May 6, 2019

2898 words 14 mins read

Paper Group ANR 329

Towards Blended Reactive Planning and Acting using Behavior Trees. Object Boundary Detection and Classification with Image-level Labels. Multilinear Grammar: Ranks and Interpretations. Deep Multi-Task Learning with Shared Memory. Lexical-Morphological Modeling for Legal Text Analysis. Enhancing Genetic Algorithms using Multi Mutations. ODE - Augmen …

Towards Blended Reactive Planning and Acting using Behavior Trees


Title	Towards Blended Reactive Planning and Acting using Behavior Trees
Authors	Michele Colledanchise, Diogo Almeida, Petter Ögren
Abstract	In this paper, we show how a planning algorithm can be used to automatically create and update a Behavior Tree (BT), controlling a robot in a dynamic environment. The planning part of the algorithm is based on the idea of back chaining. Starting from a goal condition we iteratively select actions to achieve that goal, and if those actions have unmet preconditions, they are extended with actions to achieve them in the same way. The fact that BTs are inherently modular and reactive makes the proposed solution blend acting and planning in a way that enables the robot to efficiently react to external disturbances. If an external agent undoes an action the robot reexecutes it without re-planning, and if an external agent helps the robot, it skips the corresponding actions, again without replanning. We illustrate our approach in two different robotics scenarios.
Tasks
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00230v2
PDF	http://arxiv.org/pdf/1611.00230v2.pdf
PWC	https://paperswithcode.com/paper/towards-blended-reactive-planning-and-acting
Repo
Framework

Object Boundary Detection and Classification with Image-level Labels


Title	Object Boundary Detection and Classification with Image-level Labels
Authors	Jing Yu Koh, Wojciech Samek, Klaus-Robert Müller, Alexander Binder
Abstract	Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pixel-level annotations are not available, performing it in an almost zero-shot manner by relying on conventional whole image neural net classifiers that were trained using large bounding boxes. Our method performs the following two steps at test time. Firstly it predicts the class labels by applying the trained whole image network to the test images. Secondly, it computes pixel-wise scores from the obtained predictions by applying backprop gradients as well as recent visualization algorithms such as deconvolution and layer-wise relevance propagation. We show that high pixel-wise scores are indicative for the location of semantic boundaries, which suggests that the semantic boundary problem can be approached without using edge labels during the training phase.
Tasks	Boundary Detection, Edge Detection
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09187v3
PDF	http://arxiv.org/pdf/1606.09187v3.pdf
PWC	https://paperswithcode.com/paper/object-boundary-detection-and-classification
Repo
Framework

Multilinear Grammar: Ranks and Interpretations


Title	Multilinear Grammar: Ranks and Interpretations
Authors	Dafydd Gibbon, Sascha Griffiths
Abstract	Multilinear Grammar provides a framework for integrating the many different syntagmatic structures of language into a coherent semiotically based Rank Interpretation Architecture, with default linear grammars at each rank. The architecture defines a Sui Generis Condition on ranks, from discourse through utterance and phrasal structures to the word, with its sub-ranks of morphology and phonology. Each rank has unique structures and its own semantic-pragmatic and prosodic-phonetic interpretation models. Default computational models for each rank are proposed, based on a Procedural Plausibility Condition: incremental processing in linear time with finite working memory. We suggest that the Rank Interpretation Architecture and its multilinear properties provide systematic design features of human languages, contrasting with unordered lists of key properties or single structural properties at one rank, such as recursion, which have previously been been put forward as language design features. The framework provides a realistic background for the gradual development of complexity in the phylogeny and ontogeny of language, and clarifies a range of challenges for the evaluation of realistic linguistic theories and applications. The empirical objective of the paper is to demonstrate unique multilinear properties at each rank and thereby motivate the Multilinear Grammar and Rank Interpretation Architecture framework as a coherent approach to capturing the complexity of human languages in the simplest possible way.
Tasks
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05511v5
PDF	http://arxiv.org/pdf/1609.05511v5.pdf
PWC	https://paperswithcode.com/paper/multilinear-grammar-ranks-and-interpretations
Repo
Framework

Deep Multi-Task Learning with Shared Memory


Title	Deep Multi-Task Learning with Shared Memory
Authors	Pengfei Liu, Xipeng Qiu, Xuanjing Huang
Abstract	Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural model with an external memory, which is shared by several tasks. Experiments on two groups of text classification tasks show that our proposed architectures can improve the performance of a task with the help of other related tasks.
Tasks	Multi-Task Learning, Text Classification
Published	2016-09-23
URL	http://arxiv.org/abs/1609.07222v1
PDF	http://arxiv.org/pdf/1609.07222v1.pdf
PWC	https://paperswithcode.com/paper/deep-multi-task-learning-with-shared-memory
Repo
Framework

