AI Paper Atlas

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

VLPrompt-PSG: Vision-Language Prompting for Panoptic Scene Graph Generation

Zijian Zhou, Holger Caesar, Qijun Chen, Miaojing Shi

IJCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 13 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 language information from LLMs (ablation)VLPrompt · PSG (SGDet)mR@100: 44.2 -> 53.7Improved
add language features for rare relationsVLPrompt · PSG rare relationsmR@100: 37.9 -> 51.7Improved
add language features for common relationsVLPrompt · PSG common relationsmR@100: 54.7 -> 57.0Improved
add chain-of-thought prompts (ablation)VLPrompt · PSG (SGDet)mR@100: 45.7 -> 53.7Improved
take object features from pixel decoder rather than transformer decoder (ablation)VLPrompt · PSG (SGDet)mR@100: 50.3 -> 53.7Improved
use mask pooling rather than bbox pooling (ablation)VLPrompt · PSG (SGDet)mR@100: 52.6 -> 53.7Improved
concatenate object features rather than subtract (ablation)VLPrompt · PSG (SGDet)mR@100: 48.9 -> 53.7Improved
add spatial features (ablation)VLPrompt · PSG (SGDet)mR@100: 52.1 -> 53.7Improved
use separate RP and RJ feature extraction instead of swapping (ablation)VLPrompt · PSG (SGDet)mR@100: 46.4 -> 53.7Improved
use both RP and RJ decoders instead of RP only (ablation)VLPrompt · PSG (SGDet)mR@100: 49.6 -> 53.7Improved
use 2 decoder blocks instead of 1 (ablation)VLPrompt · PSG (SGDet)mR@100: 46.9 -> 53.7Improved
use 12 decoder blocks instead of 2 (ablation)VLPrompt · PSG (SGDet)mR@100: 53.7 -> 29.4Hurt

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