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 701–750 of 2167 papers

TitleStatusHype
HAAR: Text-Conditioned Generative Model of 3D Strand-based Human HairstylesCode1
An Evaluation of GPT-4V and Gemini in Online VQA—0
M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge BaseCode0
Advancing Surgical VQA with Scene Graph Knowledge—0
RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment—0
CogAgent: A Visual Language Model for GUI AgentsCode5
BESTMVQA: A Benchmark Evaluation System for Medical Visual Question Answering—0
ViLA: Efficient Video-Language Alignment for Video Question AnsweringCode1
Genixer: Empowering Multimodal Large Language Models as a Powerful Data GeneratorCode1
NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup AnnotationsCode1
Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models—0
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects—0
Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology VideosCode1
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks—0
Language-Informed Visual Concept LearningCode1
Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models—0
Recursive Visual ProgrammingCode1
MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation—0
Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario—0
How to Configure Good In-Context Sequence for Visual Question AnsweringCode1
Zero-Shot Video Question Answering with Procedural Programs—0
Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts—0
Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering—0
Debiasing Multimodal Models via Causal Information MinimizationCode1
The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation—0
Fully Authentic Visual Question Answering Dataset from Online CommunitiesCode0
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMsCode1
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency TrainingCode1
From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation—0
KNVQA: A Benchmark for evaluation knowledge-based VQA—0
Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask QuestionsCode0
Understanding and Mitigating Classification Errors Through Interpretable Token Patterns—0
HIDRO-VQA: High Dynamic Range Oracle for Video Quality AssessmentCode1
Video-LLaVA: Learning United Visual Representation by Alignment Before ProjectionCode4
Multiple-Question Multiple-Answer Text-VQA—0
Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question PromptsCode0
Attribute Diversity Determines the Systematicity Gap in VQACode0
Asking More Informative Questions for Grounded Retrieval—0
A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question AnsweringCode1
CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings—0
What Large Language Models Bring to Text-rich VQA?—0
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language ModelsCode4
InfMLLM: A Unified Framework for Visual-Language TasksCode1
Visual Commonsense based Heterogeneous Graph Contrastive Learning—0
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal ModelsCode3
Analyzing Modular Approaches for Visual Question DecompositionCode0
Improving Vision-and-Language Reasoning via Spatial Relations Modeling—0
Zero-shot Translation of Attention Patterns in VQA Models to Natural LanguageCode0
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality CollaborationCode4
CogVLM: Visual Expert for Pretrained Language ModelsCode5
Show:102550
← PrevPage 15 of 44Next →
All datasetsGQA Test2019VQA v2 test-devVQA v2 test-stdOK-VQAMSVD-QADocVQA testMSRVTT-QAInfographicVQAGQA test-devVizWiz 2020 VQAA-OKVQACLEVR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1humanAccuracy89.3—Unverified
2DREAM+Unicoder-VL (MSRA)Accuracy76.04—Unverified
3TRRNet (Ensemble)Accuracy74.03—Unverified
4MIL-nbgaoAccuracy73.81—Unverified
5Kakao BrainAccuracy73.33—Unverified
6Coarse-to-Fine Reasoning, Single ModelAccuracy72.14—Unverified
7270Accuracy70.23—Unverified
8NSM ensemble (updated)Accuracy67.55—Unverified
9VinVL-DPTAccuracy64.92—Unverified
10VinVL+LAccuracy64.85—Unverified
#ModelMetricClaimedVerifiedStatus
1PaLIAccuracy84.3—Unverified
2BEiT-3Accuracy84.19—Unverified
3VLMoAccuracy82.78—Unverified
4ONE-PEACEAccuracy82.6—Unverified
5mPLUG (Huge)Accuracy82.43—Unverified
6CuMo-7BAccuracy82.2—Unverified
7X2-VLM (large)Accuracy81.9—Unverified
8MMUAccuracy81.26—Unverified
9LyricsAccuracy81.2—Unverified
10InternVL-CAccuracy81.2—Unverified
#ModelMetricClaimedVerifiedStatus
1BEiT-3overall84.03—Unverified
2mPLUG-Hugeoverall83.62—Unverified
3ONE-PEACEoverall82.52—Unverified
4X2-VLM (large)overall81.8—Unverified
5VLMooverall81.3—Unverified
6SimVLMoverall80.34—Unverified
7X2-VLM (base)overall80.2—Unverified
8VASToverall80.19—Unverified
9VALORoverall78.62—Unverified
10Prompt Tuningoverall78.53—Unverified