Richard Bowden

papers

1,238

total citations

papers (14)

Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation

CVPR 2020arXiv

662

citations

Progressive Transformers for End-to-End Sign Language Production

ECCV 2020arXiv

194

citations

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

CVPR 2020arXiv

113

citations

Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production

CVPR 2022arXiv

citations

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

CVPR 2020arXiv

citations

Learning Adaptive Neighborhoods for Graph Neural Networks

ICCV 2023arXiv

citations

VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts

CVPR 2021arXiv

citations

"The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping

CVPR 2022arXiv

citations

VALLR: Visual ASR Language Model for Lip Reading

ICCV 2025arXiv

citations

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

NEURIPS 2025arXiv

citations

SignRep: Enhancing Self-Supervised Sign Representations

ICCV 2025arXiv

citations

Richard Bowden

papers (14)

Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation

Progressive Transformers for End-to-End Sign Language Production

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production

Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives

Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV

NestedVAE: Isolating Common Factors via Weak Supervision

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

Learning Adaptive Neighborhoods for Graph Neural Networks

VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts

"The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping

VALLR: Visual ASR Language Model for Lip Reading

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

SignRep: Enhancing Self-Supervised Sign Representations

papers (14)

Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation

Progressive Transformers for End-to-End Sign Language Production

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production

Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives

Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV

NestedVAE: Isolating Common Factors via Weak Supervision

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

Learning Adaptive Neighborhoods for Graph Neural Networks

VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts

"The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping

VALLR: Visual ASR Language Model for Lip Reading

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

SignRep: Enhancing Self-Supervised Sign Representations