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 1–50 of 2167 papers

TitleStatusHype
Qwen2.5-VL Technical ReportCode11
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any ResolutionCode11
SWIFT:A Scalable lightWeight Infrastructure for Fine-TuningCode11
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction DataCode7
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language ModelsCode7
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsCode7
Improved Baselines with Visual Instruction TuningCode6
GPT-4 Technical ReportCode6
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language TasksCode5
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsCode5
Ovis: Structural Embedding Alignment for Multimodal Large Language ModelCode5
TextMonkey: An OCR-Free Large Multimodal Model for Understanding DocumentCode5
CogAgent: A Visual Language Model for GUI AgentsCode5
CogVLM: Visual Expert for Pretrained Language ModelsCode5
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondCode5
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction ModelCode5
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init AttentionCode5
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationCode5
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenCode4
Multi-label Cluster Discrimination for Visual Representation LearningCode4
Tarsier: Recipes for Training and Evaluating Large Video Description ModelsCode4
Long Context Transfer from Language to VisionCode4
Exploring the Capabilities of Large Multimodal Models on Dense TextCode4
OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual ReasoningCode4
OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMCode4
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional TokenizationCode4
Video-LLaVA: Learning United Visual Representation by Alignment Before ProjectionCode4
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language ModelsCode4
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality CollaborationCode4
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language ModelsCode4
Otter: A Multi-Modal Model with In-Context Instruction TuningCode4
mPLUG-Owl: Modularization Empowers Large Language Models with MultimodalityCode4
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and VideoCode4
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsCode4
InternVideo: General Video Foundation Models via Generative and Discriminative LearningCode4
GLIPv2: Unifying Localization and Vision-Language UnderstandingCode4
Flamingo: a Visual Language Model for Few-Shot LearningCode4
MMSearch-R1: Incentivizing LMMs to SearchCode3
An Empirical Study on Prompt Compression for Large Language ModelsCode3
Lyra: An Efficient and Speech-Centric Framework for Omni-CognitionCode3
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning AgentCode3
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language ModelsCode3
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for MedicineCode3
HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at ScaleCode3
AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language ModelsCode3
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-MakingCode3
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video UnderstandingCode3
Evaluating Text-to-Visual Generation with Image-to-Text GenerationCode3
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought ReasoningCode3
Show:102550
← PrevPage 1 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
9InternVL-CAccuracy81.2—Unverified
10LyricsAccuracy81.2—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