Open-Sign-Language

This repository is all you need for Sign Language Study!

📌 This project is licensed under the Apache License 2.0 – see the LICENSE file for details.

📝 Table of Contents

• Datasets
• Papers
  • Survey Papers
  • SLR Papers
  • SLT Papers
  • SLP Papers
• Leaderboard
  • SLR Leaderboard
  • SLT Leaderboard
  • SLP Leaderboard
• Challenge & Workshop

🔍 Datasets

• Please refer to this page for more information.

Commonly Used Fingerspelling Datasets

Dataset	Year	Language	#Samples	#Signers	Domain
ChicagoFSWild	2018	American	7304 sequences	168	Letters + Char
ChicagoFSWild+	2019	American	55,232 sequences	260	Letters + Char
ArASL	2019	Arabic	54,049 images	40	Letters
RWTH-FingerSpelling	2006	German	1,400 image sequences	20	Letters + Umlauts + Number

Commonly Used Isolated Datasets

Dataset	Year	Language	#Samples	#Signers	Domain
Purdue RVL-SLLL	2002	American	2,576 video clips	14	Motion primitives + Handshapes + General
Boston ASLLVD	2008	American	9,800 tokens	6	General
MS-ASL	2018	American	25,513 videos	222	General
WLASL	2019	American	21,083 videos	119	General
ASL-100-RGBD	2020	American	~4,150 tokens	22	General
ASL Citizen	2023	American	83,399 videos	52	General
LSA-64	2016	Argentina	3,200 video sequences	10	Dictionary

Commonly Used Continuous Datasets

Dataset	Year	Language	#Samples	#Signers	Domain
RWTH-Boston-104	2007	American	201 sentences	3	General
How2Sign	2020	American	>35k sentences	11	General
OpenASL	2022	American	-	~220	General
YouTube-ASL	2023	American	-	>2500	General
DailyMoth-70h	2024	American	48,386 clips	1	News
BOBSL	2021	British	1.2M sequences	39	General
CSL-Daily	2021	Chinese	20,645 videos	10	General
RWTH-PHOENIX 2012	2012	Germany	1,980 sentences	7	Weather
RWTH-PHOENIX 2014	2014	Germany	6,861 sentences	9	Weather
RWTH-PHOENIX14T	2020	Germany	8,257 sentences	9	Weather

📜 Papers

Survey Papers

---

Datasets Survey Papers

2022

Journal

• [LREC 2022] Challenges with sign language datasets for sign language recognition and translation. Paper

---

SLR Survey Papers

2024

Journal

• [Information Processing & Management] Reviewing 25 years of continuous sign language recognition research: Advances, challenges, and prospects. Paper
• [IEEE Access] Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges. Paper
• [Advanced Robotics] A Review of Deep Learning-Based Approaches to Sign Language Processing. Paper

2023

Conference

• [ICCV] Unraveling a Decade: A Comprehensive Survey on Isolated Sign Language Recognition. Paper
• [ICCMC] A Extensive Survey on Sign Language Recognition Methods. Paper

Journal

• [ACM TALLIP] State of the Art of Automation in Sign Language: A Systematic Review. Paper

2022

Arxiv

• [Arxiv] A Comprehensive Review of Sign Language Recognition: Different Types, Modalities, and Datasets. Paper

Journal

• [Meas. Sens.] Survey on sign language recognition in context of vision-based and deep learning. Paper
• [Open Comput. Sci.] Sign language identification and recognition: A comparative study. Paper
• [IEEE Access] Technological Solutions for Sign Language Recognition: A Scoping Review of Research Trends, Challenges, and Opportunities. Paper

2021

Conference

• [ICITIIT] ML Based Sign Language Recognition System. Paper

Journal

• [ScienceDirect] Sign Language Recognition: A Deep Survey. Paper
• [Sensors] Artificial Intelligence Technologies for Sign Language. Paper
• [IEEE Access] Deep Learning for Sign Language Recognition: Current Techniques, Benchmarks, and Open Issues. Paper
• [ISA] Machine Learning Methods for Sign Language Recognition: A Critical Review and Analysis. Paper

2020

Conference

• [INOCON] Sign Language Recognition Techniques- A Review. Paper

Journal

• [Arab. J. Sci. Eng.] A Survey on Artificial Intelligence in Chinese Sign Language Recognition. Paper
• [J. Eng. Appl. Sci.] Advances, challenges and opportunities in continuous sign language recognition. Paper
• [MTA] Understanding Vision-Based Continuous Sign Language Recognition. Paper
• [EAAI] A Comprehensive Survey and Taxonomy of Sign Language Research. Paper

Arxiv

• [Arxiv] Quantitative Survey of the State of the Art in Sign Language Recognition. Paper

2019

Journal

• [IEEE] Technical approaches to Chinese sign language processing: A review. Paper
• [Arch. Comput. Methods Eng.] Sign Language Recognition Systems: A Decade Systematic Literature Review. Paper
• [Int. J. Mach. Learn. & Cyber.] A review of hand gesture and sign language recognition techniques. Paper

Earlier

Journal

• [IEEE] Automatic sign language recognition: A survey. Paper
• [ARPN] SIGN LANGUAGE RECOGNITION: STATE OF THE ART. Paper

---

SLT Survey Papers

2024

Journal

• [Advanced Robotics] A Review of Deep Learning-Based Approaches to Sign Language Processing. Paper

2023

ArXiv

• [ArXiv] From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation. Paper

Journal

• [Research in Computing Science] A Comprehensive Review of Sign Language Translation Technologies Using Linguistic Approaches. Paper
• [Electronics] Sign Language Translation: A Survey of Approaches and Techniques. Paper
• [Expert Syst. Appl.] A survey on Sign Language machine translation. Paper
• [ACM TALLIP] State of the Art of Automation in Sign Language: A Systematic Review. Paper
• [Univ. Access Inf. Soc.] Machine translation from text to sign language: a systematic review. Paper

2021

Journal

• [Sensors] Artificial Intelligence Technologies for Sign Language. Paper

---

SLP Survey Papers

2024

Journal

• [ACM TALLIP] A Comprehensive Review of Sign Language Production. Paper
• [Expert Syst. Appl.] A survey on recent advances in Sign Language Production. Paper
• [Advanced Robotics] A Review of Deep Learning-Based Approaches to Sign Language Processing. Paper

2023

Journal

• [ACM TALLIP] State of the Art of Automation in Sign Language: A Systematic Review. Paper
• [Univ. Access Inf. Soc.] Machine translation from text to sign language: a systematic review. Paper

2022

ArXiv

• [ArXiv] All You Need In Sign Language Production. Paper

2021

Conference

• [CVPR] Sign Language Production: A Review. Paper

Journal

• [Sensors] Artificial Intelligence Technologies for Sign Language. Paper

---

SLR Papers

2025

Conference

• [WACV] Sign Language Recognition: A Large-Scale Multi-View Dataset and Comprehensive Evaluation. Paper
• [ICLR] UNI-SIGN: TOWARD UNIFIED SIGN LANGUAGE UNDERSTANDING AT SCALE. Paper
• [IEEE] Continuous Sign Language Recognition With Multi-Scale Spatial-Temporal Feature Enhancement. Paper
• [CVPR] CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition. Paper
• [CVPR] Cross-Modal Consistency Learning for Sign Language Recognition. Paper
• [ICCV] Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement. Paper

