AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

G3raphGround: Graph-Based Language Grounding

Mohit Bajaj, Lanjun Wang, Leonid Sigal

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 58 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 the phrase graph (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 60.82 -> 63.87Improved
add the visual graph (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 62.23 -> 63.87Improved
add the fusion graph (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 59.13 -> 63.87Improved
add the fusion graph (ablation)G3RAPHGROUND · ReferIt Game testphrase grounding accuracy (%): 36.54 -> 41.79Improved
add the visual graph and fusion graph together (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 56.32 -> 63.87Improved
add the full image embedding as context (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 62.32 -> 63.87Improved
add the full caption embedding as context (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 62.73 -> 63.87Improved
add the full caption embedding as context (ablation)G3RAPHGROUND · ReferIt Game testphrase grounding accuracy (%): 41.79 -> 41.79No clear effect
add the full image embedding as context (ablation)G3RAPHGROUND · ReferIt Game testphrase grounding accuracy (%): 40.92 -> 41.79Improved
use per-phrase conditional fusion graphs instead of one big fusion graph (ablation)GGFusionBase · Flickr30k Entities testphrase grounding accuracy (%): 60.41 -> 63.87Improved
add count prediction branch replacing threshold post-processing (ablation)G3RAPHGROUND · Flickr30k Entities testphrase grounding accuracy (%): 63.87 -> 66.93Improved
add count prediction branch replacing threshold post-processing (ablation)G3RAPHGROUND · ReferIt Game testphrase grounding accuracy (%): 41.79 -> 44.91Improved

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