CVPR 2026 Open Access Repository

2nd Workshop on Multimodal Sign Language Recognition

Cross-Modal Fusion for Tamil Sign Language Vowel Recognition from RGB Video and Flex Sensor Data: Manisha A,

Tamilselvi S,

Nityashree S; [pdf]
[bibtex]
@InProceedings{A_2026_CVPR, author = {A, Manisha and S, Tamilselvi and S, Nityashree}, title = {Cross-Modal Fusion for Tamil Sign Language Vowel Recognition from RGB Video and Flex Sensor Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10455-10462} }
LiftSign at SignEval 2026: A Distilled Multi-Stream Ensemble with Temporal Lift Pooling for Skeleton-Based Sign Language Recognition: Nguyen Tu Nam,

Hiroki Takahashi; [pdf]
[bibtex]
@InProceedings{Nam_2026_CVPR, author = {Nam, Nguyen Tu and Takahashi, Hiroki}, title = {LiftSign at SignEval 2026: A Distilled Multi-Stream Ensemble with Temporal Lift Pooling for Skeleton-Based Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10567-10574} }
Isolated Sign Language Recognition via MediaPipe Landmarks: A Case Study On Indian Sign Language: Abhishek Bharadwaj Varanasi,

Manjira Sinha,

Tirthankar Dasgupta; [pdf]
[bibtex]
@InProceedings{Varanasi_2026_CVPR, author = {Varanasi, Abhishek Bharadwaj and Sinha, Manjira and Dasgupta, Tirthankar}, title = {Isolated Sign Language Recognition via MediaPipe Landmarks: A Case Study On Indian Sign Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10595-10604} }
TWASEL at SignEval 2026: Adaptive Multi-Stream Pose Fusion for Continuous Sign Language Recognition: Sadam Al-Azani,

Safwan Nabeel,

Qasim Al Mahfood,

Mohanad Mohamed; [pdf]
[bibtex]
@InProceedings{Al-Azani_2026_CVPR, author = {Al-Azani, Sadam and Nabeel, Safwan and Al Mahfood, Qasim and Mohamed, Mohanad}, title = {TWASEL at SignEval 2026: Adaptive Multi-Stream Pose Fusion for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10473-10480} }
CAPY at SignEval 2026: Range-Aware Transformer with Kinematic Feature Augmentation for Robust Radar-Based Sign Language Recognition: Duc-Thien Tran,

Le-Vu Nguyen-Dinh,

Hoang-Nam Trinh,

Thanh-Toan Le-Ngo,

Tinh-Anh Nguyen-Nhu; [pdf]
[bibtex]
@InProceedings{Tran_2026_CVPR, author = {Tran, Duc-Thien and Nguyen-Dinh, Le-Vu and Trinh, Hoang-Nam and Le-Ngo, Thanh-Toan and Nguyen-Nhu, Tinh-Anh}, title = {CAPY at SignEval 2026: Range-Aware Transformer with Kinematic Feature Augmentation for Robust Radar-Based Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10585-10594} }
Sign Language Recognition in the Age of LLMs: Václav Javorek,

Jakub Honzík,

Ivan Gruber,

Tomáš Železný,

Marek Hrúz; [pdf]
[bibtex]
@InProceedings{Javorek_2026_CVPR, author = {Javorek, V\'aclav and Honz{\'\i}k, Jakub and Gruber, Ivan and \v{Z}elezn\'y, Tom\'a\v{s} and Hr\'uz, Marek}, title = {Sign Language Recognition in the Age of LLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10511-10519} }
Sign Language Recognition with Visual State Space Model: Bogdan Kwolek; [pdf]
[bibtex]
@InProceedings{Kwolek_2026_CVPR, author = {Kwolek, Bogdan}, title = {Sign Language Recognition with Visual State Space Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10520-10527} }
PRISM at SignEval 2026: Privacy-Preserving Radar-Based Italian Sign Language Recognition via ConvNeXt and Ensemble Learning: Huayu Wang,

Zhiwei Tan,

Jia-Xian Jian,

Simon Zou,

Shiqi Huang,

Pau-Choo Chung,

Jenq-Neng Hwang; [pdf]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Huayu and Tan, Zhiwei and Jian, Jia-Xian and Zou, Simon and Huang, Shiqi and Chung, Pau-Choo and Hwang, Jenq-Neng}, title = {PRISM at SignEval 2026: Privacy-Preserving Radar-Based Italian Sign Language Recognition via ConvNeXt and Ensemble Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10622-10630} }
CSLRTransformer: A Pose-Only System for Continuous Sign Language Recognition: Rosario Licciardello,

Georgia Fargetta,

Alessandro Ortis,

Sebastiano Battiato; [pdf]
[bibtex]
@InProceedings{Licciardello_2026_CVPR, author = {Licciardello, Rosario and Fargetta, Georgia and Ortis, Alessandro and Battiato, Sebastiano}, title = {CSLRTransformer: A Pose-Only System for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10538-10545} }
SignEval 2026 Challenge Results: Ahmed Hasanaath,

Raffaele Mineo,

Hamzah Luqman,

Sarah Alyami,

Maad Alowaifeer,

Amelia Sorrenti,

Gaia Caligiore,

Sabina Fontana,

Egidio Ragonese,

Giovanni Bellitto,

Federica Proietto Salanitri,

Concetto Spampinato,

Motaz Alfarraj,

Mufti Mahmud,

Simone Palazzo,

Nour Imane Zeghib; [pdf]
[bibtex]
@InProceedings{Hasanaath_2026_CVPR, author = {Hasanaath, Ahmed and Mineo, Raffaele and Luqman, Hamzah and Alyami, Sarah and Alowaifeer, Maad and Sorrenti, Amelia and Caligiore, Gaia and Fontana, Sabina and Ragonese, Egidio and Bellitto, Giovanni and Salanitri, Federica Proietto and Spampinato, Concetto and Alfarraj, Motaz and Mahmud, Mufti and Palazzo, Simone and Zeghib, Nour Imane}, title = {SignEval 2026 Challenge Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10490-10501} }
Towards Inclusive Sign Language Recognition: Dataset Gaps, Ethical Challenges, and Deployment Barriers in the Indian Context: Tanu Wadhera,

