AI Paper Atlas

Research map / Video / Action recognition

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

Yuxiao Chen, Long Zhao, Jianbo Yuan, Yu Tian, Zhaoyang Xia, Shijie Geng, Ligong Han, Dimitris N. Metaxas

ECCV 2022 · Video › Action recognition · approach: Skeleton-based action recognition · 65 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 frame-level (F-TRS) pre-training (ablation)Hi-TRS random init · NTU-60 xsub (supervised)top-1 accuracy: 79.6 -> 80.8Improved
add clip-level (C-TRS) pre-training (ablation)Hi-TRS random init · NTU-60 xsub (supervised)top-1 accuracy: 79.6 -> 81.1Improved
add video-level (V-TRS) pre-training (ablation)Hi-TRS random init · NTU-60 xsub (supervised)top-1 accuracy / MPJPE: 79.6 -> 82.0 accuracy, 98.4 -> 88.1 MPJPEImproved
add clip-level pre-training to frame-level (ablation)Hi-TRS pre-trained at F · NTU-60 xsub (supervised)top-1 accuracy: 80.8 -> 83.9Improved
add video-level pre-training to F+C (ablation)Hi-TRS pre-trained at F+C · NTU-60 xsub (supervised)top-1 accuracy: 83.9 -> 86.0Improved
pre-train on all three levels instead of F+V (ablation)Hi-TRS · NTU-60 xsub (supervised)MPJPE: 87.4 -> 85.6Improved
add video-level pre-training to F+C for detection (ablation)Hi-TRS · PKUMMD Part I action detectionmAP_a / mAP_v: mAP_a 55.6 -> 58.4, mAP_v 65.1 -> 66.3Improved
add F+C pre-training for detection (ablation)Hi-TRS random init · PKUMMD Part I action detectionmAP_a / mAP_v: mAP_a 53.4 -> 55.6, mAP_v 63.2 -> 65.1Improved
pre-train on NTU-60 then fine-tune on PKU Part IIHi-TRS random init · PKUMMD Part II (transfer)MPJPE / accuracy: MPJPE 105.4 -> 94.2, accuracy 50.9 -> 55.0Improved
pre-train on larger NTU-120 instead of NTU-60Hi-TRS · PKUMMD Part I (transfer)mAP_a / mAP_v: mAP_a 55.2 -> 57.9, mAP_v 66.6 -> 67.3Improved
fuse three streams (joint, motion, bone) instead of single streamHi-TRS · NTU-60 xsub (supervised)top-1 accuracy: 86.0 -> 90.0Improved
use only 1% labeled data vs strong baselinesHi-TRS · NTU-60 xsub semi-supervised (1%)top-1 accuracy: Hi-TRS 39.1 vs SCC-3S 48.3, CrosSCLR-3S 51.1Hurt

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