Journal

• [MVA] MAM-FSD Continuous Sign Language Recognition Based on Motor Attention Mechanism and Frame-Level Self-Distillation. Paper
• [FO] Mamba vision models: Automated American sign language recognition. Paper
• [SN] Empowering deaf communication: a novel LSTM model for recognizing Indonesian sign language. Paper
• [ICPR] EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Based Transformers for Accurate Recognition of Bangla Word-Level Sign Language. Paper
• [Neurocomputing] Swin-MSTP Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognition. Paper
• [Scientific Reports] Improved feature reduction framework for sign language recognition using autoencoders and adaptive Grey Wolf Optimization. Paper
• [MDPI] Real-Time Norwegian Sign Language Recognition Using MediaPipe and LSTM. Paper

ArXiv

• [ArXiv] SSLR SSLR: A Semi-Supervised Learning Method for Isolated Sign Language Recognition. Paper
• [ArXiv] TSLFormer: A Lightweight Transformer Model for Turkish Sign Language Recognition Using Skeletal Landmarks. Paper
• [ArXiv] SignX: The Foundation Model for Sign Recognition. Paper

2024

Conference

• [CVPR] SignGraph SignGraph: A Sign Sequence is Worth Graphs of Nodes. Paper | Code
• [ICEECT] SLRMPCMC SLRMPCMC: Sign Language Recognition using Mediapipe and Cross-Model Comparison. Paper
• [ICME] XMC Cross-Modality Consistency Mining for Continuous Sign Language Recognition with Text-Domain Equivalents. Paper

Journal

• [PR] Scalable Frame Resolution for Efficient Continuous Sign Language Recognition. Paper
• [ACM TOMM] SRM Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal. Paper | Code
• [TALLIP] Isolated Arabic Sign Language Recognition Using a Transformer-based Model and Landmark Keypoints. Paper
• [IFS] SLR-YOLO SLR-YOLO: An Improved YOLOv8 Network for Real-Time Sign Language Recognition. Paper
• [AJSE] CRKD Continuous Sign Language Recognition Based on Cross-Resolution Knowledge Distillation. Paper

ArXiv

• [ArXiv] SignVTCL SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning. Paper

2023

Conference

• [AAAI] SEN Self-Emphasizing Network for Continuous Sign Language Recognition. Paper
• [ACM MM] AdaBrowse AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition. Paper
• [ICASSP] DFConv Self-Sufficient Framework for Continuous Sign Language Recognition. Paper
• [CVPR] CorrNet Continuous Sign Language Recognition with Correlation Network. Paper | Code
• [CVPR] CTCA Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition. Paper
• [CVPR] CVT-SLR CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment. Paper | Code
• [CVPR] NLA-SLR Natural Language-Assisted Sign Language Recognition. Paper | Code
• [ICCV] CoSign CoSign: Exploring Co-Occurrence Signals in Skeleton-Based Continuous Sign Language Recognition. Paper
• [ICCV] C²ST C²2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition. Paper
• [ICCV] Cross-Ling Improving Continuous Sign Language Recognition with Cross-Lingual Signs. Paper
• [NeurIPS] TwoStream-SLT Two-Stream Network for Sign Language Recognition and Translation. Paper

Journal

• [AJSE] TSRNet Continuous Sign Language Recognition via Temporal Super-Resolution Network. Paper
• [PR] mLTSF-Net Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition. Paper
• [IEEE TM] Multilingual-CSLR Collaborative Multilingual Continuous Sign Language Recognition: A Unified Framework. Paper
• [IEEE TM] PA-CMA Prior-Aware Cross Modality Augmentation Learning for Continuous Sign Language Recognition. Paper
• [CIS] STTN Spatial–Temporal Transformer for End-to-End Sign Language Recognition. Paper
• [IEEE Access] BAE-Attention Boundary-Adaptive Encoder with Attention Method for Chinese Sign Language Recognition. Paper
• [AIHC] Continuous Sign Language Recognition Using Isolated Signs Data and Deep Transfer Learning. Paper
• [TPAMI] SignBERT+ SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding. Paper

2022

Conference

• [ISCA] LCSA Local Context-aware Self-attention for Continuous Sign Language Recognition. Paper
• [ECCV] TLP Temporal Lift Pooling for Continuous Sign Language Recognition. Paper | Code
• [ECCV] RadialCTC Deep Radial Embedding for Visual Sequence Learning. Paper
• [CVPR] C²SLR C²SLR: Consistency-Enhanced Continuous Sign Language Recognition. Paper

Journal

• [Sensors] STAMF Novel Spatio-Temporal Continuous Sign Language Recognition Using an Attentive Multi-Feature Network. Paper
• [IEEE SPL] CA-SignBERT A Cross-Attention BERT-Based Framework for Continuous Sign Language Recognition. Paper

ArXiv

• [ArXiv] MSTN Multi-View Spatial-Temporal Network for Continuous Sign Language Recognition. Paper
• [ArXiv] MSTNet Multi-Scale Temporal Network for Continuous Sign Language Recognition. Paper

2021

Conference

• [ICCV] VAC Visual Alignment Constraint for Continuous Sign Language Recognition. Paper
• [ICCV] SMKD Self-Mutual Distillation Learning for Continuous Sign Language Recognition. Paper
• [IJCNN] ST-GCN Continuous Sign Language Recognition based on Multi-Part Skeleton Data. Paper
• [CVPR] Fingerspelling Detection in American Sign Language. Paper

Journal

• [TCSVT] SBD-RL Semantic Boundary Detection With Reinforcement Learning for Continuous Sign Language Recognition. Paper
• [Sensors] SLRGAN Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network. Paper
• [IEEE TM] PiSLTRc PiSLTRc: Position-Informed Sign Language Transformer with Content-Aware Convolution. Paper
• [ESA] H-GAN An optimized Generative Adversarial Network based continuous sign language classification. Paper
• [IEEE TM] STMC-SLRT Spatial-Temporal Multi-Cue Network for Sign Language Recognition and Translation. Paper
• [IEEE Access] SignBERT SignBERT: A BERT-Based Deep Learning Framework for Continuous Sign Language Recognition. Paper
• [IEEE TM] EnStimCTC A Comprehensive Study on Deep Learning-Based Methods for Sign Language Recognition. Paper

