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 651–675 of 2167 papers

TitleStatusHype
CLIPPO: Image-and-Language Understanding from Pixels Only—0
DePlot: One-shot visual language reasoning by plot-to-table translation—0
What BERT Sees: Cross-Modal Transfer for Visual Question Generation—0
RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training—0
An Empirical Evaluation of Visual Question Answering for Novel Objects—0
Generating Question Relevant Captions to Aid Visual Question Answering—0
Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation Network—0
Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study—0
Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains—0
An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients—0
ICDAR 2019 Competition on Scene Text Visual Question Answering—0
Deep learning evaluation using deep linguistic processing—0
Deep Exemplar Networks for VQA and VQG—0
Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat—0
Deep Equilibrium Multimodal Fusion—0
Deep Bayesian Active Learning for Multiple Correct Outputs—0
Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets—0
Deep Attention Neural Tensor Network for Visual Question Answering—0
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering—0
Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering—0
@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology—0
``A Distorted Skull Lies in the Bottom Center...'' Identifying Paintings from Text Descriptions—0
ICDAR 2021 Competition on Document VisualQuestion Answering—0
Improved Bilinear Pooling with CNNs—0
Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks—0
Show:102550
← PrevPage 27 of 87Next →
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