SOTAVerified

Generative Visual Question Answering

Generating answers in free form to questions posed about images.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–9 of 9 papers

TitleStatusHype
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsCode4
Flamingo: a Visual Language Model for Few-Shot LearningCode4
WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question AnsweringCode2
Multimodal Prompt Retrieval for Generative Visual Question AnsweringCode1
PMC-VQA: Visual Instruction Tuning for Medical Visual Question AnsweringCode1
Towards Flexible Evaluation for Generative Visual Question AnsweringCode0
VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic ReconstructionCode0
Can Generative AI Support Patients' & Caregivers' Informational Needs? Towards Task-Centric Evaluation Of AI Systems—0
Generative Visual Question Answering—0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MedVInTBLEU-123.2—Unverified
2BLIP-2BLEU-17.6—Unverified
3Open-FlamingoBLEU-14.1—Unverified