Lexical-Morphological Modeling for Legal Text Analysis


Title	Lexical-Morphological Modeling for Legal Text Analysis
Authors	Danilo S. Carvalho, Minh-Tien Nguyen, Tran Xuan Chien, Minh Le Nguyen
Abstract	In the context of the Competition on Legal Information Extraction/Entailment (COLIEE), we propose a method comprising the necessary steps for finding relevant documents to a legal question and deciding on textual entailment evidence to provide a correct answer. The proposed method is based on the combination of several lexical and morphological characteristics, to build a language model and a set of features for Machine Learning algorithms. We provide a detailed study on the proposed method performance and failure cases, indicating that it is competitive with state-of-the-art approaches on Legal Information Retrieval and Question Answering, while not needing extensive training data nor depending on expert produced knowledge. The proposed method achieved significant results in the competition, indicating a substantial level of adequacy for the tasks addressed.
Tasks	Information Retrieval, Language Modelling, Natural Language Inference, Question Answering
Published	2016-09-03
URL	http://arxiv.org/abs/1609.00799v1
PDF	http://arxiv.org/pdf/1609.00799v1.pdf
PWC	https://paperswithcode.com/paper/lexical-morphological-modeling-for-legal-text
Repo
Framework

Enhancing Genetic Algorithms using Multi Mutations


Title	Enhancing Genetic Algorithms using Multi Mutations
Authors	Ahmad B. A. Hassanat, Esra’a Alkafaween, Nedal A. Al-Nawaiseh, Mohammad A. Abbadi, Mouhammd Alkasassbeh, Mahmoud B. Alhasanat
Abstract	Mutation is one of the most important stages of the genetic algorithm because of its impact on the exploration of global optima, and to overcome premature convergence. There are many types of mutation, and the problem lies in selection of the appropriate type, where the decision becomes more difficult and needs more trial and error. This paper investigates the use of more than one mutation operator to enhance the performance of genetic algorithms. Novel mutation operators are proposed, in addition to two selection strategies for the mutation operators, one of which is based on selecting the best mutation operator and the other randomly selects any operator. Several experiments on some Travelling Salesman Problems (TSP) were conducted to evaluate the proposed methods, and these were compared to the well-known exchange mutation and rearrangement mutation. The results show the importance of some of the proposed methods, in addition to the significant enhancement of the genetic algorithm’s performance, particularly when using more than one mutation operator.
Tasks
Published	2016-02-26
URL	http://arxiv.org/abs/1602.08313v2
PDF	http://arxiv.org/pdf/1602.08313v2.pdf
PWC	https://paperswithcode.com/paper/enhancing-genetic-algorithms-using-multi
Repo
Framework

ODE - Augmented Training Improves Anomaly Detection in Sensor Data from Machines


Title	ODE - Augmented Training Improves Anomaly Detection in Sensor Data from Machines
Authors	Mohit Yadav, Pankaj Malhotra, Lovekesh Vig, K Sriram, Gautam Shroff
Abstract	Machines of all kinds from vehicles to industrial equipment are increasingly instrumented with hundreds of sensors. Using such data to detect anomalous behaviour is critical for safety and efficient maintenance. However, anomalies occur rarely and with great variety in such systems, so there is often insufficient anomalous data to build reliable detectors. A standard approach to mitigate this problem is to use one class methods relying only on data from normal behaviour. Unfortunately, even these approaches are more likely to fail in the scenario of a dynamical system with manual control input(s). Normal behaviour in response to novel control input(s) might look very different to the learned detector which may be incorrectly detected as anomalous. In this paper, we address this issue by modelling time-series via Ordinary Differential Equations (ODE) and utilising such an ODE model to simulate the behaviour of dynamical systems under varying control inputs. The available data is then augmented with data generated from the ODE, and the anomaly detector is retrained on this augmented dataset. Experiments demonstrate that ODE-augmented training data allows better coverage of possible control input(s) and results in learning more accurate distinctions between normal and anomalous behaviour in time-series.
Tasks	Anomaly Detection, Time Series
Published	2016-05-05
URL	http://arxiv.org/abs/1605.01534v1
PDF	http://arxiv.org/pdf/1605.01534v1.pdf
PWC	https://paperswithcode.com/paper/ode-augmented-training-improves-anomaly
Repo
Framework

