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 1401–1450 of 2167 papers

TitleStatusHype
Visual Superordinate Abstraction for Robust Concept Learning—0
V-Doc : Visual questions answers with Documents—0
Avoiding Barren Plateaus with Classical Deep Neural Networks—0
Guiding Visual Question Answering with Attention Priors—0
Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization—0
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization—0
VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering—0
Making Video Quality Assessment Models Sensitive to Frame Rate Distortions—0
Gender and Racial Bias in Visual Question Answering Datasets—0
A Neuro-Symbolic ASP Pipeline for Visual Question AnsweringCode0
A Framework to Map VMAF with the Probability of Just Noticeable Difference between Video Encoding Recipes—0
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures—0
Joint learning of object graph and relation graph for visual question answering—0
Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study—0
From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data—0
QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual ReasoningCode0
LAWS: Look Around and Warm-Start Natural Gradient Descent for Quantum Neural NetworksCode0
What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task LearningCode0
Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering—0
ViLMedic: a framework for research at the intersection of vision and language in medical AI—0
Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks—0
DuReader_vis: A Chinese Dataset for Open-domain Document Visual Question Answering—0
Vision-Language Pretraining: Current Trends and the Future—0
Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks—0
LayoutLMv3: Pre-training for Document AI with Unified Text and Image MaskingCode0
Attention Mechanism based Cognition-level Scene Understanding—0
Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning—0
Question-Driven Graph Fusion Network For Visual Question Answering—0
Co-VQA : Answering by Interactive Sub Question Sequence—0
Perceptual Quality Assessment of UGC Gaming Videos—0
SimVQA: Exploring Simulated Environments for Visual Question Answering—0
VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language TransformersCode0
Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment—0
Single-Stream Multi-Level Alignment for Vision-Language PretrainingCode0
Subjective and Objective Analysis of Streamed Gaming Videos—0
Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question AnsweringCode0
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering—0
WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models—0
Can you even tell left from right? Presenting a new challenge for VQA—0
CARETS: A Consistency And Robustness Evaluative Test Suite for VQACode0
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Barlow constrained optimization for Visual Question AnsweringCode0
Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question AnsweringCode0
Modeling Coreference Relations in Visual Dialog—0
Recent, rapid advancement in visual question answering architecture: a review—0
Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment—0
Joint Answering and Explanation for Visual Commonsense ReasoningCode0
On Modality Bias Recognition and ReductionCode0
Measuring CLEVRness: Blackbox testing of Visual Reasoning Models—0
Show:102550
← PrevPage 29 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