AI Paper Atlas

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

DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition

Jingmin Zhu, Anqi Zhu, James Bailey, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, Farid Boussaïd, Qiuhong Ke

TPAMI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 2 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 inference-time dynamic refinement (ablation)adaptive alignment model · NTU60 55/5ZSL accuracy: 79.23 -> 88.52 (+9.29)Improved
add inference-time dynamic refinement (ablation)adaptive alignment model · NTU60 48/12ZSL accuracy: 40.99 -> 71.80 (+30.81)Improved
add inference-time dynamic refinement (ablation)adaptive alignment model · NTU120 110/10ZSL accuracy: 71.95 -> 89.06 (+17.11)Improved
add class-balanced memory bank over naive pseudo-labeling (ablation)DynaPURLS refinement · NTU60 48/12ZSL accuracy: 51.60 -> 71.80Improved
naive pseudo-labeling refinement without memory bank (ablation)PURLS baseline · NTU60 55/5ZSL accuracy: 79.22 -> 78.02Hurt
replace static body-part partition with adaptive attention partition (ablation)PURLS-style alignment · NTU60 55/5ZSL accuracy: 76.46 -> 79.23Improved
replace global alignment with multi-granularity alignment (ablation)Shift-GCN encoder, GPT-3 · NTU60 55/5ZSL accuracy: 64.69 -> 79.23Improved
replace global alignment with multi-granularity alignment (ablation)PoseC3D encoder, GPT-3 · NTU60 55/5ZSL accuracy: 63.45 -> 81.14Improved
add temporal-interval alignment to body-part alignment, with refinement (ablation)DynaPURLS · NTU60 48/12ZSL accuracy: 61.46 -> 71.80Improved
use GPT-4 instead of GPT-3 descriptors (ablation)DynaPURLS · NTU60 55/5ZSL accuracy: 79.23 -> 81.53No clear effect
use random instead of identity initialization of refinement parameters (ablation)DynaPURLS · NTU60 55/5ZSL accuracy: 88.52 -> 88.31No clear effect
adapt on full test distribution instead of seen only (ablation)DynaPURLS GZSL · NTU60 48/12unseen accuracy: 36.92 -> 61.81Improved

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.

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

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