SOTAVerified

Sign Language Recognition

Sign Language Recognition is a computer vision and natural language processing task that involves automatically recognizing and translating sign language gestures into written or spoken language. The goal of sign language recognition is to develop algorithms that can understand and interpret sign language, enabling people who use sign language as their primary mode of communication to communicate more easily with non-signers.

( Image credit: Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison )

Papers

Showing 1–50 of 297 papers

TitleStatusHype
Hierarchical Sub-action Tree for Continuous Sign Language RecognitionCode0
SignBart -- New approach with the skeleton sequence for Isolated Sign language RecognitionCode0
SLRNet: A Real-Time LSTM-Based Sign Language Recognition SystemCode0
Fine-Tuning Video Transformers for Word-Level Bangla Sign Language: A Comparative Analysis for Classification Tasks—0
Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign LanguageCode0
Enhancing Mathematics Learning for Hard-of-Hearing Students Through Real-Time Palestinian Sign Language Recognition: A New Dataset—0
Logos as a Well-Tempered Pre-train for Sign Language Recognition—0
HandReader: Advanced Techniques for Efficient Fingerspelling RecognitionCode0
TSLFormer: A Lightweight Transformer Model for Turkish Sign Language Recognition Using Skeletal Landmarks—0
Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition—0
SignX: The Foundation Model for Sign Recognition—0
Breaking the Barriers: Video Vision Transformers for Word-Level Sign Language Recognition—0
CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language RecognitionCode0
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language RecognitionCode1
OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition—0
BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)—0
Representing Signs as Signs: One-Shot ISLR to Facilitate Functional Sign Language Technologies—0
Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognitionCode1
Exploiting Ensemble Learning for Cross-View Isolated Sign Language RecognitionCode0
Uni-Sign: Toward Unified Sign Language Understanding at ScaleCode2
Survey on Hand Gesture Recognition from Visual Input—0
Revolutionizing Communication with Deep Learning and XAI for Enhanced Arabic Sign Language Recognition—0
Comparison of Autoencoders for tokenization of ASL datasets—0
VSNet: Focusing on the Linguistic Characteristics of Sign Language—0
Beyond Words: AuralLLM and SignMST-C for Precise Sign Language Production and Bidirectional Accessibility—0
Training Strategies for Isolated Sign Language Recognition—0
Real-time Sign Language Recognition Using MobileNetV2 and Transfer Learning—0
EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Based Transformers for Accurate Recognition of Bangla Word-Level Sign LanguageCode0
SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction—0
AzSLD: Azerbaijani Sign Language Dataset for Fingerspelling, Word, and Sentence Translation with Baseline SoftwareCode0
Continuous Sign Language Recognition System using Deep Learning with MediaPipe Holistic—0
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset—0
Bukva: Russian Sign Language AlphabetCode0
Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models—0
A Chinese Continuous Sign Language Dataset Based on Complex Environments—0
Deep Neural Network-Based Sign Language Recognition: A Comprehensive Approach Using Transfer Learning with Explainability—0
1DCNNTrans: BISINDO Sign Language Interpreters in Improving the Inclusiveness of Public Services—0
SCOPE: Sign Language Contextual Processing with Embedding from LLMsCode0
Bengali Sign Language Recognition through Hand Pose Estimation using Multi-Branch Spatial-Temporal Attention Model—0
BAUST Lipi: A BdSL Dataset with Deep Learning Based Bangla Sign Language Recognition—0
Scaling up Multimodal Pre-training for Sign Language Understanding—0
Sign language recognition based on deep learning and low-cost handcrafted descriptorsCode0
SLVideo: A Sign Language Video Moment Retrieval Framework—0
Hierarchical Windowed Graph Attention Network and a Large Scale Dataset for Isolated Indian Sign Language RecognitionCode1
EvSign: Sign Language Recognition and Translation with Streaming Events—0
A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production—0
Sign Language Recognition Based On Facial Expression and Hand Skeleton—0
