AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Gloss-Free Sign Language Translation: Improving from Visual-Language Pretraining

Benjia Zhou, Zhigang Chen, Albert Clapés, Jun Wan, Yanyan Liang, Sergio Escalera, Zhen Lei, Du Zhang

ICCV 2023 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 130 citations (OpenAlex)

This paper tried a common change: Add data augmentation

add strong data augmentation in stage 1 on top of VLP · PHOENIX14T test · BLEU-4: 19.77 -> 21.23 Improved

What 689 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 changedWhereMeasuredEffect
add visual-language pretraining (CLIP-style plus masked text) with strong augmentation (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 21.44Improved
add VLP with only lightweight augmentation (random crop) (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 19.77No clear effect
add strong data augmentation in stage 1 on top of VLP (ablation)GFSLT-VLP · PHOENIX14T testBLEU-4: 19.77 -> 21.23Improved
add strong data augmentation in stage 2 without VLP (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 18.41Hurt
fine-tune Visual Embedding and Transformer Encoder jointly from pretrained weights (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 21.43Improved
initialize only Visual Embedding from pretraining (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 18.93Hurt
initialize Text Decoder from pretraining (ablation)GFSLT · PHOENIX14T testBLEU-4: 19.66 -> 20.27Improved
train stage 2 for 200 instead of 40 epochs (ablation)GFSLT-VLP · PHOENIX14TBLEU-4: 18.23 -> 22.12Improved
increase stage 1 pretraining beyond 80 epochs (ablation)GFSLT-VLP · PHOENIX14TBLEU-4: 22.12 -> 22.13No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy