Crowd-sourced Evaluation of Combat Animations

Yunhao Zhang, Tomer Weiss

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Combat sequences are commonly seen in films, animated media, and video games. Although significant advancements have led to the creation of extensive online collections of these animations, selecting suitable motions for specific uses remains challenging because of their dynamic characteristics. This dynamism and perceptual complexity stem from stylized combat scenes' diverse physical and aesthetic elements. This paper introduces a novel methodology to comprehend user preferences in combat animations with a crowd-sourced learning strategy. We deduce user preferences towards certain motion attributes, which are not easily identifiable through raw geometric data. Our study primarily focuses on sword fighting, which is widely popular in combat scenes.

Original languageEnglish (US)
Title of host publicationProceedings - 2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages60-65
Number of pages6
ISBN (Electronic)9798350372021
DOIs
StatePublished - 2024
Event6th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024 - Los Angeles, United States
Duration: Jan 17 2024Jan 19 2024

Publication series

NameProceedings - 2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024

Conference

Conference6th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024
Country/TerritoryUnited States
CityLos Angeles
Period1/17/241/19/24

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Media Technology
  • Modeling and Simulation

Keywords

  • animation
  • statistical learning

Fingerprint

Dive into the research topics of 'Crowd-sourced Evaluation of Combat Animations'. Together they form a unique fingerprint.

Cite this