atlas

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

Unambiguous Text Localization and Retrieval for Cluttered Scenes

CVPR 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 31 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 recurrent dense text localization instead of Tian et al.'s methodDTLN · ICDAR 2013PASCAL Eval F: 0.88 -> 0.85Hurt
Use recurrent dense text localization instead of Tian et al.'s methodDTLN · SVTPASCAL Eval F: 0.66 -> 0.64Hurt
Use DTLN instead of FCRNall+filtsscene text localization · ICDAR 2013DetEval F: 0.83 -> 0.85Helped
Use DTLN instead of FCRNall+filtsscene text localization · SVTDetEval F: 0.27 -> 0.28Helped
Use CRTR instead of SCRC for text retrievalCOCO-TextRef retrieval with annotated text regions · COCO-TextRefP@1: 0.457 -> 0.582Helped
Use CRTR instead of SCRC to rank DTLN-generated text regionsCOCO-TextRef retrieval · COCO-TextRefR@1: 0.135 -> 0.184Helped
Use CRTR instead of SCRC to rank DTLN-generated text regionsCOCO-TextRef retrieval · COCO-TextRefR@5: 0.313 -> 0.394Helped

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