October 20, 2019

2979 words 14 mins read

Paper Group ANR 39

Starting Movement Detection of Cyclists Using Smart Devices. Optimization Design of Decentralized Control for Complex Decentralized Systems. Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models. Subsampling MCMC - An introduction for the survey statistician. GroundNet: Monocular Ground Plane Normal Estimation with Geomet …

Starting Movement Detection of Cyclists Using Smart Devices


Title	Starting Movement Detection of Cyclists Using Smart Devices
Authors	Maarten Bieshaar, Malte Depping, Jan Schneegans, Bernhard Sick
Abstract	In near future, vulnerable road users (VRUs) such as cyclists and pedestrians will be equipped with smart devices and wearables which are capable to communicate with intelligent vehicles and other traffic participants. Road users are then able to cooperate on different levels, such as in cooperative intention detection for advanced VRU protection. Smart devices can be used to detect intentions, e.g., an occluded cyclist intending to cross the road, to warn vehicles of VRUs, and prevent potential collisions. This article presents a human activity recognition approach to detect the starting movement of cyclists wearing smart devices. We propose a novel two-stage feature selection procedure using a score specialized for robust starting detection reducing the false positive detections and leading to understandable and interpretable features. The detection is modelled as a classification problem and realized by means of a machine learning classifier. We introduce an auxiliary class, that models starting movements and allows to integrate early movement indicators, i.e., body part movements indicating future behaviour. In this way we improve the robustness and reduce the detection time of the classifier. Our empirical studies with real-world data originating from experiments which involve 49 test subjects and consists of 84 starting motions show that we are able to detect the starting movements early. Our approach reaches an F1-score of 67 % within 0.33 s after the first movement of the bicycle wheel. Investigations concerning the device wearing location show that for devices worn in the trouser pocket the detector has less false detections and detects starting movements faster on average. We found that we can further improve the results when we train distinct classifiers for different wearing locations.
Tasks	Activity Recognition, Feature Selection, Human Activity Recognition
Published	2018-08-08
URL	http://arxiv.org/abs/1808.04449v1
PDF	http://arxiv.org/pdf/1808.04449v1.pdf
PWC	https://paperswithcode.com/paper/starting-movement-detection-of-cyclists-using
Repo
Framework

Optimization Design of Decentralized Control for Complex Decentralized Systems


Title	Optimization Design of Decentralized Control for Complex Decentralized Systems
Authors	Ying Huang, Jiyang Dai, Chen Peng
Abstract	A new method is developed to deal with the problem that a complex decentralized control system needs to keep centralized control performance. The systematic procedure emphasizes quickly finding the decentralized subcontrollers that matching the closed-loop performance and robustness characteristics of the centralized controller, which is featured by the fact that GA is used to optimize the design of centralized H-infinity controller K(s) and decentralized engine subcontroller KT(s), and that only one interface variable needs to satisfy decentralized control system requirement according to the proposed selection principle. The optimization design is motivated by the implementation issues where it is desirable to reduce the time in trial and error process and accurately find the best decentralized subcontrollers. The method is applied to decentralized control system design for a short takeoff and landing fighter. By comparing the simulation results of the decentralized control system with those of the centralized control system, the target of the decentralized control attains the performance and robustness of centralized control is validated.
Tasks
Published	2018-09-03
URL	http://arxiv.org/abs/1809.00596v1
PDF	http://arxiv.org/pdf/1809.00596v1.pdf
PWC	https://paperswithcode.com/paper/optimization-design-of-decentralized-control
Repo
Framework

Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models


Title	Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models
Authors	Takashi Wada, Tomoharu Iwata
Abstract	We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as an input. The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages. The other parameters, i.e. word embeddings and linear transformation between hidden states and outputs, are specific to each language. The shared LSTMs can capture the common sentence structure among all languages. Accordingly, word embeddings of each language are mapped into a common latent space, making it possible to measure the similarity of words across multiple languages. We evaluate the quality of the cross-lingual word embeddings on a word alignment task. Our experiments demonstrate that our model can obtain cross-lingual embeddings of much higher quality than existing unsupervised models when only a small amount of monolingual data (i.e. 50k sentences) are available, or the domains of monolingual data are different across languages.
Tasks	Word Alignment, Word Embeddings
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02306v1
PDF	http://arxiv.org/pdf/1809.02306v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-cross-lingual-word-embedding-by
Repo
Framework

