AI Paper Atlas

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

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Hejie Cui, Xinyu Fang, Zihan Zhang, Ran Xu, Xuan Kan, Xin Liu, Yue Yu, Manling Li, Yangqiu Song, Carl Yang

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 1 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
Use relation-oriented region prompting and format-free multimodal generationOpenVik · Open visual knowledge generationBLEU: 0.275 -> 0.280Improved
Use relation-oriented region prompting and format-free multimodal generationOpenVik · Open visual knowledge generationValidity: 0.897 -> 0.907Improved
Use relation-oriented region prompting and format-free multimodal generationOpenVik · Open visual knowledge generationConformity: 0.871 -> 0.883Improved
Use relation-oriented region prompting and format-free multimodal generationOpenVik · Open visual knowledge generationFreshness: 0.795 -> 0.809Improved
Use relation-oriented region prompting and format-free multimodal generationOpenVik · Open visual knowledge generationDiversity: 0.547 -> 0.619Improved
Enrich captions with OpenVik relational contextZero-shot CLIP retrieval · MS-COCO text-to-image retrievalAvg: more than 6.0%Improved
Enrich event descriptions with OpenVik verb-related contextsZero-shot CLIP and BLIP · Grounded Situation RecognitionAccuracyImproved
Add two-level entity and relation context from OpenVikZero-shot VCR baseline · Visual Commonsense ReasoningAccuracy: above 3.0%Improved
Add the inter-sequence information variety regularizer (ablation)OpenVik visual knowledge generator · Generated knowledge qualityDiversityImproved
Add diversity-driven random dropping of low-quality, frequent descriptions (ablation)OpenVik training data · Generated knowledge qualityDiversityImproved
Augment entities and relations with external knowledge resources (ablation)OpenVik training data · Generated knowledge qualityFreshnessImproved
Augment entities and relations with external knowledge resources (ablation)OpenVik training data · Generated knowledge qualityDiversityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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