3 papers
cs.SD2026
MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck
Fan Bu, Rongfeng Li, Linfeng Fan
Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise…
cs.CV2026
STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
Linfeng Fan, Yuan Tian, Ziwei Li +1
Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing miti…
cs.CV2025
The Renaissance of Expert Systems: Optical Recognition of Printed Chinese Jianpu Musical Scores with Lyrics
Fan Bu, Rongfeng Li, Zijin Li +3
Large-scale optical music recognition (OMR) research has focused mainly on Western staff notation, leaving Chinese Jianpu (numbered notation) and its rich lyric resources underexpl…