5 papers
SoccerNet 2026 Challenges Results
Anthony Cioppa, Silvio Giancola, Håkan Ardö +102
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video underst…
Actions and Objects Pathways for Domain Adaptation in Video Question Answering
Safaa Abdullahi Moallim Mohamud, Ho-Young Jung
In this paper, we introduce the Actions and Objects Pathways (AOPath) for out-of-domain generalization in video question answering tasks. AOPath leverages features from a large pre…
BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification
June-Woo Kim, Miika Toikkanen, Yera Choi +2
Respiratory sound classification (RSC) is challenging due to varied acoustic signatures, primarily influenced by patient demographics and recording environments. To address this is…
Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding
Suyoung Kim, Jiyeon Hwang, Ho-Young Jung
Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech da…
RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
June-Woo Kim, Miika Toikkanen, Sangmin Bae +2
Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generaliz…