SOTAVerified

Sign Language Translation

Given a video containing sign language, the task is to predict the translation into (written) spoken language.

Image credit: How2Sign

Papers

Showing 125 of 153 papers

TitleStatusHype
An Open-Source American Sign Language Fingerspell Recognition and Semantic Pose Retrieval InterfaceCode2
Uni-Sign: Toward Unified Sign Language Understanding at ScaleCode2
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language TranslationCode2
Signformer is all you need: Towards Edge AI for Sign LanguageCode1
Machine Translation between Spoken Languages and Signed Languages Represented in SignWritingCode1
SignBank+: Preparing a Multilingual Sign Language Dataset for Machine Translation Using Large Language ModelsCode1
Gloss-Free End-to-End Sign Language TranslationCode1
Event Stream based Sign Language Translation: A High-Definition Benchmark Dataset and A New AlgorithmCode1
Frozen Pretrained Transformers for Neural Sign Language TranslationCode1
Gloss Attention for Gloss-free Sign Language TranslationCode1
ISLTranslate: Dataset for Translating Indian Sign LanguageCode1
LSA-T: The first continuous Argentinian Sign Language dataset for Sign Language TranslationCode1
Multi-Stream Keypoint Attention Network for Sign Language Recognition and TranslationCode1
Open-Domain Sign Language Translation Learned from Online VideoCode1
A Simple Multi-Modality Transfer Learning Baseline for Sign Language TranslationCode1
An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMsCode1
CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal CorrelationCode1
Cross-modality Data Augmentation for End-to-End Sign Language TranslationCode1
Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal AlignmentCode1
Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language TranslationCode1
An Open-Source Gloss-Based Baseline for Spoken to Signed Language TranslationCode1
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language TranslationCode1
How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign LanguageCode1
Improving Gloss-free Sign Language Translation by Reducing Representation DensityCode1
Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data AugmentationCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MSKA-SLTBLEU-429.03Unverified
2TwoStream-SLTBLEU-428.95Unverified
3SignBERT+BLEU-425.7Unverified
4S2T Stochastic Transformer (Ens)BLEU-425.59Unverified
5STMC+Transformer (Ens)BLEU-425.4Unverified
6BN-TIN-Transf.+SignBTBLEU-424.32Unverified
7SignformerBLEU-423.43Unverified
8BERT2RNDBLEU-422.47Unverified
9BN-TIN-Transf.BLEU-421.68Unverified
10BERT2BERTBLEU-421.26Unverified
#ModelMetricClaimedVerifiedStatus
1TwoStream-SLTBLEU-425.79Unverified
2MSKA-SLTBLEU-425.52Unverified
3MMTLBBLEU-423.92Unverified
4XmDABLEU-421.58Unverified
5BN-TIN-Transf.+SignBTBLEU-421.34Unverified
6IP-SLTBLEU-416.72Unverified
7ConSLTBLEU-414.53Unverified
8BN-TIN-Transf.BLEU-413.19Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer Ens.BLEU-482.87Unverified
#ModelMetricClaimedVerifiedStatus
1BLEU8.03Unverified
#ModelMetricClaimedVerifiedStatus
1Keypoints-Transformer-UNLPWord Error Rate (WER)0.94Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer BaselineBLEU-44.14Unverified