HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Cross Modal Retrieval On Recipe1M

评估指标

Image-to-text R@1
Text-to-image R@1

评测结果

各个模型在此基准测试上的表现结果

Paper Title
VLPCook (R1M+)74.975.6Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval
VLPCook73.674.7Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval
T-Food (CLIP)72.372.6Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval
T-Food68.268.3Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval
X-MRS6463.9Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning
H-T60.060.3Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
SCAN54.054.9Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism
ACME51.852.8Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images
AdaMine39.840.2Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings
0 of 9 row(s) selected.
Cross Modal Retrieval On Recipe1M | SOTA | HyperAI超神经