List your company

Image-Text Retrieval on Unity

55.21Recall@1DetailCLIP-ViT-L/14
21.82630.49339.1647.827Aug 31, 2022

Evaluation results

MethodLinks
DetailCLIP-ViT-L/14Single Feature=Yes, Input=CC@102022.0855.21
CLIP-ViT-L/14Single Feature=No, Input=CC@102022.0852.4
InternVL-C (MLLM)Single Feature=Yes, Input=Full Image2022.0838.93
CLIP-ViT-L/14Single Feature=Yes, Input=Full Image2022.0835.74
BLIP2 (CLIP-like)Single Feature=Yes, Input=Full Image2022.0832.34
GLIP (detector/grounding-based)Single Feature=Yes, Input=Full Image2022.0828.31
MDETR (detector/grounding-based)Single Feature=Yes, Input=Full Image2022.0825.75
DetailCLIP-ViT-B/16Single Feature=Yes, Input=CC@102022.0825.02
CLIP-ViT-B/16Single Feature=Yes, Input=Full Image2022.0824.63
SLIP (CLIP-like)Single Feature=Yes, Input=Full Image2022.0824.42
RegionCLIP (detector-based)Single Feature=Yes, Input=Full Image2022.0824.1
CLIP-ViT-B/16Single Feature=No, Input=CC@102022.0823.11