AI Paper Atlas

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

C2SLR: Consistency-Enhanced Continuous Sign Language Recognition

Ronglai Zuo, Brian Mak

CVPR 2022 · Large language models › Language, safety and interpretability · approach: Sign and cross-lingual translation

Check 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
Add keypoint-guided spatial attention consistency (SAC) (ablation)VLT · PHOENIX-2014WER: 21.5 -> 20.8Improved
Add sentence embedding consistency (SEC) (ablation)VLT · PHOENIX-2014WER: 21.5 -> 20.9Improved
Add SAC and SEC together (ablation)VLT · PHOENIX-2014WER: 21.5 -> 20.4Improved
Add SAC and SEC together (ablation)VTB · PHOENIX-2014WER: 25.0 -> 22.6Improved
Add SAC and SEC together (ablation)CT · PHOENIX-2014WER: 26.1 -> 24.5Improved
Add spatial attention without its heatmap-guidance loss (ablation)VLT · PHOENIX-2014WER: 21.5 -> 21.4No clear effect
Add dynamic channel weights to the spatial attention module (ablation)VLT + SAC · PHOENIX-2014WER: 21.3 -> 20.8Improved
Add heatmap post-processing and refinement (ablation)VLT + SAC · PHOENIX-2014WER: 21.7 -> 20.8Improved
Use a Transformer plus depth-wise TCN sentence embedding extractor rather than Transformer alone (ablation)VLT + SEC · PHOENIX-2014WER: 21.1 -> 20.9Improved
Use a Transformer-based sentence embedding extractor rather than BiLSTM (ablation)VLT + SEC · PHOENIX-2014WER: 21.3 -> 20.9Improved
Add negative sampling to SEC (ablation)VLT + SEC · PHOENIX-2014WER: 21.5 -> 20.9Improved
Enforce consistency at the sentence level instead of the frame level (ablation)VLT · PHOENIX-2014WER: 21.6 -> 20.9Improved

Later papers that compared with this method

2 later accepted papers report C2SLR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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