5 papers
Cross-Modal Knowledge Distillation for Acoustic Pedestrian Detection
Yonghyun Kim, Chaeyeon Han, Sancho Gatungay +2
Audio-only pedestrian detection is attractive for urban sensing but limited by weak acoustic cues. An appealing strategy is cross-modal knowledge distillation, in which a video tea…
Multi-Task Multi-Frame Visual Piano Transcription
Yonghyun Kim, Hoyeol Sohn, Juhan Nam +1
Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extende…
Audio-Based Pedestrian Detection in the Presence of Vehicular Noise
Yonghyun Kim, Chaeyeon Han, Akash Sarode +3
Audio-based pedestrian detection is a challenging task and has, thus far, only been explored in noise-limited environments. We present a new dataset, results, and a detailed analys…
Two Web Toolkits for Multimodal Piano Performance Dataset Acquisition and Fingering Annotation
Junhyung Park, Yonghyun Kim, Joonhyung Bae +4
Piano performance is a multimodal activity that intrinsically combines physical actions with the acoustic rendition. Despite growing research interest in analyzing the multimodal n…
PianoVAM: A Multimodal Piano Performance Dataset
Yonghyun Kim, Junhyung Park, Joonhyung Bae +4
The multimodal nature of music performance has driven increasing interest in data beyond the audio domain within the music information retrieval (MIR) community. This paper introdu…