2020

Conference

• [ICPR] ISFT Continuous Sign Language Recognition with Iterative Spatiotemporal Fine-Tuning. Paper
• [ECAI] SAFI Self-Attention-Based Fully-Inception Networks for Continuous Sign Language Recognition. Paper
• [ICPR] SAN Context Matters: Self-Attention for Sign Language Recognition. Paper
• [ECCV] SMS Stochastic Fine-Grained Labeling of Multi-State Sign Glosses for Continuous Sign Language Recognition. Paper
• [ECCV] FCN Fully Convolutional Networks for Continuous Sign Language Recognition. Paper
• [ACM MM] CMAug Boosting Continuous Sign Language Recognition via Cross Modality Augmentation. Paper
• [CVPR] SL-Transf Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation.
  Paper | Code
• [AAAI] STMC Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition. Paper

Journal

• [JCR] Skeleton-Based Chinese Sign Language Recognition and Generation for Bidirectional Communication Between Deaf and Hearing People. Paper
• [TPAMI] Multi-Stream CLH Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos. Paper
• [IEEE Access] CMA-TE Continuous Sign Language Recognition through Cross-Modal Alignment of Video and Text Embeddings in a Joint-Latent Space. Paper
• [Sensors] Recognition of Non-Manual Content in Continuous Japanese Sign Language. Paper

2019

Conference

• [MAHCI] CSLR-PL Continuous Sign Language Recognition Based on Pseudo-Supervised Learning. Paper
• [ICIP] CSLR-RL Continuous Sign Language Recognition via Reinforcement Learning. Paper
• [CVPR] Align-iOpt Iterative Alignment Network for Continuous Sign Language Recognition. Paper
• [ICME] DPLD Dynamic Pseudo Label Decoding for Continuous Sign Language Recognition. Paper
• [BigMM] WIC-NGC Deep Grammatical Multi-classifier for Continuous Sign Language Recognition. Paper
• [APSIPA ASC] Exploring RNN-Transducer for Chinese Speech Recognition. Paper
• [IJCAI] DenseTCN Dense Temporal Convolution Network for Sign Language Translation. Paper

Journal

• [IEEE TM] IterativeTrain A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training. Paper

ArXiv

• [ArXiv] Sf-net Sf-net: Structured feature network for continuous sign language recognition. Paper

2018

Conference

• [IJCAI] DCN-IterativeOpt Dilated Convolutional Network with Iterative Optimization for Continuous Sign Language Recognition. Paper
• [AAAI] LS-HAN Video-based Sign Language Recognition Without Temporal Segmentation. Paper
• [AAAI] HLSTM Hierarchical LSTM for Sign Language Translation. Paper
• [CVPRW] 3DRCNN Recognizing American Sign Language Gestures from Within Continuous Videos. Paper

2017

Conference

• [CVPR] ReSign Re-Sign: Re-Aligned End-to-End Sequence Modelling with Deep Recurrent CNN-HMMs. Paper
• [ICCV] SubUNets SubUNets: End-to-End Hand Shape and Continuous Sign Language Recognition. Paper | Code
• [CVPR] StagedOpt Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization. Paper
• [SenSys] DeepASL DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign. Paper

Journal

• [CMRA] Openpose-LSTM Towards Continuous Sign Language Recognition with Deep Learning. Paper

2016

Conference

• [LREC] HamNoSys CSLR Automatic Alignment of HamNoSys Subunits for Continuous Sign Language Recognition. Paper
• [BMVC] Deep Sign Deep Sign: Hybrid CNN-HMM for Continuous Sign Language Recognition. Paper

---

SLT Papers

Gloss-based SLT

2025

Conference

• [COLING] TextCTC-SLT Improvement in Sign Language Translation Using Text CTC Alignment. Paper | Code
• [CVPR] Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues. Paper

ArXiv

• [ArXiv] Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation. Paper
• [ArXiv] GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation. Paper

2024

Conference

• [ECCV] EVSign EVSign: Sign Language Recognition and Translation with Streaming Events. Paper
• [NAACL] SDDA Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation. Paper
• [ECAI] Improving Non-autoregressive Sign Language Translation with Random Ordering Progressive Prediction Pre-training.

2023

Conference

• [ICLR] SLTUNET SLTUNET: A Simple Unified Model for Sign Language Translation. Paper|Code

2022

Conference

• [WACV] HST-GNN Sign Language Translation with Hierarchical Spatio-Temporal Graph Neural Network. Paper
• [NeurIPS] TwoStream-SLT Two-Stream Network for Sign Language Recognition and Translation. Paper
• [CVPR] MMTLB A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation. Paper

Journal

• [Applied Intelligence] Sign language recognition and translation network based on multi-view data. Paper

ArXiv

• [ArXiv] Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation. Paper

2021

Conference

• [CVPR] BN-TIN-Transf Improving Sign Language Translation with Monolingual Data by Sign Back-Translation. Paper
• [MT Summit] BERT2RND Frozen Pretrained Transformers for Neural Sign Language Translation. Paper | Code

Journal

• [Neurocomputing] Facial-SLT Enhancing neural sign language translation by highlighting the facial expression information. Paper
• [IET] How Important Is Motion in Sign Language Translation? Paper
• [IEEE TMM] STMC-T Spatial-Temporal Multi-Cue Network for Sign Language Recognition and Translation. Paper

2020

Conference

• [ACCV] Understanding Motion in Sign Language: A New Structured Translation Dataset. Paper

ArXiv

• [ArXiv] STMC-Transf Better Sign Language Translation with STMC-Transformer. Paper|Code

2019

Journal

• [MDPI] Neural Sign Language Translation Based on Human Keypoint Estimation. Paper

2018

Conference

• [CVPR] NSLT Neural Sign Language Translation. Paper|Code
• [ACM MM] CTF Connectionist Temporal Fusion for Sign Language Translation. Paper

Gloss-free SLT

2025

Conference

• [WACV] UniGloR A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production. Paper | Code
• [ICLR] UNI-SIGN UNI-SIGN: TOWARD UNIFIED SIGN LANGUAGE UNDERSTANDING AT SCALE. Paper|Code
• [ACL] Improving Multilingual Sign Language Translation with Automatically Clustered Language Family Information. Paper

ArXiv

• [ArXiv] Spatio-temporal transformer to support automatic sign language translation. Paper
• [ArXiv] ADAT ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation. Paper
• [ArXiv] Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms. Paper
• [ArXiv] GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation. Paper
• [ArXiv] SignMusketeers SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale. Paper

2024

Conference

• [NeurIPS] Scaling Sign Language Translation. Paper
• [NeurIPS] SignCL Improving Gloss-free Sign Language Translation by Reducing Representation Density. Paper | Code
• [ACL] SLT-SEM Sign Language Translation with Sentence Embedding Supervision. Paper | Code
• [ECCV] VAP Visual Alignment Pre-training for Sign Language Translation. Paper
• [CVPR] LLM-SLT LLMs Are Good Sign Language Translators. Paper
• [LREC-COLING] SimulSLT-CLT Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation. Paper | Code
• [LREC-COLING] FLa-LLM Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation. Paper
• [AAAI] CV-SLT Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment. Paper|Code
• [ICASSP] EMF-SLT An Explicit Multi-Modal Fusion Method for Sign Language Translation. Paper
• [ICLR] Sign2GPT Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation. Paper