Mufti Mahmud,

Ritika Dhaneshwar; [pdf]
[bibtex]
@InProceedings{Wadhera_2026_CVPR, author = {Wadhera, Tanu and Mahmud, Mufti and Dhaneshwar, Ritika}, title = {Towards Inclusive Sign Language Recognition: Dataset Gaps, Ethical Challenges, and Deployment Barriers in the Indian Context}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10612-10621} }
Geometry-Aware Metric Learning for Cross-Lingual Few-Shot Sign Language Recognition on Static Hand Keypoints: Chayanin Chamachot,

Kanokphan Lertniphonphan; [pdf]
[bibtex]
@InProceedings{Chamachot_2026_CVPR, author = {Chamachot, Chayanin and Lertniphonphan, Kanokphan}, title = {Geometry-Aware Metric Learning for Cross-Lingual Few-Shot Sign Language Recognition on Static Hand Keypoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10481-10489} }
AI4Good at SignEval 2026: Mix, Measure, Merge with Spectro-Temporal Augmentation and Multi-Model Fusion for Isolated Radar-Based Italian Sign Language Recognition: Cristian Lazo Quispe,

Gissella Bejarano; [pdf]
[bibtex]
@InProceedings{Quispe_2026_CVPR, author = {Quispe, Cristian Lazo and Bejarano, Gissella}, title = {AI4Good at SignEval 2026: Mix, Measure, Merge with Spectro-Temporal Augmentation and Multi-Model Fusion for Isolated Radar-Based Italian Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10528-10537} }
RTM-CNN at SignEval 2026: A Lightweight Convolutional Baseline for RTM Sequence Classification: Abhishek Bharadwaj Varanasi,

Manjira Sinha,

Tirthankar Dasgupta; [pdf]
[bibtex]
@InProceedings{Varanasi_2026_CVPR, author = {Varanasi, Abhishek Bharadwaj and Sinha, Manjira and Dasgupta, Tirthankar}, title = {RTM-CNN at SignEval 2026: A Lightweight Convolutional Baseline for RTM Sequence Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10605-10611} }
Dynamic Rank Compressed Network: A Novel Approach for Efficient Bangla Sign Language Recognition: Nadim Ahmed,

Md. Ashraful Babu,

Md. Mortuza Ahmmed,

M. Mostafizur Rahman,

David J. Brown,

Mufti Mahmud; [pdf]
[bibtex]
@InProceedings{Ahmed_2026_CVPR, author = {Ahmed, Nadim and Babu, Md. Ashraful and Ahmmed, Md. Mortuza and Rahman, M. Mostafizur and Brown, David J. and Mahmud, Mufti}, title = {Dynamic Rank Compressed Network: A Novel Approach for Efficient Bangla Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10463-10472} }
A Benchmark for Radar-Based Italian Sign Language Recognition using Frequency-Domain Range-Time Maps: Raffaele Mineo,

Amelia Sorrenti,

Gaia Caligiore,

Federica Proietto Salanitri,

Giovanni Bellitto,

Senya Polikovsky,

Sabina Fontana,

Egidio Ragonese,

Concetto Spampinato,

Simone Palazzo; [pdf]
[bibtex]
@InProceedings{Mineo_2026_CVPR, author = {Mineo, Raffaele and Sorrenti, Amelia and Caligiore, Gaia and Salanitri, Federica Proietto and Bellitto, Giovanni and Polikovsky, Senya and Fontana, Sabina and Ragonese, Egidio and Spampinato, Concetto and Palazzo, Simone}, title = {A Benchmark for Radar-Based Italian Sign Language Recognition using Frequency-Domain Range-Time Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10556-10566} }
CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition: Md. Shakhoyat Rahman Shujon,

Sheikh Md. Galib Mahim,

Md. Milon Islam,

Md Rezwanul Haque,

Md Rabiul Islam,

Hamdi Altaheri,

Fakhri Karray; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shujon_2026_CVPR, author = {Shujon, Md. Shakhoyat Rahman and Mahim, Sheikh Md. Galib and Islam, Md. Milon and Haque, Md Rezwanul and Islam, Md Rabiul and Altaheri, Hamdi and Karray, Fakhri}, title = {CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10575-10584} }
TEMPO at SignEval 2026: Signer-Independent Temporal Modeling and Vocabulary-Constrained Post-Processing for Arabic CSLR: Ahmed Hassan,

Nadine Alsayad; [pdf]
[bibtex]
@InProceedings{Hassan_2026_CVPR, author = {Hassan, Ahmed and Alsayad, Nadine}, title = {TEMPO at SignEval 2026: Signer-Independent Temporal Modeling and Vocabulary-Constrained Post-Processing for Arabic CSLR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10502-10510} }
MSBAD at SignEval 2026: Multi-Scale Born-Again Distillation Ensemble for Radar-Based Sign Language Recognition: Arkadip Maitra,

Suvajit Patra,

Soumitra Samanta; [pdf]
[bibtex]
@InProceedings{Maitra_2026_CVPR, author = {Maitra, Arkadip and Patra, Suvajit and Samanta, Soumitra}, title = {MSBAD at SignEval 2026: Multi-Scale Born-Again Distillation Ensemble for Radar-Based Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {10546-10555} }