AI Paper Atlas

Research map / Video / Video segmentation and tracking

Fingerspelling Recognition in the Wild With Iterative Visual Attention

Bowen Shi, Aurora Martinez Del Rio, Jonathan Keane, Diane Brentari, Greg Shakhnarovich, Karen Livescu

ICCV 2019 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 82 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 standard visual attention (ablation)whole frame · ChicagoFSWild devletter accuracy (%): 11.0 -> 23.0Improved
replace standard attention with iterative attention (ablation)whole frame+attention · ChicagoFSWild devletter accuracy (%): 23.0 -> 42.8Improved
replace standard attention with iterative attention (ablation)face ROI+attention · ChicagoFSWild devletter accuracy (%): 33.4 -> 45.6Improved
replace standard attention with iterative attention (ablation)hand ROI+attention · ChicagoFSWild devletter accuracy (%): 41.4 -> 45.0Improved
add language model (ablation)Ours+face ROI · ChicagoFSWild devletter accuracy (%): 45.6 -> 46.8Improved
add language model (ablation)Ours+whole frame · ChicagoFSWild devletter accuracy (%): 42.8 -> 43.6Improved
add ChicagoFSWild+ training data (ablation)Ours+face ROI+LM · ChicagoFSWild testletter accuracy (%): 45.1 -> 61.2Improved
add ChicagoFSWild+ training data (ablation)Hand ROI+LM · ChicagoFSWild testletter accuracy (%): 41.9 -> 57.5Improved
add ChicagoFSWild+ training data (ablation)Ours+whole frame+LM · ChicagoFSWild+ testletter accuracy (%): 43.8 -> 61.0Improved
zoom into region instead of enlarging input, with motion prior (ablation)Ours+face ROI · ChicagoFSWild dev, face ROI, R=0.9^3letter accuracy (%): 39.3 -> 39.6No clear effect
zoom into region instead of enlarging input, no motion prior (ablation)Ours+face ROI · ChicagoFSWild dev, face ROI, R=0.9^3letter accuracy (%): 38.1 -> 39.8Improved
use iterative-attention ROI as hand detector instead of off-the-shelf detector (ablation)face ROI model · ChicagoFSWild hand annotations (200 frames)average IoU at miss rate 0.158: 0.213 -> 0.443Improved

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