Filters








473 Hits in 10.5 sec

Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks

Jonathan Tompson, Murphy Stein, Yann Lecun, Ken Perlin
2014 ACM Transactions on Graphics  
As one possible application of this pipeline, we show state-of-the-art results for real-time puppeteering of a skinned hand-model.  ...  Our method consists of the following stages: a randomized decision forest classifier for image segmentation, a robust method for labeled dataset generation, a convolutional network for dense feature extraction  ...  Since experimentally we have found that hand-pose extraction requires knowledge of both local and global features, a single resolution ConvNet would need to examine a large image window and thus would  ... 
doi:10.1145/2629500 fatcat:wnumayuaszho5gi7tnm2sfhyte

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
2021 arXiv   pre-print
We believe this survey will provide the readers with a deep and insightful understanding of monocular human pose estimation.  ...  Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications.  ...  Then a two-level hierarchy of LSTM network is developed to model the global and local features progressively. Furthermore, SemGCN [28] and Liu et al.  ... 
arXiv:2104.11536v1 fatcat:tdag2jq2vjdrjekwukm5nu7l6a

A Survey on Human Performance Capture and Animation

Shihong Xia, Lin Gao, Yu-Kun Lai, Ming-Ze Yuan, Jinxiang Chai
2017 Journal of Computer Science and Technology  
With the rapid development of computing technology, three-dimensional (3D) human body models and their dynamic motions are widely used in the digital entertainment industry.  ...  Human performance mainly involves human body shapes and motions.  ...  involved for style transfer by building online local mixtures of autoregressive (MAR) models, which Figure 3 . 3 Figure 3.  ... 
doi:10.1007/s11390-017-1742-y fatcat:kxfoylv535axtnpj6iaqda3mz4

Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective

Wu Liu, Tao Mei
2022 ACM Computing Surveys  
Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications.  ...  Recently, benefiting from the deep learning technologies, a significant amount of research efforts have advanced the monocular human pose estimation both in 2D and 3D areas.  ...  They randomly transform the lifted 3D pose in a loop to avoid converging to a local minimum with a constant depth. Robust 2D pose estimation can only provide limited information about the human body.  ... 
doi:10.1145/3524497 fatcat:4pbvntngrnfp7lqhcpjmy7p2fq

Control, localization and human interaction with an autonomous lighter-than-air performer

David St-Onge, Pierre-Yves Brèches, Inna Sharf, Nicolas Reeves, Ioannis Rekleitis, Patrick Abouzakhm, Yogesh Girdhar, Adam Harmat, Gregory Dudek, Philippe Giguère
2017 Robotics and Autonomous Systems  
Due to the recent technological progress, Human-Robot Interaction (HRI) has become a major field of research in both engineering and artistic realms, particularly so in the last decade.  ...  The artistic context of this project required a number of advances in engineering on the aspects of localization and control systems, flight dynamics, as well as interaction strategies, and their evolution  ...  , as well as of the UQAM fund for support of research and creation (PAFARC).  ... 
doi:10.1016/j.robot.2016.10.013 fatcat:ixdwzy6trben5ng5x7fs2hh5hi

Artificial Intelligence for the Metaverse: A Survey [article]

Thien Huynh-The and Quoc-Viet Pham and Xuan-Qui Pham and Thanh Thi Nguyen and Zhu Han and Dong-Seong Kim
2022 arXiv   pre-print
We then convey a comprehensive investigation of AI-based methods concerning six technical aspects that have potentials for the metaverse: natural language processing, machine vision, blockchain, networking  ...  , digital twin, and neural interface, and being potential for the metaverse.  ...  Regarding architecture, the Decentraland protocol has three layers: a consensus layer to track land ownership and its content, a land content layer to distribute the materials for rendering via a decentralized  ... 
arXiv:2202.10336v1 fatcat:35isd745dbaqfnpzthnmbaosue

Real Time Animation of Virtual Humans: A Trade-off Between Naturalness and Control [article]

H. Van Welbergen, B. J. H. Van Basten, A. Egges, Zs. Ruttkay, M. H. Overmars
2009 Eurographics State of the Art Reports  
The motion of such virtual humans should look realistic (or 'natural') and allow interaction with the surroundings and other (virtual) humans.  ...  Virtual humans are employed in many interactive applications using 3D virtual environments, including (serious) games.  ...  Acknowledgements This research has been supported by the GATE project, funded by the Netherlands Organization for Scientific Research (NWO) and the Netherlands ICT Research and Innovation Authority (ICT  ... 
doi:10.2312/egst.20091061 fatcat:eyx5isa3nzchngwspuc4tiam54

Real Time Animation of Virtual Humans: A Trade-off Between Naturalness and Control

H. Van Welbergen, B. J. H. Van Basten, A. Egges, Zs. M. Ruttkay, M. H. Overmars
2010 Computer graphics forum (Print)  
The motion of such virtual humans should look realistic (or 'natural') and allow interaction with the surroundings and other (virtual) humans.  ...  Virtual humans are employed in many interactive applications using 3D virtual environments, including (serious) games.  ...  Acknowledgements This research has been supported by the GATE project, funded by the Netherlands Organization for Scientific Research (NWO) and the Netherlands ICT Research and Innovation Authority (ICT  ... 
doi:10.1111/j.1467-8659.2010.01822.x fatcat:dkmuecxsirbdbgnsfzqb7ulxca

