AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training

Yunjiao Zhou, Xinyan Chen, Junlang Qian, Lihua Xie, Jianfei Yang

AAAI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add test-time training with LLM sub-action decomposition (LSP) over no TTT with rule-based segmentation (ablation)ZOMG · HumanML3D groundingmAP: 5.86 -> 22.69Improved
add LLM-guided Language Semantic Partition instead of rule-based segmentation (ablation)ZOMG · HumanML3D groundingmAP: 5.86 -> 10.16Improved
add learnable soft mask [M] in SMO (ablation)ZOMG · HumanML3D groundingmAP: 22.69 -> 38.63Improved
add smoothness loss to soft mask (ablation)ZOMG · HumanML3D groundingmAP: 38.63 -> 41.54Improved
add exclusivity loss to soft mask (ablation)ZOMG · HumanML3D groundingmAP: 38.63 -> 47.28Improved
add both smoothness and exclusivity losses (ablation)ZOMG · HumanML3D groundingmAP: 47.28 -> 50.46Improved
use ZOMG instead of AdaZADmotion grounding · HumanML3D groundingmAP: 41.77 -> 50.46Improved
use ZOMG instead of AdaZADmotion grounding · BABEL groundingmAP: 10.15 -> 13.44Improved
optimize only soft masks with frozen encoder instead of adapter parameterstest-time training efficiency · HumanML3D grounding (TTT, 100 steps)Samples/s: 6.65 -> 23.25Improved
augment retrieval training data with ZOMG-grounded segmentsMESM · HumanML3D retrieval protocol A (T2M)T2M retrieval: 19.20 -> 19.38Improved
augment retrieval training data with ZOMG-grounded segmentsMESM · KIT-ML retrieval protocol B (T2M)T2M retrieval: 43.04 -> 42.04Hurt
add more TTT optimization steps (ablation)ZOMG · HumanML3D groundinggrounding errorImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy