AI Paper Atlas

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

Integration of Global and Local Representations for Fine-grained Cross-modal Alignment

Seungwan Jin, Hoyoung Choi, Taehyung Noh, Kyungsik Han

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 2 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 modality-agnostic adapter (MAA) integrating local patch embeddings (ablation)FashionSAP-style baseline · FashionGen full evaluationSumR: 451.82 -> 454.37Improved
add HNM-F (hard negative mining with focal loss) (ablation)Baseline + MAA · FashionIQSumR: 308.28 -> 318.92Improved
add C-CmA (comprehensive cross-modal alignment) (ablation)Baseline + MAA + HNM-F · FashionIQSumR: 318.92 -> 323.06Improved
add C-CmA (ablation)Baseline + MAA + HNM-F · FashionGen full evaluationSumR: 456.67 -> 458.11Improved
add MAA, HNM-F and C-CmA to Fashion-FINE vs FashionSAPFashionSAP · FashionGen full evaluation ITR R@1R@1: 54.43 -> 54.29No clear effect
add Fashion-FINE modules to BLIP at fine-tuning only (ablation)BLIP · FashionGen full evaluationSumR: 451.70 -> 479.87Improved
add MAA only to BLIP (ablation)BLIP · FashionGen ITR R@1R@1: 55.27 -> 54.60 (ITR R@1); TIR R@1 61.63 -> 65.05Mixed
weight global vs local representation with lambda 0.95 (ablation)MAA integration · FashionGenretrieval performanceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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