Jinhao Tian — accepted AI-conference papers

2025

NOTA: Multimodal Music Notation Understanding for Visual Large Language Model

Mingni Tang, Jiajia Li, Lu Yang, Zhiqiang Zhang, Jinhao Tian, Zuchao Li +2

NAACL 2025findings

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol seque…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding

Jinhao Tian, Zuchao Li, Jiajia Li, Ping Wang

AAAI 2024technical

The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Subsequently, the sequences are fed into a neural sequence model to accomplish spec…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