Papers › C2SLR: Consistency-Enhanced Continuous Sign Language Recognition

C2SLR: Consistency-Enhanced Continuous Sign Language Recognition

1 Jan 2022CVPR 2022 1archive 2025-07-28

Ronglai Zuo, Brian Mak

The backbone of most deep-learning-based continuous sign language recognition (CSLR) models consists of a visual module, a sequential module, and an alignment module. However, such CSLR backbones are hard to be trained sufficiently with a single connectionist temporal classification loss. In this work, we propose two auxiliary constraints to enhance the CSLR backbones from the perspective of consistency. The first constraint aims to enhance the visual module, which easily suffers from the insufficient training problem. Specifically, since sign languages convey information mainly with signers' faces and hands, we insert a keypoint-guided spatial attention module into the visual module to enforce it to focus on informative regions, i.e., spatial attention consistency. Nevertheless, only enhancing the visual module may not fully exploit the power of the backbone. Motivated by that both the output features of the visual and sequential modules represent the same sentence, we further impose a sentence embedding consistency constraint between them to enhance the representation power of both the features. Experimental results over three representative backbones validate the effectiveness of the two constraints. More remarkably, with a transformer-based backbone, our model achieves state-of-the-art or competitive performance on three benchmarks, PHOENIX-2014, PHOENIX-2014-T, and CSL.

PaperPDFCode

Code

2000zrl/lcsa_c2slr_srm officialpytorch 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

SentenceSentence EmbeddingSentence-EmbeddingSign Language Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sign Language Recognition RWTH-PHOENIX-Weather 2014 C2SLR Word Error Rate (WER) 20.4 #9 of 22 Archive leaderboard report
Sign Language Recognition RWTH-PHOENIX-Weather 2014 T C2SLR Word Error Rate (WER) 20.4 #7 of 15 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

Average PoolingCSLConvolutionMax PoolingSigmoid Activation

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