SignCLIP: Connecting Text and Sign Language by Contrastive LearningCode1
A Transformer-Based Multi-Stream Approach for Isolated Iranian Sign Language Recognition—0
Continuous Sign Language Recognition Using Intra-inter Gloss Attention—0
Show:102550
← PrevPage 1 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SubUNetsWord Error Rate (WER)40.7—Unverified
2CTF-MMWord Error Rate (WER)37.8—Unverified
3DTNWord Error Rate (WER)36.5—Unverified
4SANWord Error Rate (WER)29.7—Unverified
5Stochastic CSLRWord Error Rate (WER)25.3—Unverified
6CrossModalWord Error Rate (WER)24—Unverified
7SLRGANWord Error Rate (WER)23.4—Unverified
8DNFWord Error Rate (WER)22.86—Unverified
9VACWord Error Rate (WER)22.1—Unverified
10MSKA-SLRWord Error Rate (WER)22.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Stochastic CSLRWord Error Rate (WER)26.1—Unverified
2CrossModalWord Error Rate (WER)24.3—Unverified
3SignBTWord Error Rate (WER)23.9—Unverified
4MMTLBWord Error Rate (WER)22.45—Unverified
5SMKDWord Error Rate (WER)22.4—Unverified
6STMCWord Error Rate (WER)21—Unverified
7WRNN + LETWord Error Rate (WER)20.73—Unverified
8MSKA-SLRWord Error Rate (WER)20.5—Unverified
9C2SLRWord Error Rate (WER)20.4—Unverified
10SignBERT+Word Error Rate (WER)19.9—Unverified
#ModelMetricClaimedVerifiedStatus
1BN-TIN+Transf.Word Error Rate (WER)33.1—Unverified
2C2SLRWord Error Rate (WER)31—Unverified
3SENWord Error Rate (WER)30.7—Unverified
4AdaBrowseWord Error Rate (WER)30.6—Unverified
5CorrNetWord Error Rate (WER)30.1—Unverified
6CTCAWord Error Rate (WER)29.4—Unverified
7TCNetWord Error Rate (WER)29.3—Unverified
8CorrNet+ACDRWord Error Rate (WER)29—Unverified
9MSKA-SLRWord Error Rate (WER)27.8—Unverified
10Swin-MSTPWord Error Rate (WER)27.1—Unverified
#ModelMetricClaimedVerifiedStatus
1STF+LSTMRank-1 Recognition Rate0.99—Unverified
2SAM-SLR (RGB-D)Rank-1 Recognition Rate0.99—Unverified
33D-DCNN + ST-MGCNRank-1 Recognition Rate0.98—Unverified
4Ensemble - NTISRank-1 Recognition Rate0.96—Unverified
5HWGATRank-1 Recognition Rate0.96—Unverified
6MViT-SLRRank-1 Recognition Rate0.96—Unverified
7FE+LSTMRank-1 Recognition Rate0.93—Unverified
8VTN-PFRank-1 Recognition Rate0.93—Unverified
9CNN+FPM+BLSTM+Attention (RGB-D)Rank-1 Recognition Rate0.62—Unverified
#ModelMetricClaimedVerifiedStatus
1Logos-PretrainingTop-1 Accuracy66.82—Unverified
2Uni-SignTop-1 Accuracy63.52—Unverified
3NLA-SLRTop-1 Accuracy61.26—Unverified
4StepNetTop-1 Accuracy61.17—Unverified
5SAM-SLRTop-1 Accuracy58.73—Unverified
6SWIN-SLRTop-1 Accuracy58.51—Unverified
7HWGATTop-1 Accuracy48.49—Unverified
8I3D (pretraining: BSL-1K)Top-1 Accuracy46.82—Unverified
9I3DTop-1 Accuracy32.48—Unverified
#ModelMetricClaimedVerifiedStatus
1Uni-SignTop-1 Accuracy92.25—Unverified
2SiformerTop-1 Accuracy86.5—Unverified
3SignBERTTop-1 Accuracy83.3—Unverified
4I3D, ST-GCNTop-1 Accuracy81.38—Unverified
5StepNetTop-1 Accuracy78.29—Unverified
6I3DTop-1 Accuracy65.89—Unverified
7SPOTERTop-1 Accuracy63.18—Unverified
#ModelMetricClaimedVerifiedStatus
1HandReader_RGBCER (%)30.7—Unverified
2HandReader_KPCER (%)28—Unverified
3HandReader_RGBCER (%)27.6—Unverified
4HandReader_RGB_KPCER (%)27.1—Unverified
5HandReader_KPCER (%)26.2—Unverified
6HandReader_RGB+KPCER (%)24.4—Unverified
#ModelMetricClaimedVerifiedStatus
1SPOTERAccuracy (%)100—Unverified
2SiformerAccuracy (%)99.84—Unverified
3HWGATAccuracy (%)98.59—Unverified
4Bag of words fusion of hand pose/movement/positionAccuracy (%)97—Unverified
53DGCNAccuracy (%)94.84—Unverified
#ModelMetricClaimedVerifiedStatus
1HandReader_RGBCER (%)7.61—Unverified
2HandReader_KPCER (%)7.35—Unverified
3HandReader_RGB_KPCER (%)5.06—Unverified
#ModelMetricClaimedVerifiedStatus
1Uni-SignP-I Top-1 Accuracy78.16—Unverified
2SignBERT+P-I Top-1 Accuracy73.71—Unverified
#ModelMetricClaimedVerifiedStatus
1StepNetTop-1 Accuracy61.17—Unverified
2SignBERT+Top-1 Accuracy55.59—Unverified
#ModelMetricClaimedVerifiedStatus
1StepNetActions Top-177.1—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileNetV2_TSMAccuracy (Top-1)83.6—Unverified
#ModelMetricClaimedVerifiedStatus
1HWGATTop-1 Accuracy93.86—Unverified
#ModelMetricClaimedVerifiedStatus
13D-DCNN + ST-MGCNRank-1 Recognition Rate0.98—Unverified
#ModelMetricClaimedVerifiedStatus
1Skeleton Image RepresentationAccuracy82—Unverified
#ModelMetricClaimedVerifiedStatus
1Skeleton Image RepresentationAccuracy93—Unverified
#ModelMetricClaimedVerifiedStatus
1mVITv2-SMean Accuracy64.09—Unverified