Matches in SemOpenAlex for { <https://semopenalex.org/work/W4364322905> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4364322905 abstract "The gradual increase in online fencing videos over the past decade has allowed for novel technical projects in fencing that rely heavily on data, such as artificial intelligence. This study resulted in a state-of-the-art lightweight Temporal Convolutional Network to referee fencing bouts and classify actions as either a touch for the fencer on the left, or the fencer on the right. To address this problem, we developed a pose estimation and audio analysis approach to autonomously referee fencing bouts. Using a custom dataset of international level fencing from the last 7 years, including ~4000 unique clips, our model achieved an accuracy of 89.1%, a 20% increase over previous state-of-the-art models. This model leverages advancements in human pose estimation to extract the position of both fencers and avoids high computational loads typically associated with CNNs. Additionally, it uses a novel technique to solve the issue of blade contact, a key component of refereeing fencing that was generally unaddressed in previous works. Our novel approach uses audio to ‘listen’ for the sound of blade contact rather than attempting to identify it visually." @default.
- W4364322905 created "2023-04-12" @default.
- W4364322905 creator A5013574284 @default.
- W4364322905 date "2022-11-30" @default.
- W4364322905 modified "2023-10-11" @default.
- W4364322905 title "Allez Go: Computer Vision and Audio Analysis for AI Fencing Referees" @default.
- W4364322905 doi "https://doi.org/10.47611/jsrhs.v11i4.3394" @default.
- W4364322905 hasPublicationYear "2022" @default.
- W4364322905 type Work @default.
- W4364322905 citedByCount "0" @default.
- W4364322905 crossrefType "journal-article" @default.
- W4364322905 hasAuthorship W4364322905A5013574284 @default.
- W4364322905 hasBestOaLocation W43643229051 @default.
- W4364322905 hasConcept C119857082 @default.
- W4364322905 hasConcept C154945302 @default.
- W4364322905 hasConcept C173608175 @default.
- W4364322905 hasConcept C26517878 @default.
- W4364322905 hasConcept C2778739407 @default.
- W4364322905 hasConcept C38652104 @default.
- W4364322905 hasConcept C41008148 @default.
- W4364322905 hasConcept C48515440 @default.
- W4364322905 hasConcept C81363708 @default.
- W4364322905 hasConceptScore W4364322905C119857082 @default.
- W4364322905 hasConceptScore W4364322905C154945302 @default.
- W4364322905 hasConceptScore W4364322905C173608175 @default.
- W4364322905 hasConceptScore W4364322905C26517878 @default.
- W4364322905 hasConceptScore W4364322905C2778739407 @default.
- W4364322905 hasConceptScore W4364322905C38652104 @default.
- W4364322905 hasConceptScore W4364322905C41008148 @default.
- W4364322905 hasConceptScore W4364322905C48515440 @default.
- W4364322905 hasConceptScore W4364322905C81363708 @default.
- W4364322905 hasIssue "4" @default.
- W4364322905 hasLocation W43643229051 @default.
- W4364322905 hasOpenAccess W4364322905 @default.
- W4364322905 hasPrimaryLocation W43643229051 @default.
- W4364322905 hasRelatedWork W2337926734 @default.
- W4364322905 hasRelatedWork W2963958939 @default.
- W4364322905 hasRelatedWork W3027997911 @default.
- W4364322905 hasRelatedWork W4287776258 @default.
- W4364322905 hasRelatedWork W4308353688 @default.
- W4364322905 hasRelatedWork W4312501200 @default.
- W4364322905 hasRelatedWork W4313050734 @default.
- W4364322905 hasRelatedWork W4319994054 @default.
- W4364322905 hasRelatedWork W4320802194 @default.
- W4364322905 hasRelatedWork W4327499916 @default.
- W4364322905 hasVolume "11" @default.
- W4364322905 isParatext "false" @default.
- W4364322905 isRetracted "false" @default.
- W4364322905 workType "article" @default.