HyperAIHyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAIHyperAI

Image Text Matching On Commercialadsdataset

المقاييس

ADD(S) AUC

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
ADD(S) AUC
Paper TitleRepository
OSCAR87.45Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks-
Unicoder-VL83.16Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training-
VinVL88.56VinVL: Revisiting Visual Representations in Vision-Language Models-
BLIP83.51BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation-
AlignCMSS91.73Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search-
ALBEF82.74Align before Fuse: Vision and Language Representation Learning with Momentum Distillation-
VL-BERT86.27VL-BERT: Pre-training of Generic Visual-Linguistic Representations-
AdsCVLR87.90AdsCVLR: Commercial Visual-Linguistic Representation Modeling in Sponsored Search-
0 of 8 row(s) selected.