AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

CLIP2Pose: Frozen CLIP as Semantic Guide for Domain Adaptive Pose Estimation

Jiawen Li, Fei Jiang, Dandan Zhu, Jinxin Shi, Aimin Zhou

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 0 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 Semantic-Driven Prompt (SDP) (ablation)CLIP2Pose · SURREAL->Human3.6MPCK@0.05 (All): 75.2 -> 77.1Improved
add Semantic Modulation of Visual Features (SMVF) on top of SDP (ablation)CLIP2Pose · SURREAL->Human3.6MPCK@0.05 (All): 77.1 -> 78.7Improved
add Directional Alignment Loss (DAL) (ablation)CLIP2Pose · SURREAL->Human3.6MPCK@0.05 (All): 78.7 -> 79.9Improved
add Semantic-Driven Prompt (SDP) (ablation)CLIP2Pose · RHD->H3DPCK@0.05 (All): 75.8 -> 78.9Improved
add SMVF on top of SDP (ablation)CLIP2Pose · RHD->H3DPCK@0.05 (All): 78.9 -> 81.5Improved
add DAL on top of SDP and SMVF (ablation)CLIP2Pose · RHD->H3DPCK@0.05 (All): 81.5 -> 83.6Improved
use SDP instead of CoOp / CoCoOp prompts (ablation)CLIP2Pose · SURREAL->Human3.6M and RHD->H3DPCK@0.05Improved
vary GCN layers, lambda, token length around optimum (n=3, lambda=0.3, m=10) (ablation)CLIP2Pose · RHD->H3D and SURREAL->Human3.6MPCK@0.05No clear effect
use frozen CLIP prompt guidance vs prior CLIP-based UDA (AD-CLIP)AD-CLIP · SURREAL->Human3.6MPCK@0.05 (All): 75.4 -> 79.9Improved
use CLIP2Pose vs UniFrame in synthetic-to-wildUniFrame · RHD->WBHPCK@0.05 (All): 26.9 -> 31.2Improved
use CLIP2Pose on unseen target domainUniFrame · Train RHD->H3D, test FreiHandPCK@0.05 (All): 47.1 -> 55.2Improved
use CLIP2Pose vs best prior on LSPDA-LLPose · SURREAL->LSPPCK@0.05 (All): 83.5 -> 84.2Improved

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