Xmodal-Ctx + OSCAR

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Image CaptioningonCOCO Captions
BLEU-4· 2022-05-09
41.3
best: 46.5 (mPLUG)
Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning arXiv:2205.04363
Image CaptioningonCOCO Captions
CIDER· 2022-05-09
142.2
best: 155.1 (mPLUG)
Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning arXiv:2205.04363
Image CaptioningonCOCO Captions
SPICE· 2022-05-09
24.9
best: 27 (VAST)
Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning arXiv:2205.04363