Deep Deformation Network for Object Landmark Localization


Title	Deep Deformation Network for Object Landmark Localization
Authors	Xiang Yu, Feng Zhou, Manmohan Chandraker
Abstract	We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects. The hallmarks of DDN are its incorporation of geometric constraints within a convolutional neural network (CNN) framework, ease and efficiency of training, as well as generality of application. A novel shape basis network (SBN) forms the first stage of the cascade, whereby landmarks are initialized by combining the benefits of CNN features and a learned shape basis to reduce the complexity of the highly nonlinear pose manifold. In the second stage, a point transformer network (PTN) estimates local deformation parameterized as thin-plate spline transformation for a finer refinement. Our framework does not incorporate either handcrafted features or part connectivity, which enables an end-to-end shape prediction pipeline during both training and testing. In contrast to prior cascaded networks for landmark localization that learn a mapping from feature space to landmark locations, we demonstrate that the regularization induced through geometric priors in the DDN makes it easier to train, yet produces superior results. The efficacy and generality of the architecture is demonstrated through state-of-the-art performances on several benchmarks for multiple tasks such as facial landmark localization, human body pose estimation and bird part localization.
Tasks	Face Alignment, Pose Estimation
Published	2016-05-03
URL	http://arxiv.org/abs/1605.01014v2
PDF	http://arxiv.org/pdf/1605.01014v2.pdf
PWC	https://paperswithcode.com/paper/deep-deformation-network-for-object-landmark
Repo
Framework

Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions


Title	Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions
Authors	Vincent Drouard, Radu Horaud, Antoine Deleforge, Silèye Ba, Georgios Evangelidis
Abstract	Head-pose estimation has many applications, such as social event analysis, human-robot and human-computer interaction, driving assistance, and so forth. Head-pose estimation is challenging because it must cope with changing illumination conditions, variabilities in face orientation and in appearance, partial occlusions of facial landmarks, as well as bounding-box-to-face alignment errors. We propose tu use a mixture of linear regressions with partially-latent output. This regression method learns to map high-dimensional feature vectors (extracted from bounding boxes of faces) onto the joint space of head-pose angles and bounding-box shifts, such that they are robustly predicted in the presence of unobservable phenomena. We describe in detail the mapping method that combines the merits of unsupervised manifold learning techniques and of mixtures of regressions. We validate our method with three publicly available datasets and we thoroughly benchmark four variants of the proposed algorithm with several state-of-the-art head-pose estimation methods.
Tasks	Face Alignment, Head Pose Estimation, Pose Estimation
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09732v3
PDF	http://arxiv.org/pdf/1603.09732v3.pdf
PWC	https://paperswithcode.com/paper/robust-head-pose-estimation-based-on
Repo
Framework

Video Summarization in a Multi-View Camera Network


Title	Video Summarization in a Multi-View Camera Network
Authors	Rameswar Panda, Abir Das, Amit K. Roy-Chowdhury
Abstract	While most existing video summarization approaches aim to extract an informative summary of a single video, we propose a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space. We learn the embedding by minimizing an objective function that has two terms: one due to intra-view correlations and another due to inter-view correlations across the multiple views. The solution can be obtained directly by solving one Eigen-value problem that is linear in the number of multi-view videos. We then employ a sparse representative selection approach over the learned embedding space to summarize the multi-view videos. Experimental results on several benchmark datasets demonstrate that our proposed approach clearly outperforms the state-of-the-art.
Tasks	Video Summarization
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00310v1
PDF	http://arxiv.org/pdf/1608.00310v1.pdf
PWC	https://paperswithcode.com/paper/video-summarization-in-a-multi-view-camera
Repo
Framework

Kinematic-Layout-aware Random Forests for Depth-based Action Recognition


Title	Kinematic-Layout-aware Random Forests for Depth-based Action Recognition
Authors	Seungryul Baek, Zhiyuan Shi, Masato Kawade, Tae-Kyun Kim
Abstract	In this paper, we tackle the problem of 24 hours-monitoring patient actions in a ward such as “stretching an arm out of the bed”, “falling out of the bed”, where temporal movements are subtle or significant. In the concerned scenarios, the relations between scene layouts and body kinematics (skeletons) become important cues to recognize actions; however they are hard to be secured at a testing stage. To address this problem, we propose a kinematic-layout-aware random forest which takes into account the kinematic-layout (\ie layout and skeletons), to maximize the discriminative power of depth image appearance. We integrate the kinematic-layout in the split criteria of random forests to guide the learning process by 1) determining the switch to either the depth appearance or the kinematic-layout information, and 2) implicitly closing the gap between two distributions obtained by the kinematic-layout and the appearance, when the kinematic-layout appears useful. The kinematic-layout information is not required for the test data, thus called “privileged information prior”. The proposed method has also been testified in cross-view settings, by the use of view-invariant features and enforcing the consistency among synthetic-view data. Experimental evaluations on our new dataset PATIENT, CAD-60 and UWA3D (multiview) demonstrate that our method outperforms various state-of-the-arts.
Tasks	Temporal Action Localization
Published	2016-07-23
URL	http://arxiv.org/abs/1607.06972v3
PDF	http://arxiv.org/pdf/1607.06972v3.pdf
PWC	https://paperswithcode.com/paper/kinematic-layout-aware-random-forests-for
Repo
Framework

