AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning

Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka, Stefan Schmid, Yuqicheng Zhu, Jingcheng Wu, Nadeem Nazer, Steffen Staab

AAAI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 3 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 lead images of entities (ablation)KnowCoL-L · OVEN entity testHM: 30.0 -> 31.5Improved
add KG hierarchical knowledge (ablation)KnowCoL-L · OVEN entity testunseen accuracy: 25.3 -> 29.1Improved
use simple addition instead of 2-layer MLP fusion (ablation)KnowCoL-L · OVEN entity testHM: 28.7 -> 31.5Improved
use transformer encoder fusion instead of addition (ablation)KnowCoL-L · OVEN entity testseen vs unseen accuracy: seen 34.3 -> 54.4; unseen 29.1 -> 16.6Mixed
add local image patch tokens to transformer fusion (ablation)KnowCoL-L · OVEN entity testunseen accuracy: 16.6 -> 17.9Improved
use TransE with cosine instead of Euclidean distance (ablation)KnowCoL-L · OVEN entity testHM: 31.0 -> 31.5Improved
use TransE instead of DistMult (ablation)KnowCoL-L · OVEN entity testHM: 30.9 -> 31.5Improved
scale CLIP backbone from ViT-L to ViT-bigG (ablation)KnowCoL · OVEN entity testHM: 31.5 -> 38.8Improved
add knowledge-guided contrastive learning on same ViT-L-14CLIP2CLIP · OVEN entity testHM: 11.4 -> 31.5Improved
KnowCoL-bigG vs Auto-VER-14B on seen entitiesAuto-VER-14B · OVEN entity testseen accuracy: 65.0 -> 41.8Hurt
KnowCoL-bigG vs Auto-VER-14B on unseen entitiesAuto-VER-14B · OVEN entity testunseen accuracy: 18.6 -> 36.1Improved

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