PromptCap

Reported on 5 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing5 results

Visual Question Answering (VQA)onA-OKVQA
DA VQA Score· 2022-11-15
59.6
best: 70.55 (SMoLA-PaLI-X Specialist Model)
SOTA
PromptCap: Prompt-Guided Task-Aware Image Captioning arXiv:2211.09699
Visual Question Answering (VQA)onA-OKVQA
MC Accuracy· 2022-11-15
73.2
best: 83.75 (SMoLA-PaLI-X Specialist Model)
SOTA
PromptCap: Prompt-Guided Task-Aware Image Captioning arXiv:2211.09699
Visual Question AnsweringonTextVQA test-standard
overall· 2022-11-15
51.8
SOTA
PromptCap: Prompt-Guided Task-Aware Image Captioning arXiv:2211.09699
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2022-11-15
60.4
best: 66.8 (PaLI-X-VPD)
PromptCap: Prompt-Guided Task-Aware Image Captioning arXiv:2211.09699
Visual Question Answering (VQA)onTextVQA test-standard
overall· 2022-11-15
51.8
best: 73.1 (PaLI)
PromptCap: Prompt-Guided Task-Aware Image Captioning arXiv:2211.09699