TAvE: Template-based augmentation of visual effects to human actions in videos

J. Liu; X. Zhou; H. Fu; C. L. Tai

doi:10.2312/pg.20181289

TAvE: Template-based augmentation of visual effects to human actions in videos

J. Liu
, X. Zhou
, H. Fu
, C. L. Tai

School of Creative Media

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

We present TAVE, a framework that allows novice users to add interesting visual effects by mimicking human actions in a given template video, in which pre-defined visual effects have already been associated with specific human actions. Our framework is mainly based on high-level features of human pose extracted from video frames, and uses low-level image features as the auxiliary information. We encode an action into a set of code sequences representing joint motion directions and use a finite state machine to recognize the action state of interest. The visual effects, possibly with occlusion masks, can be automatically transferred from the template video to a target video containing similar human actions.

Original language	English
Title of host publication	Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings
Publisher	IEEE Computer Society
Pages	3-4
Volume	2018-October
ISBN (Print)	9783038680734
DOIs	https://doi.org/10.2312/pg.20181289
Publication status	Published - 2018
Event	26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018) - City University of Hong Kong, Hong Kong, China Duration: 8 Oct 2018 → 11 Oct 2018 http://sweb.cityu.edu.hk/pg2018/ https://dl.acm.org/doi/proceedings/10.5555/3308497

Publication series

Name	Proceedings - Pacific Conference on Computer Graphics and Applications
Volume	2018-October
ISSN (Print)	1550-4085

Conference

Conference	26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018)
Abbreviated title	PG 2018
Place	China
City	Hong Kong
Period	8/10/18 → 11/10/18
Internet address	http://sweb.cityu.edu.hk/pg2018/ https://dl.acm.org/doi/proceedings/10.5555/3308497

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Access Output

10.2312/pg.20181289

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Liu, J., Zhou, X., Fu, H., & Tai, C. L. (2018). TAvE: Template-based augmentation of visual effects to human actions in videos. In Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings (Vol. 2018-October, pp. 3-4). (Proceedings - Pacific Conference on Computer Graphics and Applications; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.2312/pg.20181289

Liu, J. ; Zhou, X. ; Fu, H. et al. / TAvE : Template-based augmentation of visual effects to human actions in videos. Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings. Vol. 2018-October IEEE Computer Society, 2018. pp. 3-4 (Proceedings - Pacific Conference on Computer Graphics and Applications).

@inproceedings{d1d48a42b14a47fba97f08b3c066485f,

title = "TAvE: Template-based augmentation of visual effects to human actions in videos",

abstract = "We present TAVE, a framework that allows novice users to add interesting visual effects by mimicking human actions in a given template video, in which pre-defined visual effects have already been associated with specific human actions. Our framework is mainly based on high-level features of human pose extracted from video frames, and uses low-level image features as the auxiliary information. We encode an action into a set of code sequences representing joint motion directions and use a finite state machine to recognize the action state of interest. The visual effects, possibly with occlusion masks, can be automatically transferred from the template video to a target video containing similar human actions.",

author = "J. Liu and X. Zhou and H. Fu and Tai, \{C. L.\}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; 26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018), PG 2018 ; Conference date: 08-10-2018 Through 11-10-2018",

year = "2018",

doi = "10.2312/pg.20181289",

language = "English",

isbn = "9783038680734",

volume = "2018-October",

series = "Proceedings - Pacific Conference on Computer Graphics and Applications",

publisher = "IEEE Computer Society",

pages = "3--4",

booktitle = "Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings",

address = "United States",

url = "http://sweb.cityu.edu.hk/pg2018/, https://dl.acm.org/doi/proceedings/10.5555/3308497",

}

Liu, J, Zhou, X, Fu, H & Tai, CL 2018, TAvE: Template-based augmentation of visual effects to human actions in videos. in Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings. vol. 2018-October, Proceedings - Pacific Conference on Computer Graphics and Applications, vol. 2018-October, IEEE Computer Society, pp. 3-4, 26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018), Hong Kong, China, 8/10/18. https://doi.org/10.2312/pg.20181289

TAvE: Template-based augmentation of visual effects to human actions in videos. / Liu, J.; Zhou, X.; Fu, H. et al.
Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings. Vol. 2018-October IEEE Computer Society, 2018. p. 3-4 (Proceedings - Pacific Conference on Computer Graphics and Applications; Vol. 2018-October).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - TAvE

T2 - 26th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2018)

AU - Liu, J.

AU - Zhou, X.

AU - Fu, H.

AU - Tai, C. L.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2018

Y1 - 2018

N2 - We present TAVE, a framework that allows novice users to add interesting visual effects by mimicking human actions in a given template video, in which pre-defined visual effects have already been associated with specific human actions. Our framework is mainly based on high-level features of human pose extracted from video frames, and uses low-level image features as the auxiliary information. We encode an action into a set of code sequences representing joint motion directions and use a finite state machine to recognize the action state of interest. The visual effects, possibly with occlusion masks, can be automatically transferred from the template video to a target video containing similar human actions.

AB - We present TAVE, a framework that allows novice users to add interesting visual effects by mimicking human actions in a given template video, in which pre-defined visual effects have already been associated with specific human actions. Our framework is mainly based on high-level features of human pose extracted from video frames, and uses low-level image features as the auxiliary information. We encode an action into a set of code sequences representing joint motion directions and use a finite state machine to recognize the action state of interest. The visual effects, possibly with occlusion masks, can be automatically transferred from the template video to a target video containing similar human actions.

UR - https://www.scopus.com/pages/publications/85121275525

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85121275525&origin=recordpage

U2 - 10.2312/pg.20181289

DO - 10.2312/pg.20181289

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783038680734

VL - 2018-October

T3 - Proceedings - Pacific Conference on Computer Graphics and Applications

SP - 3

EP - 4

BT - Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings

PB - IEEE Computer Society

Y2 - 8 October 2018 through 11 October 2018

ER -

Liu J, Zhou X, Fu H, Tai CL. TAvE: Template-based augmentation of visual effects to human actions in videos. In Pacific Graphics 2018 - 26th Pacific Conference on Computer Graphics and Applications, Short Papers and Posters Proceedings. Vol. 2018-October. IEEE Computer Society. 2018. p. 3-4. (Proceedings - Pacific Conference on Computer Graphics and Applications). doi: 10.2312/pg.20181289

TAvE: Template-based augmentation of visual effects to human actions in videos

Abstract

Publication series

Conference

Bibliographical note

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this