Research map / 3D vision / 3D generation
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
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces Intend to Move (I2M), a large-scale multimodal dataset for intention-aware human motion understanding, aimed at embodied reasoning beyond short decontextualized actions in static scenes.
Problem
Existing human motion datasets capture short, decontextualized actions in static scenes, which gives little grounding for modeling the semantic and causal intentions behind motion and for embodied reasoning.
Approach
A large-scale multimodal motion dataset whose sequences are contextualized by scene and intention, shifting motion modeling from low-level kinematics toward intent-aware understanding.
Closest papers by meaning
- Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents (ECCV 2026 · similarity 0.89)
- IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes (AAAI 2026 · similarity 0.89)
- WANDR: Intention-guided Human Motion Generation (CVPR 2024 · similarity 0.88)
- Multimodal Sense-Informed Forecasting of 3D Human Motions (CVPR 2024 · similarity 0.87)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.87)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
