AI Paper Atlas

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

Object-Oriented Anchoring and Modal Alignment in Multimodal Learning

Shibin Mei, Bingbing Ni, Hang Wang, Chenglong Zhao, fengfa hu, Zhiming Pi, BiLian Ke

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 0 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 region object anchors (ablation)Base Model · COCO zero-shot text retrievalR@1: 68.92 -> 70.80Improved
add region object anchors (ablation)Base Model · SNLI-VE valaccuracy: 77.03 -> 79.29Improved
add optimal transport alignment (ablation)Base + region object · NLVR2 devaccuracy: 77.98 -> 79.08Improved
add multiview text mining (ablation)Base + region + OT · NLVR2 devaccuracy: 79.08 -> 80.15Improved
add single-modal DINO supervision (ablation)Base + region + OT + multiview · COCO zero-shot text retrievalR@1: 71.59 -> 71.74Improved
add all four components to base model (ablation)ALBEF-style Base Model · VQA test-devaccuracy: 72.78 -> 75.16Improved
scale pre-training from 4M to 13M imagesOurs · COCO text retrievalR@1: 76.3 -> 80.3Improved
use 13M data versus BLIP 14MOurs(13M) · COCO text retrievalR@1: 80.3 vs 80.6Mixed

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