AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Towards Zero-Shot Sign Language Recognition

Yunus Can Bilge, Ramazan Gökberk Cinbiş, Nazlı İkizler-Cinbiş

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 66 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
add hand-region stream to body stream (ablation)LLE · ASL-Text ZSLtop-1 accuracy: 11.4 -> 18.0Improved
add hand-region stream to body stream (ablation)LLE · MS-ZSSLR-C ZSLtop-1 accuracy: 5.54 -> 5.74Improved
replace average pooling with bi-LSTM temporal model (ablation)LLE · ASL-Text ZSLtop-1 accuracy: 18.0 -> 20.9Improved
replace average pooling with TSM temporal model (ablation)LLE · ASL-Text and MS-ZSSLR-C ZSLtop-1 accuracy: ASL-Text 18.0 -> 16.8; MS-ZSSLR-C 5.74 -> 7.01Mixed
replace average pooling with LSTM (ablation)LLE · ASL-Text ZSLtop-1 accuracy: 18.0 -> 18.2No clear effect
add attribute embeddings to text embeddings (ablation)LLE with bi-LSTM · ASL-Text ZSLtop-1 accuracy: 20.9 -> 31.3Improved
add attribute embeddings to text embeddings (ablation)LLE with TSM · MS-ZSSLR-C ZSLtop-1 accuracy: 7.01 -> 14.7Improved
add attributes to text embeddings (top-5) (ablation)LLE with bi-LSTM · MS-ZSSLR-C ZSLtop-5 accuracy: 19.9 -> 45.2Improved
use attributes instead of text embeddings (ablation)LLE with bi-LSTM · ASL-Text ZSLtop-1 accuracy: 20.9 -> 23.7Improved
add linear reduction of text embedding to d_t=64 (ablation)LLE with bi-LSTM · ASL-Text ZSL validationtop-1 accuracy: 26.3 to 35.5Improved
train on wild samples instead of clean samples (ablation)LLE with TSM · MS-ZSSLR-C clean evaluationtop-1 accuracy: 14.7 -> 10.3Hurt
use LLE instead of SAE (ablation)ZSL formulation · ASL-Text ZSLtop-1 accuracy: 8.0 -> 11.4Improved

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