AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding

Hezhen Hu, Weichao Zhao, Wengang Zhou, Houqiang Li

TPAMI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised speech representations · 170 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 self-supervised masked-pose pre-training (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 53.31 -> 62.42Improved
add masked joint modeling (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 53.31 -> 58.44Improved
add masked clip modeling (versus joint or frame only) (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 53.31 -> 61.94Improved
combine joint, frame and clip masking (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 61.94 -> 62.42Improved
add temporal and spatial position encoding (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 51.80 -> 62.42Improved
add spatial position encoding only versus temporal only (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 52.97 -> 60.95Improved
use hand-model-aware decoder instead of 1-layer fc (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 59.88 -> 62.42Improved
replace position encoding with temporal GCN (k=3) (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 62.42 -> 60.21No clear effect
raise masking ratio from 20% to 40% (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 59.52 -> 62.42Improved
raise masking ratio from 40% to 60% (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 62.42 -> 59.80Hurt
use 3 Transformer layers instead of 2 (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 59.20 -> 62.42Improved
increase pose theta dimension from 25 to 35 (ablation)SignBERT+ · MSASL (full)per-instance Top-1: 62.42 -> 61.60Hurt

Later papers that compared with this method

1 later accepted paper reports SignBERT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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