HyperAI超神経

プラットフォーム

Image Retrieval On Flickr30K 1K Test

評価指標

R@1

R@10

R@5

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

				Paper Title
X-VLM (base)	86.9	98.7	97.3	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
RCAR	62.6	91.1	85.8	Plug-and-Play Regulators for Image-Text Matching
SGRAF	58.5	88.8	83.0	Similarity Reasoning and Filtration for Image-Text Matching
VisualSparta	57.4	88.1	82.0	VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words
LGSGM	57.4	90.2	84.1	A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
TERAN MrSw	56.5	88.2	81.2	Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
TERAN Symm.	55.7	89.3	83.1	Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
VSRN	54.7	88.2	81.8	Visual Semantic Reasoning for Image-Text Matching
CAMP	51.5	85.3	77.1	CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
SCAN i-t	44.0	82.6	74.2	Stacked Cross Attention for Image-Text Matching
SCO	41.1	80.1	70.5	Learning Semantic Concepts and Order for Image and Sentence Matching
DAN	39.4	79.1	69.2	Dual Attention Networks for Multimodal Reasoning and Matching
2WayNet (VGG)	36.0	-	-	Linking Image and Text with 2-Way Nets
SM-LSTM (VGG)	30.2	72.3	-	Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
SPE	29.7	72.1	60.1	Learning Deep Structure-Preserving Image-Text Embeddings
mCNN	26.2	69.6	56.3	Multimodal Convolutional Neural Networks for Matching Image and Sentence
HGLMM FV	24.7	66.8	53.4	Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models
DVSA (R-CNN, AlexNet)	15.2	50.5	-	Deep Visual-Semantic Alignments for Generating Image Descriptions

0 of 18 row(s) selected.

Image Retrieval On Flickr30K 1K Test | SOTA | HyperAI超神経