Subsampling MCMC - An introduction for the survey statistician


Title	Subsampling MCMC - An introduction for the survey statistician
Authors	Matias Quiroz, Mattias Villani, Robert Kohn, Minh-Ngoc Tran, Khue-Dung Dang
Abstract	The rapid development of computing power and efficient Markov Chain Monte Carlo (MCMC) simulation algorithms have revolutionized Bayesian statistics, making it a highly practical inference method in applied work. However, MCMC algorithms tend to be computationally demanding, and are particularly slow for large datasets. Data subsampling has recently been suggested as a way to make MCMC methods scalable on massively large data, utilizing efficient sampling schemes and estimators from the survey sampling literature. These developments tend to be unknown by many survey statisticians who traditionally work with non-Bayesian methods, and rarely use MCMC. Our article explains the idea of data subsampling in MCMC by reviewing one strand of work, Subsampling MCMC, a so called pseudo-marginal MCMC approach to speeding up MCMC through data subsampling. The review is written for a survey statistician without previous knowledge of MCMC methods since our aim is to motivate survey sampling experts to contribute to the growing Subsampling MCMC literature.
Tasks
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08409v4
PDF	http://arxiv.org/pdf/1807.08409v4.pdf
PWC	https://paperswithcode.com/paper/subsampling-mcmc-an-introduction-for-the
Repo
Framework

GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency


Title	GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
Authors	Yunze Man, Xinshuo Weng, Xi Li, Kris Kitani
Abstract	We focus on estimating the 3D orientation of the ground plane from a single image. We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and depth estimates. Specifically, our proposed model, GroundNet, first estimates the depth and surface normal in two separate streams, from which two ground plane normals are then computed deterministically. To leverage the geometric correlation between depth and normal, we propose to add a consistency loss on top of the computed ground plane normals. In addition, a ground segmentation stream is used to isolate the ground regions so that we can selectively back-propagate parameter updates through only the ground regions in the image. Our method achieves the top-ranked performance on ground plane normal estimation and horizon line detection on the real-world outdoor datasets of ApolloScape and KITTI, improving the performance of previous art by up to 17.7% relatively.
Tasks	Semantic Segmentation
Published	2018-11-17
URL	https://arxiv.org/abs/1811.07222v4
PDF	https://arxiv.org/pdf/1811.07222v4.pdf
PWC	https://paperswithcode.com/paper/groundnet-segmentation-aware-monocular-ground
Repo
Framework

Exploring Emoji Usage and Prediction Through a Temporal Variation Lens


Title	Exploring Emoji Usage and Prediction Through a Temporal Variation Lens
Authors	Francesco Barbieri, Luis Marujo, Pradeep Karuturi, William Brendel, Horacio Saggion
Abstract	The frequent use of Emojis on social media platforms has created a new form of multimodal social interaction. Developing methods for the study and representation of emoji semantics helps to improve future multimodal communication systems. In this paper, we explore the usage and semantics of emojis over time. We compare emoji embeddings trained on a corpus of different seasons and show that some emojis are used differently depending on the time of the year. Moreover, we propose a method to take into account the time information for emoji prediction systems, outperforming state-of-the-art systems. We show that, using the time information, the accuracy of some emojis can be significantly improved.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00731v1
PDF	http://arxiv.org/pdf/1805.00731v1.pdf
PWC	https://paperswithcode.com/paper/exploring-emoji-usage-and-prediction-through
Repo
Framework

Single Index Latent Variable Models for Network Topology Inference


Title	Single Index Latent Variable Models for Network Topology Inference
Authors	Jonathan Mei, José M. F. Moura
Abstract	A semi-parametric, non-linear regression model in the presence of latent variables is applied towards learning network graph structure. These latent variables can correspond to unmodeled phenomena or unmeasured agents in a complex system of interacting entities. This formulation jointly estimates non-linearities in the underlying data generation, the direct interactions between measured entities, and the indirect effects of unmeasured processes on the observed data. The learning is posed as regularized empirical risk minimization. Details of the algorithm for learning the model are outlined. Experiments demonstrate the performance of the learned model on real data.
Tasks	Latent Variable Models
Published	2018-06-28
URL	http://arxiv.org/abs/1807.00002v1
PDF	http://arxiv.org/pdf/1807.00002v1.pdf
PWC	https://paperswithcode.com/paper/single-index-latent-variable-models-for
Repo
Framework

Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers


Title	Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers
Authors	Eunbyung Park, Alexander C. Berg
Abstract	This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learning, the resulting networks train significantly faster. We demonstrate this approach on top of the high performance tracking approaches: tracking-by-detection based MDNet and the correlation based CREST. Experimental results on standard benchmarks, OTB2015 and VOT2016, show that our meta-learned versions of both trackers improve speed, accuracy, and robustness.
Tasks	Meta-Learning
Published	2018-01-09
URL	http://arxiv.org/abs/1801.03049v2
PDF	http://arxiv.org/pdf/1801.03049v2.pdf
PWC	https://paperswithcode.com/paper/meta-tracker-fast-and-robust-online
Repo
Framework

Learning in Integer Latent Variable Models with Nested Automatic Differentiation


Title	Learning in Integer Latent Variable Models with Nested Automatic Differentiation
Authors	Daniel Sheldon, Kevin Winner, Debora Sujono
Abstract	We develop nested automatic differentiation (AD) algorithms for exact inference and learning in integer latent variable models. Recently, Winner, Sujono, and Sheldon showed how to reduce marginalization in a class of integer latent variable models to evaluating a probability generating function which contains many levels of nested high-order derivatives. We contribute faster and more stable AD algorithms for this challenging problem and a novel algorithm to compute exact gradients for learning. These contributions lead to significantly faster and more accurate learning algorithms, and are the first AD algorithms whose running time is polynomial in the number of levels of nesting.
Tasks	Latent Variable Models
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03207v1
PDF	http://arxiv.org/pdf/1806.03207v1.pdf
PWC	https://paperswithcode.com/paper/learning-in-integer-latent-variable-models
Repo
Framework

Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder


Title	Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
Authors	Guy Lorberbom, Andreea Gane, Tommi Jaakkola, Tamir Hazan
Abstract	Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an $\arg \max$ operation and is non-differentiable. In contrast to previous works which resort to softmax-based relaxations, we propose to optimize it directly by applying the direct loss minimization approach. Our proposal extends naturally to structured discrete latent variable models when evaluating the $\arg \max$ operation is tractable. We demonstrate empirically the effectiveness of the direct loss minimization technique in variational autoencoders with both unstructured and structured discrete latent variables.
Tasks	Latent Variable Models
Published	2018-06-07
URL	https://arxiv.org/abs/1806.02867v5
PDF	https://arxiv.org/pdf/1806.02867v5.pdf
PWC	https://paperswithcode.com/paper/direct-optimization-through-arg-max-for
Repo
Framework

Separability is not the best goal for machine learning


Title	Separability is not the best goal for machine learning
Authors	Wlodzislaw Duch
Abstract	Neural networks use their hidden layers to transform input data into linearly separable data clusters, with a linear or a perceptron type output layer making the final projection on the line perpendicular to the discriminating hyperplane. For complex data with multimodal distributions this transformation is difficult to learn. Projection on $k\geq 2$ line segments is the simplest extension of linear separability, defining much easier goal for the learning process. Simple problems are 2-separable, but problems with inherent complex logic may be solved in a simple way by $k$-separable projections. The difficulty of learning non-linear data distributions is shifted to separation of line intervals, simplifying the transformation of data by hidden network layers. For classification of difficult Boolean problems, such as the parity problem, linear projection combined with \ksep is sufficient and provides a powerful new target for learning. More complex targets may also be defined, changing the goal of learning from linear discrimination to creation of data distributions that can easily be handled by specialized models selected to analyze output distributions. This approach can replace many layers of transformation required by deep learning models.
Tasks
Published	2018-07-08
URL	http://arxiv.org/abs/1807.02873v1
PDF	http://arxiv.org/pdf/1807.02873v1.pdf
PWC	https://paperswithcode.com/paper/separability-is-not-the-best-goal-for-machine
Repo
Framework

