Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CapDec

CapDec

Reported on 9 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Natural Language Processing7 results

Image CaptioningonMSCOCO
BLEU-4· 2022-11-01
26.4
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonFlickrStyle10K
BLEU-1 (Romantic)· 2022-11-01
29.4
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonFlickr30k
CIDEr· 2022-11-01
39.1
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonFlickrStyle10K
CIDEr· 2022-11-01
30
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonCOCO Captions
BLEU-4· 2022-11-01
26.4
best: 46.5 (mPLUG)
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonCOCO Captions
CIDER· 2022-11-01
91.8
best: 155.1 (mPLUG)
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Image CaptioningonCOCO Captions
METEOR· 2022-11-01
25.1
best: 33.9 (CoCa)
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575

Miscellaneous2 results

Semi Supervised Learning for Image CaptioningonFlickr30k
CIDEr· 2022-11-01
39.1
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575
Semi Supervised Learning for Image CaptioningonFlickrStyle10K
CIDEr· 2022-11-01
30
SOTA
Text-Only Training for Image Captioning using Noise-Injected CLIP arXiv:2211.00575