrinsic parameters. The methodology is general, but it is illustrated concretely by an in-depth study of two-slit cameras, that we model using pairs of linear projections. This simple analytical form allows us to describe models for the corresponding primitive cameras, to introduce intrinsic parameters with a clear geometric meaning, and to define an epipolar tensor characterizing two-view correspondences. In turn, this leads to new algorithms for structure from motion and self-calibration. |
| Tasks | Calibration |
| Published | 2016-12-04 |
| URL | http://arxiv.org/abs/1612.01160v4 |
| http://arxiv.org/pdf/1612.01160v4.pdf | |
| PWC | https://paperswithcode.com/paper/general-models-for-rational-cameras-and-the |
| Repo | |
| Framework | |
Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention
| Title | Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention |
| Authors | Théodore Bluche, Jérôme Louradour, Ronaldo Messina |
| Abstract | We present an attention-based model for end-to-end handwriting recognition. Our system does not require any segmentation of the input paragraph. The model is inspired by the differentiable attention models presented recently for speech recognition, image captioning or translation. The main difference is the covert and overt attention, implemented as a multi-dimensional LSTM network. Our principal contribution towards handwriting recognition lies in the automatic transcription without a prior segmentation into lines, which was crucial in previous approaches. To the best of our knowledge this is the first successful attempt of end-to-end multi-line handwriting recognition. We carried out experiments on the well-known IAM Database. The results are encouraging and bring hope to perform full paragraph transcription in the near future. |
| Tasks | Image Captioning, Speech Recognition |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03286v3 |
| http://arxiv.org/pdf/1604.03286v3.pdf | |
| PWC | https://paperswithcode.com/paper/scan-attend-and-read-end-to-end-handwritten |
| Repo | |
| Framework | |
