Papers › CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition

CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition

2 Apr 2025arXiv:2504.01666archive 2025-07-28

Sarah Alyami, Hamzah Luqman

Continuous sign language recognition (CSLR) focuses on interpreting and transcribing sequences of sign language gestures in videos. In this work, we propose CLIP sign language adaptation (CLIP-SLA), a novel CSLR framework that leverages the powerful pre-trained visual encoder from the CLIP model to sign language tasks through parameter-efficient fine-tuning (PEFT). We introduce two variants, SLA-Adapter and SLA-LoRA, which integrate PEFT modules into the CLIP visual encoder, enabling fine-tuning with minimal trainable parameters. The effectiveness of the proposed frameworks is validated on four datasets: Phoenix2014, Phoenix2014-T, CSL-Daily, and Isharah-500, where both CLIP-SLA variants outperformed several SOTA models with fewer trainable parameters. Extensive ablation studies emphasize the effectiveness and flexibility of the proposed methods with different vision-language models for CSLR. These findings showcase the potential of adapting large-scale pre-trained models for scalable and efficient CSLR, which pave the way for future advancements in sign language understanding.

PaperPDFCode

Code

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 Recognitionparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sign Language Recognition CSL-Daily SLA-LoRA Word Error Rate (WER) 25.8 #3 of 14 Archive leaderboard report
Sign Language Recognition RWTH-PHOENIX-Weather 2014 SLA-Adapter Word Error Rate (WER) 18.8 #4 of 22 Archive leaderboard report
Sign Language Recognition RWTH-PHOENIX-Weather 2014 T SLA-LoRA Word Error Rate (WER) 19.4 #4 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

CLIP

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