Research map / Vision-language and multimodal / Human and embodied modeling
SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval
Jiahang Zhang, Lilang Lin, Shuai Yang, Jiaying Liu
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 SGAR, a structural generative augmentation approach for 3D human motion-text retrieval that targets fine-grained concept alignment (abstract only available).
Problem
3D human motion-text retrieval suffers from sub-optimal generalization because global motion-text alignment struggles with correspondence between multiple motion concepts coupled in one motion or text sequence.
Approach
Studies explicit fine-grained concept decomposition and alignment for motion-text retrieval, using structural generative augmentation to address correspondence uncertainty; full method details unavailable beyond the abstract.
Closest papers by meaning
- ReMoGPT: Part-Level Retrieval-Augmented Motion-Language Models (AAAI 2025 · similarity 0.91)
- Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning (ICML 2026 · similarity 0.91)
- GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation (ICCV 2025 · similarity 0.89)
- Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation (CVPR 2026 · similarity 0.88)
- Tri-Modal Motion Retrieval by Learning a Joint Embedding Space (CVPR 2024 · similarity 0.88)
- VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models (NeurIPS 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.
