Research
bruno@cabado:~$ ls -lt research/# 7 papers · action spotting, tactical classification, real-time sports AI
result 96.1% macro F1 on handball and 92.5% on basketball with sub-4 ms inference and 34.04 ms end-to-end pipeline latency.
Expert Systems with Applications 322 · Bruno Cabado, Bertha Guijarro-Berdiñas, Emilio J. Padrón
details →read publication ↗
result Reduced post-event highlight processing time by 87.5% while maintaining 90% event-selection accuracy.
FAIA / ECAI Proceedings 2025 · Bruno Cabado, Bertha Guijarro-Berdiñas, Emilio J. Padrón
details →read publication ↗
result Released a synthetic labeled dataset with 365,383 sports frames covering seven standardized game situations.
Data in Brief 2024 · Bruno Cabado, Bertha Guijarro-Berdiñas, Emilio J. Padrón et al.
details →read publication ↗
result Demonstrated practical NL-to-SQL interaction quality across four LLMs using human evaluation metrics.
SPUDC 2024 · Borja Souto, David Vilares, Bruno Cabado
details →read publication ↗
result Unified fragmented action-spotting methods into one reusable library pipeline for faster experimentation.
IEEE STAR 2024 · Yassine Benzakour, Bruno Cabado, Silvio Giancola et al.
details →read publication ↗
result Broadcast editing style appears as the dominant factor affecting cross-domain action-spotting transfer.
CVPR Workshops 2024 · Bruno Cabado, Anthony Cioppa, Silvio Giancola et al.
details →read publication ↗
result 98.6% classification accuracy with 4 ms inference and 34.04 ms end-to-end pipeline latency.
IEEE ICTAI 2022 · Bruno Cabado, Bertha Guijarro-Berdiñas, Emilio J. Padrón
details →read publication ↗