AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Propagating Over Phrase Relations for One-Stage Visual Grounding

Sibei Yang, Guanbin Li, Yizhou Yu

ECCV 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 33 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 phrase-conditional enhance maps (ablation)multimodal baseline · Flickr30K Entities testaccuracy (%): 68.15 -> 68.46Improved
add linguistic graph propagation (1 step) (ablation)enhance model · Flickr30K Entities testaccuracy (%): 68.46 -> 69.53Improved
propagate twice instead of once over the linguistic graph (ablation)LSPN · Flickr30K Entities testaccuracy (%): 69.53 -> 69.52No clear effect
use bidirectional instead of subject-to-object only propagation (ablation)LSPN · Flickr30K Entities testaccuracy (%): 68.81 -> 69.53Improved
use bidirectional instead of object-to-subject only propagation (ablation)LSPN · Flickr30K Entities testaccuracy (%): 68.97 -> 69.53Improved
use parsed linguistic graph instead of nearest-noun-phrase contextual graph (ablation)LSPN · Flickr30K Entities testaccuracy (%): 67.14 -> 69.53Improved

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