ArXiv

• [ArXiv] LLaVA-SLT Visual Language Tuning for Sign Language Translation. Paper
• [ArXiv] SSVP-SLT Towards Privacy-Aware Sign Language Translation at Scale. Paper | Code
• [ArXiv] Unsupervised Sign Language Translation and Generation. Paper
• [ArXiv] American Sign Language Video to Text Translation. Paper | Code
• [ArXiv] Online-CSLRT Towards Online Sign Language Recognition and Translation. Paper | Code
• [ArXiv] Improving Gloss-free Sign Language Translation by Reducing Representation Density. Paper
• [ArXiv] MSKA-SLT Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation. Paper | Code
• [ArXiv] Signformer Signformer is all you need: Towards Edge AI for Sign Language. Paper
• [ArXiv] C²RL C²RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval. Paper

2023

Conference

• [CVPR] GASLT Gloss Attention for Gloss-Free Sign Language Translation. Paper|Code
• [ICCV] GFSLT-VLP Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining. Paper|Code
• [ICCV] IP-SLT Sign Language Translation with Iterative Prototype. Paper
• [ICLR] SLTUNET SLTUNET: A Simple Unified Model for Sign Language Translation. Paper|Code
• [IJCAI] SLT-CND Efficient Sign Language Translation with a Curriculum-Based Non-Autoregressive Decoder. Paper|Code
• [ICASSP] ConSLT A Token-Level Contrastive Framework for Sign Language Translation. Paper|Code
• [CVPRW] SLT-IV Sign Language Translation from Instructional Videos. Paper | Code
• [NeurIPS] YouTube-ASL YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus. Paper

ArXiv

• [ArXiv] XmDA Cross-modality Data Augmentation for End-to-End Sign Language Translation. Paper ｜ Code
• [ArXiv] GloFE Gloss-Free End-to-End Sign Language Translation. Paper | Code

2022

Conference

• [WMT] Spatio-Temporal Sign Language Representation and Translation. Paper
• [WMT] Experimental Machine Translation of the Swiss German Sign Language via 3D augmentation of body keypoints. Paper|Code
• [ACL] PET Prior knowledge and memory enriched transformer for sign language translation. Paper
• [ACM MM] MC-SLT MC-SLT: Towards Low-Resource Signer-Adaptive Sign Language Translation. Paper
• [CVPR] MLSLT MLSLT: Towards Multilingual Sign Language Translation. Paper
• [CVPR] MMTLB A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation. Paper
• [NAACL] TIN-SLT Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation. Paper|Code
• [EMNLP] OpenASL Open-Domain Sign Language Translation Learned from Online Video. Paper|Code

Journal

• [IEEE] CSGCR Conditional Sentence Generation and Cross-Modal Reranking for Sign Language Translation. Paper
• [TPAMI] SignNet II: A Transformer-Based Two-Way Sign Language Translation Model. Paper

ArXiv

• [ArXiv] Tackling low-resourced sign language translation: Upc at wmt-slt 22. Paper

Others

• TF-H2S Sign Language Translation based on Transformers for the How2Sign Dataset. Paper

2021

Conference

• [FG] Content4All Open Research Sign Language Translation Datasets. Paper
• [ACM MM] SimulSLT SimulSLT: End-to-End Simultaneous Sign Language Translation. Paper
• [ACM MM] Skeleton-Aware Neural Sign Language Translation. Paper
• [ICCV] Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation. Paper

Journal

• [ACM TACCESS] Deep Learning Methods for Sign Language Translation. Paper

2020

Conference

• [CVPR] SL-Transf Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation.
  Paper | Code
• [ECCV] MCT-SLT Multi-channel Transformers for Multi-articulatory Sign Language Translation. Paper
• [FG] Tokenization-SLT Neural Sign Language Translation by Learning Tokenization. Paper
• [NeurIPS] Tspnet Tspnet: Hierarchical feature learning via temporal semantic pyramid for sign language translation. Paper|CODE
• [ICTC] Robust Keypoint Normalization Method for Korean Sign Language Translation Using Transformer. Paper

Journal

• [CIN] An Improved Sign Language Translation Model with Explainable Adaptations for Processing Long Sign Sentences. Paper

2019

Journal

• [MDPI AS] Neural Sign Language Translation based on Human Keypoint Estimation. Paper

2018

Conference

• [CVPR] NSLT Neural Sign Language Translation. Paper|Code
• [AAAI] Hierarchical LSTM for Sign Language Translation. Paper

---

SLP Papers

2025

Conference

• [ECCV] Signavatars Signavatars: A Large-Scale 3D Sign Language Holistic Motion Dataset and Benchmark. Paper
• [CVPR] Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation. Paper
• [CVPR] Diffusion-Based Continuous Sign Language Generation with Cluster-Specific Fine-Tuning and Motion-Adapted Transformer. Paper
• [ICCV] Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator. Paper

ArXiv

• [ArXiv] CNSign Beyond Words: AuralLLM and SignMST-C for Precise Sign Language Production and Bidirectional Accessibility. Paper
• [ArXiv] A Transformer-Based Framework for Greek Sign Language Production using Extended Skeletal Motion Representations. Paper
• [ArXiv] Towards AI-driven Sign Language Generation with Non-manual Markers. Paper
• [ArXiv] Text-Driven Diffusion Model for Sign Language Production. Paper
• [ArXiv] Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization. Paper

2024

Conference

• [CVPR] Neural Sign Actors Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text. Paper
• [WACV] Sign Language Production with Latent Motion Transformer. Paper
• [ECCV] Spoken2Sign A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars. Paper
• [ECCV] SignGen SignGen: End-to-End Sign Language Video Generation with Latent Diffusion. Paper
• [AAAI] G2P-DDM G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model. Paper | Project Page
• [IEEE FG] A Gloss-free Sign Language Production with Discrete Representation. Paper
• [IEEE FG] Data-Driven A Data-Driven Representation for Sign Language Production. Paper

Journal

• [TOMM] GCDM Gloss-driven Conditional Diffusion Models for Sign Language Production. Paper

ArXiv

• [ArXiv] T2S-GPT T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text. Paper | Project Page
• [ArXiv] iSign: A Benchmark for Indian Sign Language Processing. Paper
• [ArXiv] UniGloR A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production. Paper | Code
• [ArXiv] LVMCN Linguistics-Vision Monotonic Consistent Network for Sign Language Production. Paper
• [ArXiv] Sign-IDD Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production. Paper | Code
• [ArXiv] MS2SL MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production. Paper
• [ArXiv] SignLLM SignLLM: Sign Language Production Large Language Models. Paper
• [ArXiv] Stitching T2P Sign Stitching: A Novel Approach to Sign Language Production. Paper

