Research map / Video / Video generation
Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction
Guowei Xu, Jiale Tao, Wen Li, Lixin Duan
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 semantic latent directions on top of motion queries (ablation) | SLD (motion queries only) · Human3.6M | ADE: 0.361 -> 0.352 | Improved |
| add semantic latent directions on top of motion queries (ablation) | SLD (motion queries only) · HumanEva-I | APD: 1.562 -> 3.365 | Improved |
| project motion queries into SLD coefficient space (ablation) | MQ+SLD · Human3.6M | ADE: 0.352 -> 0.348 | Improved |
| project motion queries into SLD coefficient space (ablation) | MQ+SLD · HumanEva-I | ADE: 0.202 -> 0.193 | Improved |
| project motion queries into SLD coefficient space (ablation) | MQ+SLD · Human3.6M | APD: 7.936 -> 8.741 | Improved |
| use SLD versus STARS | SLD · Human3.6M | APD: 15.884 -> 8.741 | Hurt |
| use SLD versus HumanMAC | SLD · HumanEva-I | APD: 6.554 -> 4.066 | Hurt |
| orthogonal latent directions instead of Gaussian latent prior | SLD vs generative baselines · Human3.6M | ADE: 0.369 -> 0.348 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HumanMAC — HumanMAC: Masked Motion Completion for Human Motion Prediction (ICCV 2023) · better on 2 of 3 shared results
- Belfusion — BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction (ICCV 2023) · better on 2 of 2 shared results
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
- BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction (ICCV 2023 · similarity 0.89)
- Executing Your Commands via Motion Diffusion in Latent Space (CVPR 2023 · similarity 0.88)
- Progressive Guessing to Fixed Point: Rethinking Human Motion Prediction with Deep Equilibrium Models (CVPR 2026 · similarity 0.88)
- A Neural Temporal Model for Human Motion Prediction (CVPR 2019 · similarity 0.88)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.86)
- HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback (AAAI 2024 · similarity 0.86)
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.