Simplified Boardgames


Title	Simplified Boardgames
Authors	Jakub Kowalski, Jakub Sutowicz, Marek Szykuła
Abstract	We formalize Simplified Boardgames language, which describes a subclass of arbitrary board games. The language structure is based on the regular expressions, which makes the rules easily machine-processable while keeping the rules concise and fairly human-readable.
Tasks	Board Games
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02645v2
PDF	http://arxiv.org/pdf/1606.02645v2.pdf
PWC	https://paperswithcode.com/paper/simplified-boardgames
Repo
Framework

Bayesian Inference of Recursive Sequences of Group Activities from Tracks


Title	Bayesian Inference of Recursive Sequences of Group Activities from Tracks
Authors	Ernesto Brau, Colin Dawson, Alfredo Carrillo, David Sidi, Clayton T. Morrison
Abstract	We present a probabilistic generative model for inferring a description of coordinated, recursively structured group activities at multiple levels of temporal granularity based on observations of individuals’ trajectories. The model accommodates: (1) hierarchically structured groups, (2) activities that are temporally and compositionally recursive, (3) component roles assigning different subactivity dynamics to subgroups of participants, and (4) a nonparametric Gaussian Process model of trajectories. We present an MCMC sampling framework for performing joint inference over recursive activity descriptions and assignment of trajectories to groups, integrating out continuous parameters. We demonstrate the model’s expressive power in several simulated and complex real-world scenarios from the VIRAT and UCLA Aerial Event video data sets.
Tasks	Bayesian Inference
Published	2016-04-24
URL	http://arxiv.org/abs/1604.06970v1
PDF	http://arxiv.org/pdf/1604.06970v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-inference-of-recursive-sequences-of
Repo
Framework

Robust mixture of experts modeling using the $t$ distribution


Title	Robust mixture of experts modeling using the $t$ distribution
Authors	Faicel Chamroukhi
Abstract	Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification, and clustering. For regression and cluster analyses of continuous data, MoE usually use normal experts following the Gaussian distribution. However, for a set of data containing a group or groups of observations with heavy tails or atypical observations, the use of normal experts is unsuitable and can unduly affect the fit of the MoE model. We introduce a robust MoE modeling using the $t$ distribution. The proposed $t$ MoE (TMoE) deals with these issues regarding heavy-tailed and noisy data. We develop a dedicated expectation-maximization (EM) algorithm to estimate the parameters of the proposed model by monotonically maximizing the observed data log-likelihood. We describe how the presented model can be used in prediction and in model-based clustering of regression data. The proposed model is validated on numerical experiments carried out on simulated data, which show the effectiveness and the robustness of the proposed model in terms of modeling non-linear regression functions as well as in model-based clustering. Then, it is applied to the real-world data of tone perception for musical data analysis, and the one of temperature anomalies for the analysis of climate change data. The obtained results show the usefulness of the TMoE model for practical applications.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1701.07429v1
PDF	http://arxiv.org/pdf/1701.07429v1.pdf
PWC	https://paperswithcode.com/paper/robust-mixture-of-experts-modeling-using-the-1
Repo
Framework

Trilaminar Multiway Reconstruction Tree for Efficient Large Scale Structure from Motion


Title	Trilaminar Multiway Reconstruction Tree for Efficient Large Scale Structure from Motion
Authors	Kun Sun, Wenbing Tao
Abstract	Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM). In this paper, we propose a unified framework to divide the image set into clusters suitable for reconstruction as well as find multiple reliable and stable starting points. Image partitioning performs in two steps. First, some small image groups are selected at places with high image density, and then all the images are clustered according to their optimal reconstruction paths to these image groups. This promises that the scene is always reconstructed from dense places to sparse areas, which can reduce error accumulation when images have weak overlap. To enable faster speed, images outside the selected group in each cluster are further divided to achieve a greater degree of parallelism. Experiments show that our method achieves significant speedup, higher accuracy and better completeness.
Tasks
Published	2016-12-21
URL	http://arxiv.org/abs/1612.07153v1
PDF	http://arxiv.org/pdf/1612.07153v1.pdf
PWC	https://paperswithcode.com/paper/trilaminar-multiway-reconstruction-tree-for
Repo
Framework