Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding

Ryo Umagami, Liu Yue, Xuangeng Chu, Ryuto Fukushima, Tetsuya Narita, Yusuke Mukuta, Tomoyuki Takahata, Jianfei Yang, Tatsuya Harada

Keywords: human motion dataset, human motion prediction, human intention, multimodal

TL;DR: Intend to Move (I2M) is a new multimodal dataset for embodied AI, designed for intention-aware human motion understanding in real-world environments.

Abstract: Human motion is inherently intentional, yet most motion modeling paradigms focus on low-level kinematics, overlooking the semantic and causal factors that drive behavior. Existing datasets further limit progress: they capture short, decontextualized actions in static scenes, providing little grounding for embodied reasoning. To address these limitations, we introduce $\textit{Intend to Move (I2M)}$, a large-scale, multimodal dataset for intention-grounded motion modeling. I2M contains 10.1 hours of two-person 3D motion sequences recorded in dynamic realistic home environments, accompanied by multi-view RGB-D video, 3D scene geometry, and language annotations of each participant’s evolving intentions. Benchmark experiments reveal a fundamental gap in current motion models: they fail to translate high-level goals into physically and socially coherent motion. I2M thus serves not only as a dataset but as a benchmark for embodied intelligence, enabling research on models that can reason about, predict, and act upon the ``why'' behind human motion.

Dataset URL: https://ummaaa.github.io/projects/intend-to-move/

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 787