Logo do repositório
 
Publicação

Multi-modal highlight detection in broadcast audio: a deep learning approach for event recognition in sports and eSports

2026-01-01Atas de conferência Acesso aberto
Ver registo simples
dc.contributor.authorCosta, Nuno
dc.contributor.authorOliveira, António
dc.contributor.authorLobo, Armindo
dc.contributor.authorTeixeira, Ricardo
dc.contributor.authorFernandes, Duarte
dc.contributor.authorRodrigues, Ricardo
dc.contributor.authorGouveia, Emanuel
dc.date.accessioned2026-04-23T15:49:53Z
dc.date.available2026-04-23T15:49:53Z
dc.date.issued2026-01-01
dc.description.abstractThe detection of highlights in broadcast streams is essential for enhancing User Experience (UX) through automated summaries and efficient content retrieval. This is particularly relevant for live streaming environments common in sports and eSports, where audiences demand near real-time analysis. This paper presents a benchmark of models for highlight detection in broadcast audio, validated on the SoccerNet dataset but applicable to general competitive gaming streams. We propose a novel multi-modal architecture combining high-level semantic audio features (YAMNet) with Natural Language Processing (NLP) of transcribed commentary (analogous to eSports shoutcasting). Results show that fusing audio event detection with semantic text analysis significantly outperforms uni-modal baselines. The proposed framework offers a computationally efficient solution for AI-based broadcasting technologies, enabling scalable automation for content creators and improved viewer experiences.eng
dc.identifier.doi10.5220/0014585200004052
dc.identifier.eid105035626420
dc.identifier.isbn9789897587962
dc.identifier.otherbf873a90-e1ab-4836-888b-96dddaaa5f59
dc.identifier.urihttp://hdl.handle.net/10400.14/57581
dc.language.isoeng
dc.peerreviewedyes
dc.publisherScience and Technology Publications, Lda
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectAI-based sports technologieseng
dc.subjectAudio event detectioneng
dc.subjectBroadcast stream automationeng
dc.subjectMachine learning for real-time analysiseng
dc.subjectMulti-modal deep learningeng
dc.titleMulti-modal highlight detection in broadcast audio: a deep learning approach for event recognition in sports and eSports
dc.typeconference proceedings
dspace.entity.typePublication
oaire.citation.endPage996
oaire.citation.startPage989
oaire.citation.titleProceedings of the 18th international conference on agents and artificial intelligence
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
145665240.pdf
Tamanho:
963.54 KB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

CEFH - Livros e Partes de Livros / Books and Books Parts