A Survey on Deep Learning for Skeleton-Based Human Animation [article]

L. Mourot, L. Hoyet, F. Le Clerc, François Schnitzler
2021 arXiv   pre-print
In this article, we propose a comprehensive survey on the state-of-the-art approaches based on either deep learning or deep reinforcement learning in skeleton-based human character animation.  ...  First, we introduce motion data representations, most common human motion datasets and how basic deep models can be enhanced to foster learning of spatial and temporal patterns in motion data.  ...  This enables an explicit modelling of body part motion prediction at a local and global scale.  ... 
arXiv:2110.06901v1 fatcat:abppln4rbbeufiw4z6a3wnk7oy

Review of Action Recognition and Detection Methods [article]

Soo Min Kang, Richard P. Wildes
2016 arXiv   pre-print
In efforts to ensure that computer vision-based algorithms reach the capabilities that humans have of identifying actions irrespective of various nuisance variables that may be present within the field  ...  In this report, a thorough review of various action recognition and detection algorithms in computer vision is provided by analyzing the two-step process of a typical action recognition and detection algorithm  ...  Thus, action recognition and detection remains a fundamental problem for its related recognition and classification tasks.  ... 
arXiv:1610.06906v2 fatcat:tqq32ml4cjf4nlv6ivf3ydw3ce

Novel pervasive scenarios for home management: the Butlers architecture

Enrico Denti
2014 SpringerPlus  
, the corresponding technologies and the consequent value-added for users in each layer.  ...  Accordingly, we first analyse the system requirements and define a reference multi-layer architectural modelthe Butlers architecturethat specifies seven layers of functionalities, correlating the requirements  ...  Leo Di Carlo for his work and contribution in the development of the prototype.  ... 
doi:10.1186/2193-1801-3-52 pmid:24555169 pmcid:PMC3922993 fatcat:y2kixczlpneytdzgcqt7sp6yfi

Sensing through structure

Ronit Slyper, Ivan Poupyrev, Jessica Hodgins
2011 Proceedings of the fifth international conference on Tangible, embedded, and embodied interaction - TEI '11  
We also use this vocabulary to design a tongue input device for a collaboration with Disney Imagineering.  ...  , cellphone cameras . . . the interactions of a human with a computer seem not to be reducible to a few simple manipulations.  ...  Their performance animation system used a database of motion capture, and at runtime built a locally linear model of poses close to the control signals and to previous poses to find the best match to the  ... 
doi:10.1145/1935701.1935744 dblp:conf/tei/SlyperPH11 fatcat:edj74amzfvcuxo33qirabtivsm

A Comprehensive Software Framework for Complex Locomotion and Manipulation Tasks Applicable to Different Types of Humanoid Robots

Stefan Kohlbrecher, Alexander Stumpf, Alberto Romay, Philipp Schillinger, Oskar von Stryk, David C. Conner
2016 Frontiers in Robotics and AI  
It provides newcomers as well as experienced researchers in humanoid robotics a comprehensive system comprising open source packages for locomotion, manipulation, perception, world modeling, behavior control  ...  In this paper, a software framework for humanoid disaster response robots is introduced.  ...  A 3D terrain generator allows to generate terrain models for the footstep planning system online.  ... 
doi:10.3389/frobt.2016.00031 fatcat:4wjx7zaoaffpliak4iilu4cowe

28th Annual Computational Neuroscience Meeting: CNS*2019

2019 BMC Neuroscience  
The first one consisted of using the neuron oscillations to drive the robot directly, for example moving the legs when a specific neuron fires.  ...  Bio-inspired central pattern generators have been widely used to control robot locomotion, see for review [1].  ...  In the spontaneous state, the model exhibits neural avalanches, whose size distribution is scale-invariant for some global coupling strength value.  ... 
doi:10.1186/s12868-019-0538-0 fatcat:3pt5qvsh45awzbpwhqwbzrg4su

Passive Motion Paradigm: An Alternative to Optimal Control

Vishwanathan Mohan, Pietro Morasso
2011 Frontiers in Neurorobotics  
Therefore, the paper is at the same time a review of the PMP rationale, as a computational theory, and a perspective presentation of how to develop it for designing better cognitive architectures.  ...  In the last years, optimal control theory (OCT) has emerged as the leading approach for investigating neural control of movement and motor cognition for two complementary research lines: behavioral neuroscience  ...  We are indebted to the anonymous reviewers for not just their detailed analysis and criticisms to the initial versions of this paper, but also for their attempts to put their own vision into this manuscript  ... 
doi:10.3389/fnbot.2011.00004 pmid:22207846 pmcid:PMC3246361 fatcat:pbogeikyarbodlvzbwvnm4rlc4
« Previous Showing results 1 — 15 out of 473 results