AI Paper Atlas

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

Automatic Dense Annotation of Large-Vocabulary Sign Language Videos

Liliane Momeni, Hannah Bull, K R Prajwal, Samuel Albanie, Gül Varol, Andrew Zisserman

ECCV 2022 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
expand sign vocabulary from 2K to 8K with 670K annotationsI3D feature extractor · SENT-TEST I3D predictions (subtitle independent)Recall: 25.5 -> 26.3Improved
replace prior keyword spotter with Transpotter for mouthingsMouthing annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 15.1 -> 20.4Improved
finetune Transpotter on sign language data by bootstrapping (ablation)Mouthing annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 20.4 -> 23.6Improved
add subtitle alignment to mouthing spotting (ablation)Mouthing annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 23.6 -> 27.4Improved
add subtitle alignment to dictionary spotting (ablation)Dictionary annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 24.0 -> 24.2No clear effect
query synonyms for mouthing spotting (ablation)Mouthing annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 27.4 -> 25.3Hurt
query synonyms for dictionary spotting (ablation)Dictionary annotations · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 24.2 -> 26.0Improved
add attention spottings A (ablation)M* + D* · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 29.0 -> 29.6Improved
add pseudo-label spottings P (ablation)M* + D* + A · SENT-TEST spottings (subtitle dependent)Recall: 21.9 -> 25.4Improved
add pseudo-label spottings P (ablation)M* + D* + A · SENT-TEST MLP predictions 8KRecallNo clear effect
combine dictionary spottings with improved mouthing (ablation)M* · SENT-TEST MLP predictions 8K (subtitle independent)Recall: 27.4 -> 29.0Improved

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