Research map / Vision-language and multimodal / Human and embodied modeling
Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization
Guangtao Lyu, Chenghao Xu, Jiexi Yan, Muli Yang, Cheng Deng
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.
Proposes a sparse interpretable characterization framework that aligns human motion and language features to enable unified motion-language understanding, going beyond coarse CLIP-style alignment.
Problem
Existing human motion understanding methods focus on specific downstream tasks and roughly align text and motion features in a CLIP-like framework, lacking rich semantic information for deeper motion comprehension.
Approach
Uses sparse, interpretable characterization of motion and language features to achieve finer-grained motion-language alignment within a unified framework, rather than coarse CLIP-like global alignment.
Experimental setup
Builds on: CLIP
Closest papers by meaning
- LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens (CVPR 2026 · similarity 0.90)
- MotionGPT3: Human Motion as a Second Modality (ICLR 2026 · similarity 0.90)
- VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension (ECCV 2026 · similarity 0.90)
- Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models (ECCV 2024 · similarity 0.90)
- MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities (CVPR 2025 · similarity 0.88)
- LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning (ICLR 2025 · similarity 0.88)
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.
