AI Paper Atlas

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

WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition

Shan Ning, Longtian Qiu, Jiaxuan Sun, Xuming He

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 0 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 Wikipedia text descriptions to image-based entity representation (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 44.8 -> 59.7Improved
add entity images to text-only entity representation (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 50.8 -> 59.7Improved
add visual-based clustering alone as hard negative batching (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 59.7 -> 59.7No clear effect
add synthetic hard negatives alone without visual clustering (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 59.7 -> 58.9Hurt
combine visual clustering with synthetic hard negative generation (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 59.7 -> 61.2Improved
use EVA-CLIP 8B instead of CLIP ViT-L as visual encoder (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 41.6 -> 61.2Improved
use LLaMa3.2 1B instead of EVA-CLIP text encoder (ablation)WikiCLIP-S · InfoSeek (val)Overall accuracy: 58.1 -> 61.2Improved
increase encoded Wikipedia text length beyond 256 tokens (ablation)WikiCLIP-S · InfoSeek (val)accuracyHurt
scale LLM from 3B to 8B (ablation)WikiCLIP · InfoSeek (val)accuracyNo clear effect
scale LLM from 1B to 3B (ablation)WikiCLIP · InfoSeek (val)Unseen accuracy: 58.5 -> 60.3Improved
train with only 700 seen entities instead of full 7,943 (ablation)WikiCLIP · OVEN unseenUnseen accuracy: 58% -> 56%No clear effect
use WikiCLIP-L instead of AutoVER 13BOVEN entity recognition · OVEN Entity (val)Unseen accuracy: 24.5 -> 28.5Improved

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