Workshop

• [NuerIPS] Generative Interpolation of Sign Language Poses using RVQ-VAE. Paper

2023

Conference

• [SEM] IFECE Including Facial Expressions in Contextual Embeddings for Sign Language Generation. Paper
• [FG] SignVQNet Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations. Paper | Code

ArXiv

• [ArXiv] SignDiff SignDiff: Learning Diffusion Models for American Sign Language Production. Paper | Project Page

2022

Conference

• [CVPR] FS-NET Signing at scale: Learning to co-articulate signs for large-scale photo-realistic sign language production. Paper
• [ACM] GEN-OBT Gloss Semantic-Enhanced Network with Online Back-Translation for Sign Language Production. Paper
• [3DV] There and Back Again: 3D Sign Language Generation from Text Using Back-Translation. Paper

Journal

• [IEEE] Spatial–Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production. Paper

ArXiv

• [ArXiv] Non-Autoregressive Sign Language Production via Knowledge Distillation. Paper

2021

Conference

• [ACM MM] NAT-EA Towards Fast and High-Quality Sign Language Production. Paper
• [ICCV] Mixed SIGNals Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives. Paper
• [BMVC] NSLP-G Non-Autoregressive Sign Language Production with Gaussian Space. Paper

Journal

• [IJCV] Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks. Paper

2020

Conference

• [ECCV] Progressive Transf Progressive transformers for end-to-end sign language production. Paper | Code
• [IJCV] Text2Sign: Towards Sign Language Production Using Neural Machine Translation and Generative Adversarial Networks. Paper
• [WACV] Neural Sign Language Synthesis: Words Are Our Glosses. Paper
• [BMCV] Adversarial Training Adversarial Training for Multi-Channel Sign Language Production. Paper

Journal

• [INNS] Skeleton-based Chinese sign language recognition and generation for bidirectional communication between deaf and hearing people. Paper

Earlier

Conference

• [BMVC 2018] Sign Language Production using Neural Machine Translation and Generative Adversarial Networks. Paper

🏆 Leaderboard

SLR Leaderboard

Results on SIGNUM dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
IterativeTrain	2019	CNN + BLSTM	2.8	RGB-Frames	IEEE TM	-
Re-Sign	2017	CNN + BLSTM + HMM	4.8	RGB-Frames	CVPR	-
Deep Sign	2016	CNN + HMM	7.4	RGB-Frames	BMVC	-

Results on PHOENIX-2014 dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
Cross-Ling	2023	-	16.7	RGB-Frames	ICCV	-
SignVTCL	2024	S3D + CTC + mBART + Adapters	17.6	RGB-Frames, Skeleton-Keypoints, Optical Flow	ArXiv	-
C²ST	2023	-	17.7	RGB-Frames	ICCV	-
CA-SignBERT	2022	(3+2+1)D ResNet + BERT + BLSTM + CTC	18.6	RGB-Frames	IEEE SPL	-
MAM-FSD	2025	CNN + 1DCNN + BSLTM	18.8	RGB-Frames	MVA	-
TwoStream-SLT	2023	S3D + CTC	18.8	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
MultiSignGraph	2024	GCN + KNN	19.1	RGB-Frames	CVPR	Available
CorrNet	2023	CNN + BLSTM	19.4	RGB-Frames	CVPR	Available
XMC-n	2024	-	19.82	RGB-Frames	ICME	-
STTN	2023	Transformer	19.98	RGB-Frames	CIS	-
SignBERT+	2023	-	20.0	Skeleton-Keypoints	TPAMI	-
PA-CMA	2023	CNN-TCN + BLSTM + CTC	20.0	RGB-Frames	IEEE TM	-
SignGraph	2024	GCN + KNN	20.1	RGB-Frames	CVPR	Available
CoSign-2s	2023	GCN + CNN + BLSTM	20.1	RGB-Frames, Skeleton-Keypoints	ICCV	-
CVT-SLR	2023	CNN + MLP + Self-Attention + CTC	20.1	RGB-Frames	CVPR	Available
RadialCTC	2022	-	20.2	RGB-Frames	ECCV	-
MultiModal SignBERT	2021	(3+2+1)DCNN + BERT + LSTM	20.2	RGB-Frames	IEEE Access	-
CTCA	2023	CNN + 1D-TCN + BLSTM + CTC	20.3	RGB-Frames	CVPR	-
C²SLR	2022	-	20.4	RGB-Frames	CVPR	-
STMC-SLRT	2021	2D-CNN + TempConv + BLSTM + CTC	20.7	RGB-Frames	IEEE TM	-
AdaBrowse	2023	CNN + BLSTM	20.7	RGB-Frames	ACM MM	-
DFConv	2023	CNN + ME + BLSTM	20.8	RGB-Frames	ICASSP	-
TLP	2022	CNN + BLSTM + CTC	20.8	RGB-Frames	ECCV	Available
CRKD	2024	ResNet50 + 2D-CNN + TSCM-2D CNN + CTC + MSE	20.9	RGB-Frames	AJSE	-
Multilingual-CSLR	2023	CNN + BLSTM + CTC	20.9	RGB-Frames	IEEE TM	-
SEN	2023	CNN + BLSTM	21.0	RGB-Frames	AAAI	-
SMKD	2021	CNN + BLSTM + CTC	21.0	RGB-Frames	ICCV	-
SignBERT	2021	(3+2+1)DCNN + BERT + LSTM	21.4	RGB-Frames	IEEE Access	-
MSTNet	2022	CNN + Transformer	21.4	RGB-Frames	ArXiv	-
STAMF	2022	CNN + MHA + BLSTM + CTC	21.5	RGB-Frames, Skeleton-Keypoints	Sensors	-
LCSA	2022	VGGNet + Transformer	21.9	RGB-Frames	ISCA	-
CMAug	2020	CNN-TCN + LSTM	21.9	RGB-Frames	ACM MM	-
VAC	2021	CNN + BLSTM + CTC	22.3	RGB-Frames	ICCV	-
MSTN	2022	Vit + GCN + Transformer + CTC	22.8	RGB-Frames, Skelenton-Keypoints	ICCV	-
mLTSF-Net + GFE	2023	FCN	23.0	RGB-Frames	PR	-
PiSLTRc	2021	CNN + Transformer	23.2	RGB-Frames	IEEE TM	-
SLRGAN	2021	GAN	23.4	RGB-Frames	Sensors	-
mLTSF-Net	2023	FCN	23.5	RGB-Frames	PR	-
IterativeTrain + SBD-RL	2021	-	23.5	RGB-Frames	TCSVT	-
FCN	2020	FCN + GFE	23.9	RGB-Frames	ECCV	-
CMA-TE	2020	CNN + BLSTM	24.00	RGB-Frames	IEEE Access	-
IterativeTrain	2019	CNN + BLSTM	24.4	RGB-Frames	IEEE TM	-
TSRNet	2023	-	24.7	RGB-Frames	AJSE	-
SMS	2020	2DCNN + Transformer	25.3	RGB-Frames	ECCV	-
Multi-Stream CLH	2020	Multi-Stream CNN-LSTM-HMM	26.0	RGB-Frames	TPAMI	-
Re-Sign	2017	CNN + BLSTM + HMM	26.8	RGB-Frames	CVPR	-
SBD-RL	2021	CNN + BLSTM + CTC + RL	28.6	RGB-Frames	TCSVT	-
SAN	2020	2D-CNN + Transformer	29.7	RGB-Frames	ICPR	-
SAFI	2020	(2+1)D-CNN + Self-Attention	31.3	RGB-Frames	ECAI	-
ISFT	2020	(2+1)D-CNN + BLSTM	34.4	RGB-Frames	ICPR	-
DPLD + TEM	2019	I3D-BGRU-CTC	34.5	RGB-Frames	ICME	-
SF-Net(ResNet-18)	2019	2D3DCNN + LSTM + BLSTM	34.9	RGB-Frames	ArXiv	-
Align-iOpt	2019	3D-ResNet + BLSTM + Attention-LSTM + CTC	36.7	RGB-Frames	CVPR	-
DCN-IterativeOpt	2019	3DCNN + CTC	37.3	RGB-Frames	IJCAI	-
CSLR-RL	2019	3D-ResNet + Transformer	38.3	RGB-Frames	ICIP	-
LS-HAN	2018	CNN + LS + HAN	38.3	RGB-Frames	AAAI	-
StagedOpt	2017	CNN + BLSTM	38.7	RGB-Frames	CVPR	-
Deep Sign	2016	CNN + HMM	38.8	RGB-Frames	BMVC	-
CSLR-PL	2019	3DCNN + BGRU + CTC	40.6	RGB-Frames	MAHCI	-
SubUNets	2017	CNN + BLSTM	40.7	RGB-Frames	ICCV	Avaliable
HamNoSys CSLR	2016	CNN + HMM	45.1	RGB-Frames	LREC	-

