AI Paper Atlas

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

Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding

Haojun Jiang, Yuanze Lin, Dongchen Han, Shiji Song, Gao Huang

CVPR 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 66 citations (OpenAlex)

Check 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
Generate pseudo region-query supervision using nouns, attributes, and spatial relationships without task annotationsPseudo-Q visual grounding · RefCOCO valtop-1 accuracy (%): 56.02 vs. 39.21Improved
Generate pseudo region-query supervision without task annotationsPseudo-Q visual grounding · RefCOCO+ testBtop-1 accuracy (%): 32.13 vs. 38.08Hurt
Generate pseudo region-query supervision without task annotationsPseudo-Q visual grounding · ReferItGametop-1 accuracy (%): 43.32 vs. 38.39Improved
Replace 12.01%, 20.68%, or 30.75% of manually labeled spatial-query examples with pseudo-samplesFully supervised Pseudo-Q on RefCOCO · RefCOCOtop-1 accuracy: 12.01%, 20.68%, and 30.75%No clear effect
Add attributes to nouns (ablation)Pseudo-Q · RefCOCOtop-1 accuracy: 22.04 -> 31.30Improved
Add attributes to nouns (ablation)Pseudo-Q · ReferItGametop-1 accuracy: 27.91 -> 31.33Improved
Add spatial relationships to nouns (ablation)Pseudo-Q · RefCOCOtop-1 accuracy: 22.04 -> 48.71; 26.67%Improved
Add spatial relationships to nouns (ablation)Pseudo-Q · ReferItGametop-1 accuracy: 27.91 -> 39.26Improved
Add attributes and relationships to nouns (ablation)Pseudo-Q · RefCOCOtop-1 accuracy: 22.04 -> 53.39Improved
Add attributes and relationships to nouns (ablation)Pseudo-Q · ReferItGametop-1 accuracy: 27.91 -> 40.37Improved
Add multi-level cross-modality attention (ablation)Pseudo-Q with generated queries · RefCOCOtop-1 accuracy: +1.77%Improved
Add multi-level cross-modality attention (ablation)Pseudo-Q with generated queries · ReferItGametop-1 accuracy: +1.35%Improved

Later papers that compared with this method

4 later accepted papers report Pseudo-Q as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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