722 Hits in 3.0 sec

A Continuous Grasp Representation for the Imitation Learning of Grasps on Humanoid Robots

Martin Minh Thong Do
Based on the representation a framework is proposed which enables the robot to observe human grasping, learn grasp representations, and infer executable grasping actions.  ...  Models and methods are presented which enable a humanoid robot to learn reusable, adaptive grasping skills. Mechanisms and principles in human grasp behavior are studied.  ...  For the target pose, it is assumed that the object to be grasped is annotated with suitable grasp poses and contact positions 7.5 .  ... 
doi:10.5445/ir/1000047789 fatcat:3v2ylnibkvfmhirgvdcorumhqq

Learning Grasping Possibilities for Artifacts: Dimensions, Weights and Distributional Semantics [chapter]

Irene Russo, Irene De Felice
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015  
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant.  ...  We are particularly grateful to Manuela Cherchi, Erika Ibba, Anna De Santis, Giuseppe Casu, Jessica Ladu, Ilaria Del Rio, Elisa Virdis, Gino Castangia for their annotation work.  ...  Annotation scheme and corpus The scheme, described in (Di Bari et al., 2013) , specifies different attributes for the categories target, modifier and appraisal group. A target is usually a noun.  ... 
doi:10.4000/books.aaccademia.1546 fatcat:42j6mlvuavaj3psff3adymnvb4

Toward mapping pragmatic impairment of autism spectrum disorder individuals through the development of a corpus of spoken Japanese

Sumi Kato, Kazuaki Hanawa, Vo Phuong Linh, Manabu Saito, Ryuichi Iimura, Kentaro Inui, Kazuhiko Nakamura, Mitsuru Kikuchi
2022 PLoS ONE  
The aim of this research is to present a model of annotation scheme development and corpus construction to efficiently visualize and quantify for statistical investigation occurrences of PI, which enables  ...  To elucidate the whole picture of this impairment, an approach from a multifaceted perspective fusing those factors is necessary.  ...  Such a corpus, with a systematically multilayered and elaborated annotation scheme grounded in the theoretical framework of SFL, does not exist in previous studies.  ... 
doi:10.1371/journal.pone.0264204 pmid:35213580 pmcid:PMC8880787 fatcat:r4pnnxwihnfglgfcceyowv6zlu

Robot grasping by exploiting compliance and environmental constraints

Clemens Eppner, Technische Universität Berlin, Technische Universität Berlin, Oliver Brock
Grasping is a crucial skill for any autonomous system that needs to alter the physical world.  ...  We view hand compliance as an enabler for local adaptability in the grasping process that does not require explicit reasoning or planning.  ...  Controllers for reaching and grasping have been learned by approximating the Q-function with a multilayer perceptron (Lampe and Riedmiller, 2013) .  ... 
doi:10.14279/depositonce-8896 fatcat:2pncbuw7s5ccvoem746qoogwe4

Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation [article]

François Plesse, Alexandru Ginsca, Bertrand Delezoide, Françoise Prêteux
2018 arXiv   pre-print
A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world.  ...  For this, we propose a framework that makes use of semantic knowledge and estimates the relevance of object pairs during both training and test phases.  ...  Furthermore, we present a novel relevance prediction scheme that evaluates how important a given object pair is to annotate.  ... 
arXiv:1805.10802v1 fatcat:3a6cqivkanbirpssu6hkw32aca

Multimodal Attention Branch Network for Perspective-Free Sentence Generation [article]

Aly Magassouba and Komei Sugiura and Hisashi Kawai
2019 arXiv   pre-print
In this paper, we address the automatic sentence generation of fetching instructions for domestic service robots.  ...  We evaluated our approach, which outperforms the state-of-the-art method on a standard metrics.  ...  Additionally, we plan to apply the Multi-ABN on a fully communicative DSR scheme that couples sentence generation and natural language comprehension for fetching tasks.  ... 
arXiv:1909.05664v1 fatcat:wpvrdmtdafbibieoknwo6aoioq

Perspectives on algorithmic normativities: engineers, objects, activities

Jérémy Grosman, Tyler Reigeluth
2019 Big Data & Society  
This contribution aims at proposing a framework for articulating different kinds of "normativities" that are and can be attributed to "algorithmic systems."  ...  The norm expresses a technical scheme's becoming as it mutates through, but also resists, inventions.  ...  Acknowledgement We would like to thank our friends and colleagues Nathan Devos and Franc¸ois Thoreau for discussions and criticisms, the two anonymous reviewers that made very productive critiques and  ... 
doi:10.1177/2053951719858742 fatcat:ik6xjetinna5joy2nsph6c6fie

Research on PLSA Model based Semantic Image Analysis: A Systematic Review

Dongping Tian
2018 Journal of Information Hiding and Multimedia Signal Processing  
Finally, this paper is ended with a summary of some important conclusions and several potential research directions for semantic image analysis in the near future.  ...  So the current paper, to begin with, elaborates the basic principles of the PLSA model, followed by summarizes PLSA with applications to image annotation, image retrieval, image classification and several  ...  Also, the author thanks Professor Zhongzhi Shi for stimulating discussions and helpful hints. This  ... 
dblp:journals/jihmsp/Tian18b fatcat:jbhuva4bq5akdldkdkba3fseda

