SOTAVerified

Visual Question Answering (VQA)

Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.

Image Source: visualqa.org

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 2167 papers

TitleStatusHype
VisionThink: Smart and Efficient Vision Language Model via Reinforcement LearningCode0
MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM—0
Describe Anything Model for Visual Question Answering on Text-rich ImagesCode1
Evaluating Attribute Confusion in Fashion Text-to-Image Generation—0
LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation—0
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and GrounderCode1
SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning—0
Bridging Video Quality Scoring and Justification via Large Multimodal Models—0
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document ImagesCode0
FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering—0
Show:102550
← PrevPage 1 of 217Next →
All datasetsGQA Test2019VQA v2 test-devVQA v2 test-stdOK-VQAMSVD-QADocVQA testMSRVTT-QAInfographicVQAGQA test-devVizWiz 2020 VQAA-OKVQACLEVR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HumanANLS0.94—Unverified
2MLCD-Embodied-7BANLS0.92—Unverified
3SMoLA-PaLI-X SpecialistANLS0.91—Unverified
4SMoLA-PaLI-X GeneralistANLS0.91—Unverified
5Qwen-VL-PlusANLS0.9—Unverified
6ScreenAI 5B (4.62 B params, w/OCR)ANLS0.9—Unverified
7PaLI-3 (w/ OCR)ANLS0.89—Unverified
8ERNIE-Layout large (ensemble)ANLS0.88—Unverified
9GPT-4ANLS0.88—Unverified
10DocFormerv2-largeANLS0.88—Unverified