AI Paper Atlas

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

Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models

Bryan A. Plummer, Liwei Wang, Chris M. Cervantes, Juan Carlos Caicedo, Julia Hockenmaier, Svetlana Lazebnik

IJCV 2016 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 1,542 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
switch from classification VGG19 to detection Fast RCNN featuresCCA · Flickr30k Entities phrase localizationR@1: 30.83 -> 41.77Improved
add detector scores for phrases mapped to PASCAL categories (ablation)CCA · Flickr30k Entities phrase localizationR@1: 41.77 -> 43.84Improved
use detector alone instead of CCA for phrases that have itCCA or Detector · Flickr30k Entities phrase localizationR@1: 41.77 -> 42.58Improved
add region size bias (ablation)CCA+Detector · Flickr30k Entities phrase localizationR@1: 43.84 -> 49.22Improved
add color classifier term (ablation)CCA+Detector · Flickr30k Entities phrase localizationR@1: 43.84 -> 45.79Improved
add color term on top of size term (ablation)CCA+Detector+Size · Flickr30k Entities phrase localizationR@1: 49.22 -> 50.89Improved
add color term on top of size term (clothing phrases) (ablation)CCA+Detector+Size · Flickr30k Entities clothing phrasesR@1: 39.20 -> 46.88Improved
fine-tune Fast RCNN on colors instead of linear SVM on detector featurescolor classifier · Color classificationaccuracy: 16% -> 80.47%Improved
train CCA on all region-phrase pairs instead of resampling to at most N=10 per phrase (ablation)CCA · Flickr30k Entities phrase localizationR@1Hurt
add GMM Fisher vectors to HGLMM (ablation)phrase features · Flickr30k Entities phrase localizationR@1No clear effect
add region-phrase distance to whole-image CCA (VGG19) for retrievalHGLMM FV+VGG19 · Flickr30k image annotationR@1: 36.5% -> 37.0%Improved
use full region-phrase model instead of basic VGG model in retrievalWeighted Distance · Flickr30k image annotationR@1: 37.0% -> 37.5%No clear effect

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