Papers › SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
Hezhen Hu, Weichao Zhao, Wengang Zhou, Houqiang Li
Hand gesture serves as a crucial role during the expression of sign language. Current deep learning based methods for sign language understanding (SLU) are prone to over-fitting due to insufficient sign data resource and suffer limited interpretability. In this paper, we propose the first self-supervised pre-trainable SignBERT+ framework with model-aware hand prior incorporated. In our framework, the hand pose is regarded as a visual token, which is derived from an off-the-shelf detector. Each visual token is embedded with gesture state and spatial-temporal position encoding. To take full advantage of current sign data resource, we first perform self-supervised learning to model its statistics. To this end, we design multi-level masked modeling strategies (joint, frame and clip) to mimic common failure detection cases. Jointly with these masked modeling strategies, we incorporate model-aware hand prior to better capture hierarchical context over the sequence. After the pre-training, we carefully design simple yet effective prediction heads for downstream tasks. To validate the effectiveness of our framework, we perform extensive experiments on three main SLU tasks, involving isolated and continuous sign language recognition (SLR), and sign language translation (SLT). Experimental results demonstrate the effectiveness of our method, achieving new state-of-the-art performance with a notable gain.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Sign Language Recognition | MSASL-1000 | SignBERT+ | P-C Top-1 Accuracy | 70.77 | #2 of 2 | Archive leaderboard | report |
| Sign Language Recognition | MSASL-1000 | SignBERT+ | P-I Top-1 Accuracy | 73.71 | #2 of 2 | Archive leaderboard | report |
| Sign Language Recognition | RWTH-PHOENIX-Weather 2014 | SignBERT+ | Word Error Rate (WER) | 20 | #7 of 22 | Archive leaderboard | report |
| Sign Language Recognition | RWTH-PHOENIX-Weather 2014 T | SignBERT+ | Word Error Rate (WER) | 19.9 | #6 of 15 | Archive leaderboard | report |
| Sign Language Recognition | WLASL | SignBERT+ | Top-1 Accuracy | 55.59 | #2 of 2 | Archive leaderboard | report |
| Sign Language Translation | RWTH-PHOENIX-Weather 2014 T | SignBERT+ | BLEU-4 | 25.7 | #3 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections