AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

An Alternative Deep Feature Approach to Line Level Keyword Spotting

George Retsinas, Georgios Louloudis, Nikolaos Stamatopoulos, Giorgos Sfikas, Basilis Gatos

CVPR 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 10 citations (OpenAlex)

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
Use a common-space encoder for text-string queriesProposed line-level KWS · IAMDB2 globalMAP (%): 75.31Improved
Use text-string queries instead of query imagesProposed line-level KWS · IAMDB1 localMAP (%): 84.25 -> 88.73Improved
Use query strings instead of query imagesProposed line-level KWS · IAMDB1 globalMAP (%): 73.16 -> 83.15Improved
Use temporal pyramidal pooling rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbE-PHOCMAP (%): 83.27 -> 83.98No clear effect
Use zoning into 5 segments rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbE-PHOCMAP (%): 83.27 -> 83.66No clear effect
Use temporal pyramidal pooling rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbE-cfeatMAP (%): 81.73 -> 82.15No clear effect
Use zoning into 5 segments rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbE-cfeatMAP (%): 81.73 -> 82.24No clear effect
Use temporal pyramidal pooling rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbS-PHOCMAP (%): 91.11 -> 93.01No clear effect
Use zoning into 5 segments rather than entire-map max pooling (ablation)PHOC estimator · IAM word-level QbS-PHOCMAP (%): 91.11 -> 92.47No clear effect
Add ROI-based training with expanded word images (ablation)Proposed line-level KWS · IAMDB1 local QbSMAP (%): 87.13 -> 88.73Improved
Add ROI-based training with expanded word images (ablation)Proposed line-level KWS · IAMDB1 global QbSMAP (%): 79.14 -> 83.15Improved
Add ROI-based training with expanded word images (ablation)Proposed line-level KWS · IAMDB1 local QbEMAP (%): 83.01 -> 84.25Improved

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