Results on PHOENIX-2014T dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
SignVTCL	2024	S3D + CTC + mBART + Adapters	17.9	RGB-Frames, Skeleton-Keypoints, Optical Flow	ArXiv	-
Cross-Ling	2023	-	18.5	RGB-Frames	ICCV	-
C²ST	2023	-	18.9	RGB-Frames	ICCV	-
MultiSignGraph	2024	GCN + KNN	19.1	RGB-Frames	CVPR	Available
TwoStream-SLT	2023	S3D + CTC	19.3	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
MAM-FSD	2025	CNN + 1DCNN + BSLTM	19.4	RGB-Frames	MVA	-
SignBERT+	2023	-	19.9	Skeleton-Keypoints	TPAMI	-
SignGraph	2024	GCN + KNN	20.0	RGB-Frames	CVPR	Available
PA-CMA	2023	CNN-TCN + BLSTM + CTC	20.0	RGB-Frames	IEEE TM	-
CoSign-2s	2023	GCN + CNN + BLSTM	20.1	RGB-Frames, Skeleton-Keypoints	ICCV	-
C²SLR	2022	-	20.4	RGB-Frames	CVPR	-
CorrNet	2023	CNN + BLSTM	20.5	RGB-Frames	CVPR	Available
SEN	2023	CNN + BLSTM	20.7	RGB-Frames	AAAI	-
TLP	2022	CNN + BLSTM + CTC	21.2	RGB-Frames	ECCV	Available
SMKD	2021	CNN + BLSTM + CTC	22.4	RGB-Frames	ICCV	-
PiSLTRc	2021	CNN + Transformer	22.9	RGB-Frames	IEEE TM	-
Multi-Stream CLH	2020	Multi-Stream CNN-LSTM-HMM	24.1	RGB-Frames	TPAMI	-
CMA-TE	2020	CNN + BLSTM	24.3	RGB-Frames	IEEE Access	-
SL-Transf	2020	Transformer	24.49	RGB-Frames	CVPR	Avaliable
FCN	2020	FCN + GFE	25.1	RGB-Frames	ECCV	-

Results on CSL-Daily dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
SignVTCL	2024	S3D + CTC + mBART + Adapters	24.1	RGB-Frames, Skeleton-Keypoints, Optical Flow	ArXiv	-
MAM-FSD	2025	CNN + 1DCNN + BSLTM	24.5	RGB-Frames	MVA	-
TwoStream-SLT	2023	S3D + CTC	25.3	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
C²ST	2023	-	25.8	RGB-Frames	ICCV	-
UNI-SIGN	2025	RTMPose-x + Spatial-GCN + ST-GCN + EfficientNet-B0 + Prior-Guided Fusion (Multi-head + Deformable Attention + Gate) + mT5-Base + Unified LM Loss (no CTC)	26.0	RGB-Frames, Skeleton-Keypoints	ICLR	Avaliable
MultiSignGraph	2024	GCN + KNN	26.4	RGB-Frames	CVPR	Available
XMC-d	2024	-	26.4	RGB-Frames	ICME	-
XMC-n	2024	-	26.8	RGB-Frames	ICME	-
CoSign-2s	2023	GCN + CNN + BLSTM	27.2	RGB-Frames, Skeleton-Keypoints	ICCV	-
SignGraph	2024	GCN + KNN	27.4	RGB-Frames	CVPR	Available
PA-CMA	2023	CNN-TCN + BLSTM + CTC	28.7	RGB-Frames	IEEE TM	-
CorrNet	2023	CNN + BLSTM	30.1	RGB-Frames	CVPR	Available
SEN	2023	CNN + BLSTM	30.7	RGB-Frames	AAAI	-
IterativeTrain ✢	2019	CNN + BLSTM	32.4	RGB-Frames	IEEE TM	-
FCN ✢	2020	FCN + GFE	32.5	RGB-Frames	ECCV	-
LS-HAN ✢	2018	CNN + LS + HAN	39.4	RGB-Frames	AAAI	-
SubUNets	2017	CNN + BLSTM	41.0	RGB-Frames	ICCV	Avaliable

CSL-Daily SLR Table Notation:

