AI Paper Atlas

Research map / Video / Action recognition

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

Tingbing Yan, Wenzheng Zeng, Yang Xiao, Xingyu Tong, Bo Tan, Zhiwen Fang, Zhiguo Cao, Joey Tianyi Zhou

ECCV 2024 · Video › Action recognition · approach: Skeleton-based action recognition · 15 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 CrossGLG to MotionBERTMotionBERT · NTU 120 one-shot (20 base classes)accuracy: 35.5 -> 51.0Improved
add CrossGLG to InfoGCNInfoGCN · NTU 120 one-shot (100 base classes)accuracy: 56.1 -> 62.6Improved
add CrossGLG to HDGCNHDGCN · NTU 120 one-shot (20 base classes)accuracy: 39.0 -> 43.0Improved
add GAP text-guided contrastive method designed for full supervisionInfoGCN · NTU 120 one-shot (20 base classes)accuracy: 37.0 -> 35.06Hurt
add CrossGLG to InfoGCN on NTU 60 with 10 base classesInfoGCN · NTU 60 one-shot (10 base classes)accuracy: 51.1 -> 57.9Improved
InfoGCN+CrossGLG vs MotionBERT on NTU 60 with 10 base classesInfoGCN+CrossGLG · NTU 60 one-shot (10 base classes)accuracy: 58.3 -> 57.9Hurt
add CrossGLG to InfoGCN on KineticsInfoGCN · Kinetics one-shot (20 base classes)accuracy: 13.3 -> 17.4Improved
add global-to-local textual guidance (JID with calibration loss) (ablation)InfoGCN · NTU 120 one-shot (20 base classes)accuracy: 37 -> 43.3Improved
add local-to-global cross-modal interaction (ablation)InfoGCN · NTU 120 one-shot (20 base classes)accuracy: 37 -> 42.5Improved
place JID after the 5th block rather than the 9th (ablation)InfoGCN + G2L · NTU 120 one-shot (20 base classes)accuracy: 38.7 -> 43.3Improved
add text-text self-attention in interaction block (ablation)InfoGCN + L2G · NTU 120 one-shot (80 base classes)accuracy: 49.6 -> 60.1Improved
swap ChatGPT for Gemini or Qwen to generate text descriptions (ablation)CrossGLG · NTU 120 one-shot (20 base classes)accuracy: 45.3 / 45.2 / 45.7No clear effect

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