Filters








163 Hits in 6.2 sec

Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube [article]

Aravind Sivakumar, Kenneth Shaw, Deepak Pathak
2022 arXiv   pre-print
Moreover, the retargeted trajectories must effectively execute tasks on a physical robot, which requires them to be temporally smooth and free of self-collisions.  ...  Our low-cost, glove-free, marker-free remote teleoperation system makes robot teaching more accessible and we hope that it can aid robots in learning to act autonomously in the real world.  ...  ACKNOWLEDGMENTS We are grateful to Ankur Handa for initial feedback and to Shikhar Bahl, Murtaza Dalal and Russell Mendonca for feedback on the paper.  ... 
arXiv:2202.10448v2 fatcat:cjs5si64jnax3l5px5ntopcfry

A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos [article]

Thiago L. Gomes and Renato Martins and João Ferreira and Rafael Azevedo and Guilherme Torres and Erickson R. Nascimento
2021 arXiv   pre-print
Despite the advances from recent image-to-image translation approaches, there are several transferring contexts where most end-to-end learning-based retargeting methods still perform poorly.  ...  The formulation leverages the user body shape into the retargeting while considering physical constraints of the motion in 3D and the 2D image domain.  ...  The authors thank CAPES, CNPq, and FAPEMIG for funding this work. We also thank NVIDIA for the donation of a Titan XP GPU used in this research.  ... 
arXiv:2103.15596v2 fatcat:them7wrlvfchpgy36mtxmfzm2q

A computational cognition model of perception, memory, and judgment

XiaoLan Fu, LianHong Cai, Ye Liu, Jia Jia, WenFeng Chen, Zhang Yi, GuoZhen Zhao, YongJin Liu, ChangXu Wu
2014 Science China Information Sciences  
Marr's visual computing theory is the most representative cognitive computing model, which plays an important role in guiding intelligent computer image processing [5] .  ...  The visual media, including digital images, video and three-dimensional models, contains superfluous visual information.  ...  We thank ZHANG JingYu, FU QiuFang, XUAN YuMing, WANG XiaoHui, YAN WenJing, CHEN Yu-Hsin, and ZHANG Lei for useful discussions and helpful comments on earlier drafts of this manuscript.  ... 
doi:10.1007/s11432-013-4911-9 fatcat:txtu62aa7zd3plg3y2wvfdq5xe

Sketch-Based Skeleton-Driven 2D Animation and Motion Capture [chapter]

Junjun Pan, Jian J. Zhang
2011 Lecture Notes in Computer Science  
Aggarwal and Triggs [2006] described a learning based method for recovering 3D human pose from monocular image sequences.  ...  (Left: original image sequence; Middle: joints tracking result; Right: retargeted new character)From the results, the problem of self-occlusion is effectively solved.  ... 
doi:10.1007/978-3-642-22639-7_17 fatcat:7j4ililxmjgnzlhadplbzfc4a4

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

L. Mourot, L. Hoyet, F. Le Clerc, François Schnitzler
2021 arXiv   pre-print
To this end, deep neural networks drive most recent advances through deep learning and deep reinforcement learning.  ...  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.  ...  (DL) and Deep Reinforcement Learning (DRL) (see Figure 1 ).  ... 
arXiv:2110.06901v1 fatcat:abppln4rbbeufiw4z6a3wnk7oy

تأثیر المستهلک فی خلق القیمة المشترکة للسیاحة المصریة من خلال وسائل التواصل الاجتماعی

نرمین عبد الحلیم
2021 مجلة العمارة والفنون والعلوم الإنسانية  
The Egyptian tourism industry requires different strategies to develop Egypt's image with the international audience and create a relationship with the target audience due to the tremendous development  ...  The end outcome is a graphical model of important factors for successful strategy based on consumer value co-creation (VCC) through social media.  ...  online sharing can reinforce a tourism destination's image and create deeper loyalty, making these images are powerful tools for tourism marketing.  ... 
doi:10.21608/mjaf.2020.46726.1991 fatcat:wad3ddjzpbe77cybqi42lrssei

Robot Learning by Active Imitation [chapter]

Juan Pedro, Rebeca Marfil, Luis Molina, Juan Antonio, Antonio Bandera, Francisco Sandoval
2007 Humanoid Robots, Human-like Machines  
The hand poses provided by this model are translated to an egocentric image by the retargeting method described in Section 4.4.  ...  Many learning algorithms have been proposed for robotics applications.  ...  and Mind Organisation: Learning and Interaction.  ... 
doi:10.5772/4821 fatcat:ybz3usowljectoogk2l7lwpww4

Character Animation Using Reinforcement Learning and Imitation Learning Algorithms

Tokey Tahmid, Mohammad Abu Lobabah, Muntasir Ahsan, Raisa Zarin, Sabah Shahnoor Anis, Faisal Bin Ashraf
2021 2021 Joint 10th International Conference on Informatics, Electronics & Vision (ICIEV) and 2021 5th International Conference on Imaging, Vision & Pattern Recognition (icIVPR)  
In this paper, we propose a model that aims to generate real-time character animation for biped locomotion in Unity ML agents using Reinforcement learning and Imitation learning algorithms.  ...  Real-time character animation for gaming and film industries is challenging and achieving production-ready quality is the hardest part. Managing time and resources also plays a vital role here.  ...  In their work, the authors propose a self-imitation learning system that enables the stable locomotion controllers for rapid learning.  ... 
doi:10.1109/icievicivpr52578.2021.9564143 fatcat:zi3qv5fiavedzhukkcqr4url3a

Table of contents

2021 ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
LINK PREDICTION VIA REINFORCEMENT LEARNING ......................................... 3460 Ye Tao, Ying Li, Zhonghai Wu, Peking University, China MLSP-26.4: A DEEP REINFORCEMENT LEARNING APPROACH TO AUDIO-BASED  ...  Giannakis, University of Minnesota, United States MLSP-27.2: SELF-INFERENCE OF OTHERS' POLICIES FOR HOMOGENEOUS ............................................ 3960 AGENTS IN COOPERATIVE MULTI-AGENT REINFORCEMENT  ... 
doi:10.1109/icassp39728.2021.9414617 fatcat:m5ugnnuk7nacbd6jr6gv2lsfby

A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU [article]

Shuang Li, Jiaxi Jiang, Philipp Ruppel, Hongzhuo Liang, Xiaojian Ma, Norman Hendrich, Fuchun Sun, Jianwei Zhang
2020 arXiv   pre-print
Transteleop observes the human hand through a low-cost depth camera and generates not only joint angles but also depth images of paired robot hand poses through an image-to-image translation process.  ...  A keypoint-based reconstruction loss explores the resemblance in appearance and anatomy between human and robotic hands and enriches the local features of reconstructed images.  ...  ACKNOWLEDGMENT This research was funded jointly by the German Research Foundation (DFG) and the National Science Foundation of China (NSFC) in project Cross Modal Learning, NSFC 61621136008/DFG TRR-169  ... 
arXiv:2003.05212v1 fatcat:vf2auxtcxzhdfjwwpaiaabpqmq

An Innovative Serious Game for the Detection and Rehabilitation of Oral-Facial Malfunction in Children: A Pilot Study

Nuria Máximo-Bocanegra, María-Luisa Martín-Ruiz
2017 Journal of Sensors  
In the future, SONRIE could be used as a tool for detecting difficulties regarding self-control and for influencing performance and the ability to produce fine-tuned facial movements.  ...  For this purpose, tests were performed in school settings with 96 typically developing children aged between five and seven years.  ...  Thanks are due also to Laura Luna, for her insightful help with the identification of the orofacial muscles targeted by the SONRIE program for the rehabilitation of children with cerebral palsy.  ... 
doi:10.1155/2017/8745437 fatcat:w4echg7ml5fgtikzdroecf7cvu

A real time and robust facial expression recognition and imitation approach for affective human-robot interaction using Gabor filtering

Felipe Cid, Jose Augusto Prado, Pablo Bustos, Pedro Nunez
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The proposed method achieves a fast and robust facial feature extraction based on consecutively applying filters to the gradient image.  ...  This paper presents a real-time system for recognition and imitation of facial expressions in the context of affective Human Robot Interaction.  ...  Human behavior imitation has been used for learning tasks and for enhancing human-robot communication [7] .  ... 
doi:10.1109/iros.2013.6696662 dblp:conf/iros/CidPBN13 fatcat:mlzy63bubjgizczwycwsrhjp7i

Table of Contents

2020 2020 IEEE International Conference on Image Processing (ICIP)  
\ &KLQD ARS-05.5: DEEP SELF-LEARNING HASHING FOR IMAGE RETRIEVAL .................................................................... 1556 -LDZHL =KDQ =KDRJXR 0R <XHVKHQJ =KX 6KHQ]KHQ *UDGXDWH 6FKRRO 3HNLQJ  ...  ENHANCED RESOLUTION-WISE FEATURES ARS- 06 : 06 MACHINE LEARNING FOR IMAGE AND VIDEO ANALYSIS AND RETRIEVAL I ARS-06.1: SPACE-TIME GUIDED ASSOCIATION LEARNING FOR UNSUPERVISED .......................  ...  CODED-APERTURE FOR UNSUPERVISED CLASSIFICATION OF HYPERSEPCTRAL IMAGERY -LDQFKHQ =KX 7RQJ =KDQJ 6KHQJMLH =KDR 7RQJML 8QLYHUVLW\ &KLQD IMT-02.4: ADMM-INSPIRED RECONSTRUCTION NETWORK FOR COMPRESSIVE  ... 
doi:10.1109/icip40778.2020.9191006 fatcat:3fkxl2sjmre2jkryewwo5mlahi

Smart Fashion: A Review of AI Applications in the Fashion Apparel Industry [article]

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
The implementation of machine learning, computer vision, and artificial intelligence (AI) in fashion applications is opening lots of new opportunities for this industry.  ...  For each task, a time chart is provided to analyze the progress through the years.  ...  , 15.8% P@10 Street-Shop, Multiple, Detect 55 Kavitha [454] CNN, VGG-16, BoW, Word2Vec, TDF-IDF Shop, Also text-based 56 Kotouza [455] UI, NLP, Deep reinforcement learning, Clustering Multiple clustering  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control [article]

Pei Xu, Ioannis Karamouzas
2021 arXiv   pre-print
Our work builds upon generative adversarial networks (GAN) and reinforcement learning, and introduces an imitation learning framework where an ensemble of classifiers and an imitation policy are trained  ...  We present a simple and intuitive approach for interactive control of physically simulated characters.  ...  In addition, a carefully designed reward function plays a key role for imitation learning in these works.  ... 
arXiv:2105.10066v1 fatcat:5meb546ob5ga3ljm4ieptf3aae
« Previous Showing results 1 — 15 out of 163 results