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 151–200 of 2167 papers

TitleStatusHype
DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models—0
Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open SpaceCode1
KVQ: Boosting Video Quality Assessment via Saliency-guided Local PerceptionCode1
DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario UnderstandingCode2
Astrea: A MOE-based Visual Understanding Model with Progressive Alignment—0
SurgicalVLM-Agent: Towards an Interactive AI Co-Pilot for Pituitary Surgery—0
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
ComicsPAP: understanding comic strips by picking the correct panel—0
Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method—0
Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework—0
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token PruningCode2
Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru—0
CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model—0
SplatTalk: 3D VQA with Gaussian Splatting—0
Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language ModelCode2
Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models—0
MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering—0
Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text RepresentationsCode0
A Token-level Text Image Foundation Model for Document Understanding—0
BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQACode0
V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts—0
Enhancing Multi-hop Reasoning in Vision-Language Models via Self-Distillation with Multi-Prompt Ensembling—0
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language ModelsCode0
FunBench: Benchmarking Fundus Reading Skills of MLLMs—0
ABC: Achieving Better Control of Multimodal Embeddings using VLMs—0
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering—0
Fine-Grained Retrieval-Augmented Generation for Visual Question Answering—0
MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language ModelsCode0
Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual RealityCode0
ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models—0
Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation—0
FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA—0
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human PreferenceCode2
Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines—0
Directional Gradient Projection for Robust Fine-Tuning of Foundation Models—0
Hardware-Friendly Static Quantization Method for Video Diffusion Transformers—0
Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence ModelingCode0
Exploring Advanced Techniques for Visual Question Answering: A Comprehensive Comparison—0
Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning—0
PitVQA++: Vector Matrix-Low-Rank Adaptation for Open-Ended Visual Question Answering in Pituitary SurgeryCode0
Qwen2.5-VL Technical ReportCode11
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning—0
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference OptimizationCode2
Multi-Modal Retrieval Augmentation for Open-Ended and Knowledge-Intensive Video Question Answering—0
MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language ModelsCode1
USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot InteractionsCode0
VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models—0
Exploring the Potential of Encoder-free Architectures in 3D LMMsCode0
Abduction of Domain Relationships from Data for VQA—0
Show:102550
← PrevPage 4 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