AI Paper Atlas

Research map / 3D vision / Human pose estimation

PoseScript: Linking 3D Human Poses and Natural Language

Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Grégory Rogez

TPAMI 2024 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 10 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
pretrain retrieval model on automatic captions before finetuning on human captions (ablation)text-to-pose retrieval (GloVe-biGRU) · PoseScript-H testmRecall: 23.0 -> 40.9Improved
use transformer text encoder instead of GloVe-biGRU (ablation)retrieval pretrain+FT · PoseScript-H testmRecall: 40.9 -> 43.3Improved
add mirroring augmentation (ablation)retrieval with transformer encoder · PoseScript-H testmRecall: 43.3 -> 45.3Improved
train only on automatic captions and test on human captionsretrieval · PoseScript-H testmRecall: 72.8 -> 5.9Hurt
add L_reg KL regularization to generative model (ablation)text-conditioned pose VAE · PoseScript-A testFID: 0.12 -> 0.07Improved
add L_reg to generative model (ablation)text-conditioned pose VAE · PoseScript-A testmRecall G/R: 41.5 -> 40.0No clear effect
pretrain generative model on PoseScript-A (ablation)text-conditioned pose VAE · PoseScript-H testFID: 0.29 -> 0.04Improved
pretrain generative model on PoseScript-A (ablation)text-conditioned pose VAE · PoseScript-H testmRecall R/G: 5.2 -> 19.5Improved
use transformer text encoder in generative model (ablation)text-conditioned pose VAE · PoseScript-H testmRecall R/G: 19.5 -> 35.6Improved
add mirroring augmentation to generative model (ablation)text-conditioned pose VAE · PoseScript-H testmRecall R/G: 35.6 -> 37.5Improved
pretrain captioning model on automatic captions (ablation)pose description generator · PoseScript-H testR-Precision R@1: 24.39 -> 88.09Improved
add mirroring augmentation to captioning model (ablation)pose description generator · PoseScript-H testBLEU-4: 13.07 -> 13.22Improved

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