We present the H2H (Human-to-Human) Music Improvisation Dataset, containing six hours of audio-visual expert duo improvisations with clean per-player stems and per-player annotations, in which each performer annotates both their own musical navigation intentions and their peception of their partner’s. The work has been published in the Proceedings of the Society for Music Information Retrieval Conference (ISMIR) 2026. Project page could be found at https://h2himprov.github.io/.