AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Global and Local Semantic Completion Learning for Vision-Language Pre-Training

Rong-Cheng Tu, Yatai Ji, Jie Jiang, Weijie Kong, Chengfei Cai, Wenzhe Zhao, Hongfa Wang, Yujiu Yang, Wei Liu

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 15 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 MGSC pre-training task (ablation)MLM+VTM+CL baseline · Flickr30K zero-shot TR@1recall: 80.0 -> 86.2Improved
add MLM (ablation)VTM+CL+MGSC · VQA2.0 test-devaccuracy: 75.46 -> 77.59Improved
add VTM (ablation)MLM+CL+MGSC · VQA2.0 test-devaccuracy: 76.96 -> 77.59Improved
add CL (ablation)MLM+VTM+MGSC · VQA2.0 test-devaccuracy: 77.66 -> 77.59No clear effect
add MVSC (vision half of MGSC) (ablation)MLM+VTM+CL · Flickr30K zero-shot TR@1recall: 80.0 -> 85.5Improved
add MLSC (language half of MGSC) (ablation)MLM+VTM+CL · Flickr30K zero-shot TR@1recall: 80.0 -> 80.5Improved
add MLTC with image mask ratio 0.3 (ablation)MGSC model · Flickr30K zero-shot IR@1recall: 70.4 -> 71.5Improved
add MLTC without MLM (ablation)VTM+CL+MGSC · Flickr30K zero-shot IR@1recall: 66.9 -> 67.9Improved
add MLTC without MGSC (ablation)VTM+CL+MLM · Flickr30K zero-shot IR@1recall: 66.4 -> 68.3Improved
replace InfoNCE with L2 loss in MGSC (ablation)GLSCL · Flickr30K zero-shot IR@1recall: 71.5 -> 70.1Hurt
replace InfoNCE with L2 loss in MLTC (ablation)GLSCL · Flickr30K zero-shot IR@1recall: 71.5 -> 69.6Hurt
raise image mask ratio from 0.8 to 0.9 (ablation)MGSC · Flickr30K zero-shot IR@1recall: 70.4 -> 68.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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