AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Improving Zero-Shot Phrase Grounding via Reasoning on External Knowledge and Spatial Relations

Zhan Shi, Yilin Shen, Hongxia Jin, Xiaodan Zhu

AAAI 2022 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot reasoning · 9 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 multimodal knowledge graph reasoning and spatial relation reasoningZSG on Flickr-0 · Flickr-0accuracy: 43.02 -> 45.99Improved
Add multimodal knowledge graph reasoning and spatial relation reasoningZSG on Flickr-1 · Flickr-1accuracy: 31.23 -> 33.12Improved
Add multimodal knowledge graph reasoning and spatial relation reasoningZSG on VG-2B, VG-2UB, VG-3B, and VG-3UB · Visual Genome zero-shot splitsaccuracy: 12.90 -> 15.12; 12.37 -> 14.49; 13.77 -> 15.93; 12.82 -> 15.28Improved
Add multimodal knowledge graph reasoning and spatial relation reasoningZSG on Flickr30K with VGG16 · Flickr30Kaccuracy: 60.12 -> 62.56Improved
Add multimodal knowledge graph reasoning and spatial relation reasoningZSG on Flickr30K with ResNet50 · Flickr30Kaccuracy: 63.39 -> 65.02Improved
Add commonsense knowledge graph reasoning (ablation)Base on Flickr-0 · Flickr-0accuracy: 43.02 -> 44.10Improved
Add scene graph knowledge only (ablation)Base on Flickr-0 · Flickr-0accuracy: 43.02 -> 43.18Improved
Add commonsense and scene graph knowledge without spatial relation reasoning (ablation)Base on Flickr-0 · Flickr-0accuracy: 43.02 -> 44.41Improved
Add spatial relation reasoning only (ablation)Base on Flickr-0 · Flickr-0accuracy: 43.02 -> 43.48Improved
Add spatial relation reasoning to commonsense graph reasoning (ablation)Base + Gcms on Flickr-0 · Flickr-0accuracy: 44.10 -> 45.72Improved
Add scene graph knowledge to commonsense knowledge (ablation)Base + Gcms on Flickr-0 · Flickr-0accuracy: 44.10 -> 44.41Improved
Add spatial relation reasoning to multimodal knowledge graph reasoning (ablation)Base + G on Flickr-1 · Flickr-1accuracy: 32.42 -> 33.12Improved

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