Papers › Sign Pose-Based Transformer for Word-Level Sign Language Recognition

Sign Pose-Based Transformer for Word-Level Sign Language Recognition

4 Jan 2022WACV 2022 1archive 2025-07-28

Matyáš Boháček, Marek Hrúz

In this paper we present a system for word-level sign language recognition based on the Transformer model. We aim at a solution with low computational cost, since we see great potential in the usage of such recognition system on handheld devices. We base the recognition on the estimation of the pose of the human body in the form of 2D landmark locations. We introduce a robust pose normalization scheme which takes the signing space in considerationand processes the hand poses in a separate local coordinate system, independent on the body pose. We show experimentally the significant impact of this normalization on the accuracy of our proposed system. We introduce several augmentations of the body pose that further improve the accuracy, including a novel sequential joint rotation augmentation. With all the systems in place, we achieve state of theart top-1 results on the WLASL and LSA64 datasets. For WLASL, we are able to successfully recognize 63.18% of sign recordings in the 100-gloss subset, which is a relative improvement of 5% from the prior state of the art. For the 300-gloss subset, we achieve recognition rate of 43.78% which is a relative improvement of 3.8%. With the LSA64 dataset, we report test recognition accuracy of 100%.

PaperPDFCode

Code

matyasbohacek/spoter pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Sign Language Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sign Language Recognition LSA64 SPOTER Accuracy (%) 100 #1 of 5 Archive leaderboard report
Sign Language Recognition WLASL100 SPOTER Official Test Split true #7 of 7 Archive leaderboard report
Sign Language Recognition WLASL100 SPOTER Top-1 Accuracy 63.18 #7 of 7 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.

Methods

Absolute Position EncodingsAdamAttentionBASEBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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