Emotion transfer for hand animation

Ana Sabina Irimia; Jacky C.P. Chan; Kamlesh Mistry; Wei Wei; Edmond S.L. Ho

doi:10.1145/3359566.3364692

Emotion transfer for hand animation

Ana Sabina Irimia
, Jacky C.P. Chan
, Kamlesh Mistry
, Wei Wei
, Edmond S.L. Ho^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

2 Citations (Scopus)

Abstract

We propose a new data-driven framework for synthesizing hand motion at different emotion levels. Specifically, we first capture high-quality hand motion using VR gloves. The hand motion data is then annotated with the emotion type and a latent space is constructed from the motions to facilitate the motion synthesis process. By interpolating the latent representation of the hand motion, new hand animation with different levels of emotion strength can be generated. Experimental results show that our framework can produce smooth and consistent hand motions at an interactive rate.

Original language	English
Title of host publication	MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games
Editors	Stephen N. Spencer
Place of Publication	New York
Publisher	Association for Computing Machinery (ACM)
Number of pages	2
ISBN (Electronic)	9781450369947
DOIs	https://doi.org/10.1145/3359566.3364692
Publication status	Published - 28 Oct 2019
Event	2019 ACM Conference on Motion, Interaction, and Games - Northunbria University, Newcastle upon Tyne, United Kingdom Duration: 28 Oct 2019 → 30 Oct 2019 https://dl.acm.org/doi/proceedings/10.1145/3359566 (Conference proceeding) https://web.archive.org/web/20241106123253/http://www.mig2019.website/ (Conference website)

Publication series

Name	Proceedings - MIG: ACM Conference on Motion, Interaction, and Games

Conference

Conference	2019 ACM Conference on Motion, Interaction, and Games
Abbreviated title	MIG 2019
Country/Territory	United Kingdom
City	Newcastle upon Tyne
Period	28/10/19 → 30/10/19
Internet address	https://dl.acm.org/doi/proceedings/10.1145/3359566 (Conference proceeding) https://web.archive.org/web/20241106123253/http://www.mig2019.website/ (Conference website)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Emotion
Hand animation
Motion capture
Style transfer

Access to Document

10.1145/3359566.3364692

Cite this

Irimia, A. S., Chan, J. C. P., Mistry, K., Wei, W., & Ho, E. S. L. (2019). Emotion transfer for hand animation. In S. N. Spencer (Ed.), MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games Article 41 (Proceedings - MIG: ACM Conference on Motion, Interaction, and Games). Association for Computing Machinery (ACM). https://doi.org/10.1145/3359566.3364692

@inproceedings{810b7543d7474559836187e73808c756,

title = "Emotion transfer for hand animation",

abstract = "We propose a new data-driven framework for synthesizing hand motion at different emotion levels. Specifically, we first capture high-quality hand motion using VR gloves. The hand motion data is then annotated with the emotion type and a latent space is constructed from the motions to facilitate the motion synthesis process. By interpolating the latent representation of the hand motion, new hand animation with different levels of emotion strength can be generated. Experimental results show that our framework can produce smooth and consistent hand motions at an interactive rate.",

keywords = "Emotion, Hand animation, Motion capture, Style transfer",

author = "Irimia, \{Ana Sabina\} and Chan, \{Jacky C.P.\} and Kamlesh Mistry and Wei Wei and Ho, \{Edmond S.L.\}",

note = "Publisher Copyright: {\textcopyright} 2019 Copyright held by the owner/author(s).; 2019 ACM Conference on Motion, Interaction, and Games, MIG 2019 ; Conference date: 28-10-2019 Through 30-10-2019",

year = "2019",

month = oct,

day = "28",

doi = "10.1145/3359566.3364692",

language = "English",

series = "Proceedings - MIG: ACM Conference on Motion, Interaction, and Games",

publisher = "Association for Computing Machinery (ACM)",

editor = "Spencer, \{Stephen N.\}",

booktitle = "MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games",

address = "United States",

url = "https://dl.acm.org/doi/proceedings/10.1145/3359566, https://web.archive.org/web/20241106123253/http://www.mig2019.website/",

}

Irimia, AS, Chan, JCP, Mistry, K, Wei, W & Ho, ESL 2019, Emotion transfer for hand animation. in SN Spencer (ed.), MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games., 41, Proceedings - MIG: ACM Conference on Motion, Interaction, and Games, Association for Computing Machinery (ACM), New York, 2019 ACM Conference on Motion, Interaction, and Games, Newcastle upon Tyne, United Kingdom, 28/10/19. https://doi.org/10.1145/3359566.3364692

Emotion transfer for hand animation. / Irimia, Ana Sabina; Chan, Jacky C.P.; Mistry, Kamlesh et al.
MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games. ed. / Stephen N. Spencer. New York: Association for Computing Machinery (ACM), 2019. 41 (Proceedings - MIG: ACM Conference on Motion, Interaction, and Games).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Emotion transfer for hand animation

AU - Irimia, Ana Sabina

AU - Chan, Jacky C.P.

AU - Mistry, Kamlesh

AU - Wei, Wei

AU - Ho, Edmond S.L.

PY - 2019/10/28

Y1 - 2019/10/28

N2 - We propose a new data-driven framework for synthesizing hand motion at different emotion levels. Specifically, we first capture high-quality hand motion using VR gloves. The hand motion data is then annotated with the emotion type and a latent space is constructed from the motions to facilitate the motion synthesis process. By interpolating the latent representation of the hand motion, new hand animation with different levels of emotion strength can be generated. Experimental results show that our framework can produce smooth and consistent hand motions at an interactive rate.

AB - We propose a new data-driven framework for synthesizing hand motion at different emotion levels. Specifically, we first capture high-quality hand motion using VR gloves. The hand motion data is then annotated with the emotion type and a latent space is constructed from the motions to facilitate the motion synthesis process. By interpolating the latent representation of the hand motion, new hand animation with different levels of emotion strength can be generated. Experimental results show that our framework can produce smooth and consistent hand motions at an interactive rate.

KW - Emotion

KW - Hand animation

KW - Motion capture

KW - Style transfer

UR - https://www.scopus.com/pages/publications/85074818072

UR - https://dl.acm.org/doi/10.1145/3359566.3364692

U2 - 10.1145/3359566.3364692

DO - 10.1145/3359566.3364692

M3 - Conference proceeding

AN - SCOPUS:85074818072

T3 - Proceedings - MIG: ACM Conference on Motion, Interaction, and Games

BT - MIG 2019: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games

A2 - Spencer, Stephen N.

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - 2019 ACM Conference on Motion, Interaction, and Games

Y2 - 28 October 2019 through 30 October 2019

ER -

Emotion transfer for hand animation

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this