✢ denotes the results were implemented by BN-TIN-Transf

Results on CSL-Split I dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
C²SLR + SRM	2024	-	0.68	RGB-Frames	ACM TOMM	Available
STAMF	2022	CNN + MHA + BLSTM + CTC	0.7	RGB-Frames, Skeleton-Keypoints	Sensors	-
MSTNet	2022	CNN + Transformer	0.7	RGB-Frames	ArXiv	-
CorrNet	2023	CNN + BLSTM	0.8	RGB-Frames	CVPR	Available
SEN	2023	CNN + BLSTM	0.8	RGB-Frames	AAAI	-
C²SLR	2022	-	0.9	RGB-Frames	CVPR	-
CA-SignBERT	2022	(3+2+1)D ResNet + BERT + BLSTM + CTC	1.14	RGB-Frames	IEEE SPL	-
STTN	2023	Transformer	1.2	RGB-Frames	CIS	-
ST-GCN	2021	GCN + BLSTM + LSTM	1.3	RGB-Frames	IJCNN	-
LCSA	2022	VGGNet + Transformer	1.4	RGB-Frames	ISCA	-
MultiModal SignBERT	2021	(3+2+1)DCNN + BERT + LSTM	1.52	RGB-Frames	IEEE Access	-
VAC	2021	CNN + BLSTM + CTC	1.6	RGB-Frames	ICCV	-
MSTN	2022	Vit + GCN + Transformer + CTC	1.9	RGB-Frames, Skelenton-Keypoints	ICCV	-
STMC	2020	CNN + BLSTM + CTC	2.1	RGB-Frames	AAAI	-
SignBERT	2021	(3+2+1)DCNN + BERT + LSTM	2.26	RGB-Frames	IEEE Access	-
CMA-TE	2020	CNN + BLSTM	2.4	RGB-Frames	IEEE Access	-
EnStimCTC	2021	-	2.41	RGB-Frames	IEEE TM	-
mLTSF-Net	2023	FCN	2.5	RGB-Frames	PR	-
CRKD	2024	ResNet50 + 2D-CNN + TSCM-2D CNN + CTC + MSE	2.6	RGB-Frames	AJSE	-
PiSLTRc	2021	CNN + Transformer	2.8	RGB-Frames	IEEE TM	-
FCN	2020	FCN + GFE	3.0	RGB-Frames	ECCV	-
SF-Net(ResNet-18)	2019	2D3DCNN + LSTM + BLSTM	3.8	RGB-Frames	ArXiv	-
DPLD + TEM	2019	I3D-BGRU-CTC	4.7	RGB-Frames	ICME	-
DPLD	2019	I3D-BGRU-CTC	5.6	RGB-Frames	ICME	-
HLSTM-atten	2018	3D-CNN + LSTM	10.2	RGB-Frames	AAAI	-
HLSTM	2018	3D-CNN + LSTM	10.7	RGB-Frames	AAAI	-
CTF	2018	C3D-ResNet + TConv + BGRU + CTC	11.2	RGB-Frames	ACM MM	-

Results on CSL-Split II dataset

Model Name	Year	Architecture	WER	Model Input	Conference/Journal	Code
CA-SignBERT	2022	(3+2+1)D ResNet + BERT + BLSTM + CTC	19.80	RGB-Frames	IEEE SPL	-
SignBERT	2021	(3+2+1)DCNN + BERT + LSTM	24.90	RGB-Frames	IEEE Access	-
STMC	2020	CNN + BLSTM + CTC	28.6	RGB-Frames	AAAI	-
Align-iOpt	2019	3D-ResNet + BLSTM + Attention-LSTM + CTC	32.7	RGB-Frames	CVPR	-
WIC-NGC	2019	3D-ResNet + BLSTM	50.9	RGB-Frames	BigMM	-

---

SLT Leaderboard

Results on Phoenix-2014T dataset

Gloss-based

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
TextCTC-SLT	2025	28.42	RGB-Frames	COLING	Available
TwoStream-SLT	2022	26.71	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
SLTUNET	2023	26.00	RGB-Frames	ICLR	Avaliable
ConSLT	2023	25.48	RGB-Frames	ICASSP	Avaliable
MMTLB	2022	24.60	RGB-Frames	CVPR	-
STMC-Transf	2020	24.00	RGB-Frames	ArXiv	Avaliable
STMC-T	2021	23.65	RGB-Frames	IEEE TMM	-
BN-TIN-Transf + BT	2021	23.51	RGB-Frames	CVPR	-
SimulSLT	2021	23.14	RGB-Frames	ACM MM	-
BN-TIN-Transf	2021	22.54	RGB-Frames	CVPR	-
BERT2RND	2021	22.47	RGB-Frames	MT Summit	Avaliable
SL-Transf	2020	22.45	RGB-Frames	CVPR	Avaliable
HST-GNN	2022	22.3	RGB-Frames	WACV	-
NSLT	2018	18.13	RGB-Frames	CVPR	Avaliable
Facial-SLT	2021	10.89	RGB-Frames	Neurocomputing	-

Gloss-free

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
CV-SLT	2022	29.27	RGB-Frames	AAAI	Avaliable
MSKA-SLT	2024	29.03	Skeleton-Keypoints	ArXiv	Avaliable
TwoStream-SLT	2022	28.95	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
SLTUNET	2023	28.47	RGB-Frames	ICLR	Avaliable
MMTLB	2022	28.39	RGB-Frames	CVPR	-
IP-SLT	2023	27.97	RGB-Frames	ICCV	-
C²RL	2024	26.75	RGB-Frames	ArXiv	-
VAP	2024	26.16	RGB-Frames	ECCV	-
EMF-SLT	2024	26.01	RGB-Frames	ICASSP	-
SignBERT+	2023	25.70	Skeleton-Keypoints	TPAMI	-
XmDA	2023	25.36	RGB-Frames	ArXiv	Avaliable
SLT-CND	2023	24.71	RGB-Frames	IJCAI	Avaliable
BN-TIN-Transf + BT	2021	24.32	RGB-Frames	CVPR	-
SimulSLT-CTL	2024	24.20	RGB-Frames	LREC-COLING	Avaliable
SLT-SEM	2024	24.12	RGB-Frames	ACL	-
PET	2022	24.02	RGB-Frames	ICLR	-
SimulSLT-CTL++	2024	23.75	RGB-Frames	LREC-COLING	Avaliable
Online-CSLRT	2024	23.69	RGB-Frames	ArXiv	Avaliable
Signformer	2024	23.43	RGB-Frames	ArXiv	-
LLaVA-SLT	2024	23.43	RGB-Frames	ArXiv	-
LLM-SLT	2024	23.40	RGB-Frames	CVPR	-
FLa-LLM	2024	23.09	RGB-Frames	LREC-COLING	-
SignCL	2024	22.74	RGB-Frames	NeurIPS	Available
Sign2GPT	2024	22.52	RGB-Frames	ArXiv	-
BN-TIN-Transf	2021	21.68	RGB-Frames	CVPR	-
ConSLT	2023	21.59	RGB-Frames	ICASSP	Avaliable
GFSLT-VLP	2023	21.44	RGB-Frames	ICCV	Avaliable
SL-Transf	2020	21.32	RGB-Frames	CVPR	Avaliable
MCT-SLT	2020	18.30	RGB-Frames	ECCV	-
GASLT	2023	15.74	RGB-Frames	CVPR	Avaliable
CSGCR	2022	15.18	RGB-Frames	IEEE	-
Tspnet	2020	13.41	RGB-Frames	NeurIPS	Avaliable
Tokenization-SLT	2020	13.25	RGB-Frames	FG	-
UniGloR	2024	12.86	RGB-Frames	ArXiv	-
SimulSLT	2021	12.27	RGB-Frames	ACM MM	-
NSLT	2018	9.58	RGB-Frames	CVPR	Avaliable