Simulation Study on a New Peer Review Approach


Title	Simulation Study on a New Peer Review Approach
Authors	Albert Steppi, Jinchan Qu, Minjing Tao, Tingting Zhao, Xiaodong Pang, Jinfeng Zhang
Abstract	The increasing volume of scientific publications and grant proposals has generated an unprecedentedly high workload to scientific communities. Consequently, review quality has been decreasing and review outcomes have become less correlated with the real merits of the papers and proposals. A novel distributed peer review (DPR) approach has recently been proposed to address these issues. The new approach assigns principal investigators (PIs) who submitted proposals (or papers) to the same program as reviewers. Each PI reviews and ranks a small number (such as seven) of other PIs’ proposals. The individual rankings are then used to estimate a global ranking of all proposals using the Modified Borda Count (MBC). In this study, we perform simulation studies to investigate several parameters important for the decision making when adopting this new approach. We also propose a new method called Concordance Index-based Global Ranking (CIGR) to estimate global ranking from individual rankings. An efficient simulated annealing algorithm is designed to search the optimal Concordance Index (CI). Moreover, we design a new balanced review assignment procedure, which can result in significantly better performance for both MBC and CIGR methods. We found that CIGR performs better than MBC when the review quality is relatively high. As review quality and review difficulty are tightly correlated, we constructed a boundary in the space of review quality vs review difficulty that separates the CIGR-superior and MBC-superior regions. Finally, we propose a multi-stage DPR strategy based on CIGR, which has the potential to substantially improve the overall review performance while reducing the review workload.
Tasks	Decision Making
Published	2018-06-11
URL	https://arxiv.org/abs/1806.08663v3
PDF	https://arxiv.org/pdf/1806.08663v3.pdf
PWC	https://paperswithcode.com/paper/simulation-study-on-a-new-peer-review
Repo
Framework

Primal-Dual Wasserstein GAN


Title	Primal-Dual Wasserstein GAN
Authors	Mevlana Gemici, Zeynep Akata, Max Welling
Abstract	We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for building latent variable models of the data distribution based on the primal and the dual formulations of the optimal transport (OT) problem. We utilize the primal formulation to learn a flexible inference mechanism and to create an optimal approximate coupling between the data distribution and the generative model. In order to learn the generative model, we use the dual formulation and train the decoder adversarially through a critic network that is regularized by the approximate coupling obtained from the primal. Unlike previous methods that violate various properties of the optimal critic, we regularize the norm and the direction of the gradients of the critic function. Our model shares many of the desirable properties of auto-encoding models in terms of mode coverage and latent structure, while avoiding their undesirable averaging properties, e.g. their inability to capture sharp visual features when modeling real images. We compare our algorithm with several other generative modeling techniques that utilize Wasserstein distances on Frechet Inception Distance (FID) and Inception Scores (IS).
Tasks	Latent Variable Models
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09575v1
PDF	http://arxiv.org/pdf/1805.09575v1.pdf
PWC	https://paperswithcode.com/paper/primal-dual-wasserstein-gan
Repo
Framework

Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models


Title	Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models
Authors	Anton Mallasto, Søren Hauberg, Aasa Feragen
Abstract	Latent variable models (LVMs) learn probabilistic models of data manifolds lying in an \emph{ambient} Euclidean space. In a number of applications, a priori known spatial constraints can shrink the ambient space into a considerably smaller manifold. Additionally, in these applications the Euclidean geometry might induce a suboptimal similarity measure, which could be improved by choosing a different metric. Euclidean models ignore such information and assign probability mass to data points that can never appear as data, and vastly different likelihoods to points that are similar under the desired metric. We propose the wrapped Gaussian process latent variable model (WGPLVM), that extends Gaussian process latent variable models to take values strictly on a given ambient Riemannian manifold, making the model blind to impossible data points. This allows non-linear, probabilistic inference of low-dimensional Riemannian submanifolds from data. Our evaluation on diverse datasets show that we improve performance on several tasks, including encoding, visualization and uncertainty quantification.
Tasks	Latent Variable Models
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09122v2
PDF	http://arxiv.org/pdf/1805.09122v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-riemannian-submanifold-learning
Repo
Framework

Learning Sparse Latent Representations with the Deep Copula Information Bottleneck


Title	Learning Sparse Latent Representations with the Deep Copula Information Bottleneck
Authors	Aleksander Wieczorek, Mario Wieser, Damian Murezzan, Volker Roth
Abstract	Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information bottleneck method, leads to disentanglement of the features in the latent space. Building on that, we show how this transformation translates to sparsity of the latent space in the new model. We evaluate our method on artificial and real data.
Tasks	Latent Variable Models, Representation Learning
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06216v2
PDF	http://arxiv.org/pdf/1804.06216v2.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-latent-representations-with
Repo
Framework