Research map / Large language models / Language, safety and interpretability
Progressive Transformers for End-to-End Sign Language Production
Ben Saunders, Necati Cihan Camgoz, Richard Bowden
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add future prediction of the next 10 frames (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test) | BLEU-4: 5.03 -> 8.38 | Improved |
| feed only counter values as target input (just counter) (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test) | BLEU-4: 5.03 -> 9.16 | Improved |
| add Gaussian noise augmentation to skeleton poses (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test) | BLEU-4: 5.03 -> 10.02 | Improved |
| combine future prediction with Gaussian noise (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test) | BLEU-4: 5.03 -> 10.43 | Improved |
| add Gaussian noise on top of future prediction (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (dev) | BLEU-4: 9.96 -> 11.93 | Improved |
| add future prediction to Gaussian noise (ablation) | Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test) | BLEU-4: 10.02 -> 10.43 | Improved |
| use gloss intermediary (T2G2P) instead of direct text to pose | Progressive Transformer · PHOENIX14T text-to-pose (test) | BLEU-4: 10.51 -> 9.68 | Hurt |
| use gloss intermediary instead of direct text input | Progressive Transformer · PHOENIX14T text-to-pose (dev) | BLEU-4: 11.82 -> 11.43 | Hurt |
| use gloss intermediary instead of direct text input | Progressive Transformer · PHOENIX14T text-to-pose (dev) | BLEU-1: 31.41 -> 33.12 | Improved |
| use transformer instead of GRU encoder-decoder for text to gloss | Symbolic Transformer · PHOENIX14T text-to-gloss (test) | BLEU-4: 15.26 -> 19.10 | Improved |
Closest papers by meaning
- Scaling Sign Language Translation (NeurIPS 2024 · similarity 0.91)
- Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment (NeurIPS 2026 · similarity 0.90)
- Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation (NeurIPS 2025 · similarity 0.89)
- Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment (AAAI 2024 · similarity 0.89)
- Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text (CVPR 2024 · similarity 0.89)
- Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