---

Results on CSL-Daily dataset

Gloss-based

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
TwoStream-SLT	2022	25.79	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
SLTUNET	2023	23.76	RGB-Frames	ICLR	Avaliable
TextCTC-SLT	2025	22.47	RGB-Frames	COLING	Available
MMTLB	2022	21.46	RGB-Frames	CVPR	-
BN-TIN-Transf + BT	2021	19.67	RGB-Frames	CVPR	-
HST-GNN	2022	17.8	RGB-Frames	WACV	-
BN-TIN-Transf	2021	16.25	RGB-Frames	CVPR	-
NSLT + Luong ✦	2018	11.03	RGB-Frames	CVPR	Avaliable

Gloss-free

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
UNI-SIGN	2025	26.36	RGB-Frames, Skeleton-Keypoints	ICLR	Avaliable
MSKA-SLT	2024	25.52	Skeleton-Keypoints	ArXiv	Avaliable
TwoStream-SLT	2022	25.42	RGB-Frames, Skeleton-Keypoints	NeurIPS	-
SLTUNET	2023	25.01	RGB-Frames	ICLR	Avaliable
MMTLB	2022	23.92	RGB-Frames	CVPR	-
C²RL	2024	21.61	RGB-Frames	ArXiv	-
XmDA	2023	21.58	RGB-Frames	ArXiv	Avaliable
BN-TIN-Transf + BT	2021	21. 34	RGB-Frames	CVPR	-
VAP	2024	20.85	RGB-Frames	ECCV	-
LLaVA-SLT	2024	20.42	RGB-Frames	ArXiv	-
IP-SLT	2023	16.72	RGB-Frames	ICCV	-
SLT-CND	2023	16.61	RGB-Frames	IJCAI	Avaliable
SignCL	2024	16.16	RGB-Frames	NeurIPS	Available
LLM-SLT	2024	15.75	RGB-Frames	CVPR	-
Sign2GPT	2024	15.40	RGB-Frames	ArXiv	-
ConSLT	2023	14.53	RGB-Frames	ICASSP	Avaliable
FLa-LLM	2024	14.20	RGB-Frames	LREC-COLING	-
BN-TIN-Transf	2021	13.19	RGB-Frames	CVPR	-
GFSLT-VLP	2023	11.00	RGB-Frames	ICCV	Avaliable
NSLT + Luong ✦	2018	7.56	RGB-Frames	CVPR	Avaliable
GASLT	2023	4.07	RGB-Frames	CVPR	Avaliable
SL-Transf ❉	2020	3.03	RGB-Frames	CVPR	Avaliable
Tspnet ★	2020	2.97	RGB-Frames	NeurIPS	Avaliable

CSL-Daily Gloss-Free Table Notation:

✦ denotes results reproduced by BN-TIN-Transf

❉ denotes results reproduced by GFSLT-VLP

★ denotes results reproduced by GASLT

---

Results on How2Sign dataset

Gloss-free

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
SSVP-SLT-LSP	2024	15.5	RGB-Frames	ArXiv	Avaliable
UNI-SIGN	2025	14.9	RGB-Frames, Skeleton-Keypoints	ICLR	Avaliable
SignMusketeers	2024	14.3	Face & Left/Right Hand RGB crops, Skeleton-Keypoints	ArXiv	Avaliable
VAP	2024	12.87	RGB-Frames	ECCV	-
YouTube-ASL	2024	12.39	RGB-Frames	NeurIPS	-
SLT-SEM	2024	11.7	RGB-Frames	ACL	Avaliable
FLa-LLM	2024	9.66	RGB-Frames	LREC-COLING	-
SLT-IV	2023	8.03	RGB-Frames	CVPRW	Avaliable
GloFE-VN	2023	2.24	RGB-Frames	ArXiv	Avaliable
UniGloR	2024	2.22	RGB-Frames	ArXiv	-
TF-H2S	2022	2.21	RGB-Frames	-	-

---

Results on OpenASL dataset

Gloss-free

Model Name	Year	BLEU-4	Model Input	Conference/Journal	Code
C²RL	2024	13.21	RGB-Frames	ArXiv	-
GloFE-VN	2023	7.06	RGB-Frames	ArXiv	Avaliable
OpenASL	2022	6.72	RGB-Frames	EMNLP	Avaliable
I3D-Transformer	2022	5.66	RGB-Frames	-	-
NSLT ❒	2018	4.58	RGB-Frames	CVPR	Avaliable

OpenASL Gloss-Free Table Notation:

❒ denotes results reproduced by OpenASL

---

SLP Leaderboard

Results on Phoenix-2014T dataset

Gloss to Pose

Model Name	Year	BLEU-4	WER	DTW-P	Conference/Journal	Code
FS-NET	2022	18.78	-	-	CVPR	-
Adversarial Training	2020	11.7	-	-	BMVC	-
Progressive Transf	2020	10.43	-	-	ECCV	Avaliable
NSLP-G	2021	9.39	-	-	BMVC	-
LVMCN	2024	9.36	-	10.14	ArXiv	-
Data-Driven	2024	9.17	-	-	SEM	-
Sign-IDD	2024	9.08	-	-	ArXiv	-
GEN-OBT	2022	8.01	81.78	10.07	ACM	-
GCDM	2024	7.91	81.94	11.10	ACM	-
G2P-DDM	2024	7.50	-	-	AAAI	-
NAT-EA	2021	6.66	82.01	-	ACM MM	-
NAT-AT	2021	5.53	88.15	-	ACM	-

Text to Pose

Model Name	Year	BLEU-4	DTW-P	with Gloss	Conference/Journal	Code
Spoken2Sign	2024	25.46	-	✅	ECCV	-
SignDiff	2023	22.15	-	❌	ArXiv	-
FS-NET	2022	21.10	-	❌	CVPR	-
SignGen	2024	19.71	-	❌	ECCV	-
T2S-GPT	2024	11.87	-	❌	ArXiv	-
NSLP-G (+ Finetuning)	2021	11.07	-	❌	BMVC	-
NSLP-G	2021	10.95	-	❌	BMVC	-
Adversarial Training	2020	10.81	-	❌	BMVC	-
Progressive Transf	2020	10.51	-	❌	ECCV	Avaliable
Progressive Transf	2020	9.68	-	✅	ECCV	Avaliable
Data-Driven	2024	9.20	-	❌	SEM	-
IFECE (MFs)	2023	8.19	-	✅	SEM	-
SignVQNet	2024	6.85	-	❌	FG	-
IFECE (MFs + FI + AUs)	2023	5.76	-	✅	SEM	-
MS2SL	2024	4.26	-	❌	ArXiv	-

Results on CSL-Daily dataset

Text to Pose

Model Name	Year	BLEU-4	DTW-P	with Gloss	Conference/Journal	Code
Spoken2Sign	2024	21.44	-	-	✅	ECCV

🔍 Challenge & Workshop

CVPR 2025 SLRTP2025 Sign Language Production Challenge

• Challenge Summary Papar: SLRTP2025 Sign Language Production Challenge: Methodology, Results and Future Work
• Please refer to this page for more information.