ISACCO: a corpus for investigating spoken and written language development in Italian school–age children

Dominique Brunato, Felice Dell'Orletta
2016 Italian Journal of Computational Linguistics  
Written retellings were manually annotated with a typology of errors belonging to three different linguistic levels.  ...  Publisher Accademia University Press Printed version Number of pages: 63-76 Electronic reference Dominique Brunato and Felice Dell'Orletta, "ISACCO: a corpus for investigating spoken and written language  ...  Acknowledgments We would like to thank the headmaster of the primary school "Vasco Morroni" of Ghezzano (Pisa), the teachers and all the children taking part in this research for their contribution.  ... 
doi:10.4000/ijcol.356 fatcat:s4v4pneud5fjpfwv6ih7j3c53m

A Blended System for Data-Driven Learning of English for Specific Purposes

Hengbin Yan
2022 International Journal of Emerging Technologies in Learning (iJET)  
Built on a flexible plug-in architecture, the system utilizes state-of-the-art NLP tools for efficient multilayered linguistic annotation and indexing, made query-able through a user-friendly web interface  ...  interfaces for ESP learning, have limited their application in a broader range of scenarios such as blended language learning.  ...  GD20CWY15), and the Bilingual Cognition and Development Lab, Center for Linguistics and Applied Linguistics, Guangdong University of Foreign Studies (Grant No. BCD20202).  ... 
doi:10.3991/ijet.v17i12.29653 doaj:5c24f1b37a9c45259f6cf6a9286aa5f0 fatcat:baekeqrpcndebbgs22r3hulth4

2021 Index IEEE Transactions on Cognitive and Developmental Systems Vol. 13

2021 IEEE Transactions on Cognitive and Developmental Systems  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Depth Prediction and Camera Pose Estimation for A Vector-Based Constrained Obstacle Avoidance Scheme for Wheeled Mobile Redundant Robot Manipulator.  ...  ., +, TCDS June 2021 429-441 A Reinforcement Learning Method Using Multifunctional Principal Component Analysis for Human-Like Grasping.  ... 
doi:10.1109/tcds.2021.3137068 fatcat:r2zbw6js65fpnenn4kybim3kw4

Secure Data Sharing and Processing in Heterogeneous Clouds

Bojan Suzic, Andreas Reiter, Florian Reimair, Daniele Venturi, Baldur Kubo
2015 Procedia Computer Science  
Our goal is to enable both security and legal conformance as well as to facilitate transparency, privacy and effectivity of private cloud federations for the public sector needs.  ...  The extensive cloud adoption among the European Public Sector Players empowered them to own and operate a range of cloud infrastructures.  ...  The elements of SACPL are applied as annotations to XACML rules (Rissanen, 2012) , which serve as a basis for interoperable security policy.  ... 
doi:10.1016/j.procs.2015.09.228 fatcat:yfre4npnhrgfri4gnx3mymv2ze

Knowledge Amalgamation for Object Detection with Transformers [article]

Haofei Zhang, Feng Mao, Mengqi Xue, Gongfan Fang, Zunlei Feng, Jie Song, Mingli Song
2022 arXiv   pre-print
In this work, we explore a more effective KA scheme for transformer-based object detection models.  ...  Currently, most of these approaches are tailored for convolutional neural networks (CNNs).  ...  To begin with, let D = {I i } L i=1 be a dataset of L images. For image I i , we have a set of annotations Y i = {y j i } ai j=1 , where a i is the number of annotations for I i .  ... 
arXiv:2203.03187v1 fatcat:xf7i6u27erbozb3cuge6fqni5e

Recognizing Textual Entailment: Challenges in the Portuguese Language

Gil Rocha, Henrique Lopes Cardoso
2018 Information  
As in many NLP tasks, textual entailment corpora for English abound, while the same is not true for more resource-scarce languages such as Portuguese.  ...  If such relation is bidirectional, then we are in the presence of a paraphrase.  ...  Henrique Lopes Cardoso has supervised the work, namely for defining the methods proposed, designing the experimental settings and analyzing results.  ... 
doi:10.3390/info9040076 fatcat:e7n6olpwvjbbjpo3wjss5wkoxy

Learning Deep on Cyberbullying is Always Better Than Brute Force

Michal Ptaszynski, Juuso Kalevi Kristian Eronen, Fumito Masui
2017 International Joint Conference on Artificial Intelligence  
In this paper we present our research on detection of cyberbullying (CB), which stands for humiliating other people through the Internet.  ...  We propose a novel method to automatic cyberbullying detection based on Convolutional Neural Networks and increased Feature Density.  ...  To prepare gold standard for their experiments they used a crowd-sourcing approach with untrained layperson annotators hired for a classification task through Mechanical Turk.  ... 
dblp:conf/ijcai/PtaszynskiEM17 fatcat:54kthwpqkrbffjibjidqmqie6u
« Previous Showing results 1 — 15 out of 722 results