Research map / Video / Video generation
Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
Yin Wang, Zhiying Leng, Frederick W. B. Li, Shun-Cheng Wu, Xiaohui Liang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add linguistics-structure assisted module (dependency-tree GAT) (ablation) | Fg-T2M · KIT | FID: 1.077 -> 0.571 | Improved |
| add context-aware progressive reasoning module (ablation) | Fg-T2M · KIT | FID: 0.943 -> 0.571 | Improved |
| use word-level cross-attention (CAPR-2) (ablation) | Fg-T2M · KIT | FID: 0.764 -> 0.571 | Improved |
| add sentence-level feature fusion (CAPR-1) (ablation) | Fg-T2M · KIT | FID: 0.652 -> 0.571 | Improved |
| use 3 GAT layers instead of 1 (ablation) | Fg-T2M · KIT | FID: 0.951 -> 0.571 | Improved |
| use 4 GAT layers instead of 3 (ablation) | Fg-T2M · KIT | FID: 0.571 -> 0.636 | Hurt |
| increase fusion weight lambda from 0.1 to 0.5 (ablation) | Fg-T2M · KIT | FID: 0.571 -> 1.086 | Hurt |
| use Fg-T2M instead of MotionDiffuse on fine-grained test split | Fg-T2M · Harder-HumanML3D | FID: 0.732 -> 0.421 | Improved |
| Fg-T2M versus T2M-GPT on HumanML3D FID | Fg-T2M · HumanML3D test | FID: 0.116 (T2M-GPT) vs 0.243 (Fg-T2M) | Mixed |
Later papers that compared with this method
5 later accepted papers report FG-T2M++ as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation (TPAMI 2026 · better on 1 of 1 shared result)
- Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation (IJCV 2025 · better on 6 of 6 shared results)
- FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing (ICCV 2025 · better on 2 of 2 shared results)
- MMM: Generative Masked Motion Model (CVPR 2024 · better on 0 of 1 shared result)
- ParCo: Part-Coordinating Text-to-Motion Synthesis (ECCV 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TEMOS — TEMOS: Generating Diverse Human Motions from Textual Descriptions (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation (IJCV 2025 · similarity 0.92)
- Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs (NeurIPS 2023 · similarity 0.91)
- Text-to-Motion Generation With Discrete Representations and Large Language Models (TPAMI 2026 · similarity 0.91)
- Generating Diverse and Natural 3D Human Motions From Text (CVPR 2022 · similarity 0.90)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.88)
- MMM: Generative Masked Motion Model (CVPR 2024 · 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.
