AI Paper Atlas

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

HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs

Fangyu Liu, Rongtian Ye, Xun Wang, Shuaipeng Li

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 34 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 HAL instead of MaxSCAN · MS-COCOR@1, image→text: 70.9 -> 78.3Improved
Use HAL instead of MaxSCAN · MS-COCOrsum: 500.5 -> 512.7Improved
Use HAL instead of SumGRU+VGG19 · Flickr30krsum: 291.0 -> 320.0Improved
Use HAL instead of MaxGRU+VGG19 · Flickr30krsum: 281.4 -> 320.0Improved
Add global memory-bank weighting to HAL (ablation)GRU+VGG19 · MS-COCO c2 (5k)rsum: 436.1 -> 439.5Improved
Add global memory-bank weighting to HAL (ablation)GRU+IRv2 · MS-COCO c2 (5k)rsum: 453.2 -> 458.5Improved
Add global memory-bank weighting to HAL (ablation)GRU+ResNet152 · MS-COCO c2 (5k)rsum: 462.0 -> 466.7Improved
Add global memory-bank weighting to HAL (ablation)GRU+ResNet152 · MS-COCO c1 (1k)rsum: 469.2 -> 476.6Improved
Increase batch size to expand the local neighborhood (ablation)HAL · MS-COCOrsumImproved
Use a memory bank sized at 5% of training data (ablation)HAL + memory bank · MS-COCOrsumImproved

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