AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Connecting Vision and Language with Localized Narratives

Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, Vittorio Ferrari

ECCV 2020 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 191 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
use spoken narration with mouse traces instead of two-stage entity marking and box drawingLocalized Narratives annotation · Annotation costseconds per image: 643 seconds per image for Flickr30k Entities, 4.4x slowerImproved
add automatic quality control matching spoken and written transcriptsLocalized Narratives annotation · Annotation qualityfraction of annotations discarded: 23.5% of all annotations discardedImproved
describe an image with a paragraph rather than one sentenceLocalized Narratives vs COCO Captions · Caption richnessnouns per caption: 3.6 -> 10.8Improved
add per-word mouse trace grounding to paragraph captionsLocalized Narratives vs Stanford Visual Paragraphs · Dataset scaleimages annotated: 40x more images than Stanford Visual ParagraphsImproved
use free-form mouse hover tracesLocalized Narratives · Localization accuracytrace points inside correct boxMixed

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