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 1501–1550 of 2167 papers

TitleStatusHype
UFO: A UniFied TransfOrmer for Vision-Language Representation Learning—0
Medical Visual Question Answering: A Survey—0
Blind VQA on 360° Video via Progressively Learning from Pixels, Frames and VideoCode0
Achieving Human Parity on Visual Question Answering—0
Co-VQA : Answering by Interactive Sub Question Sequence—0
Language bias in Visual Question Answering: A Survey and Taxonomy—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base—0
ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named EntitiesCode0
Question-Led Semantic Structure Enhanced Attentions for VQA—0
Breaking Down Questions for Outside-Knowledge Visual Question Answering—0
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models—0
Document AI: Benchmarks, Models and Applications—0
No-Reference Video Quality Assessment Based on Benford’s Law and Perceptual FeaturesCode0
Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture—0
ICDAR 2021 Competition on Document VisualQuestion Answering—0
Visual Question Answering based on Formal Logic—0
CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization—0
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation—0
MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question AnsweringCode0
Perceptual Score: What Data Modalities Does Your Model Perceive?Code0
Subtleties in the trainability of quantum machine learning models—0
Alignment Attention by Matching Key and Query DistributionsCode0
Robustness through Data Augmentation Loss ConsistencyCode0
Single-Modal Entropy based Active Learning for Visual Question Answering—0
Evaluating and Improving Interactions with Hazy Oracles—0
Towards Language-guided Visual Recognition via Dynamic ConvolutionsCode0
Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation—0
xGQA: Cross-Lingual Visual Question Answering—0
Guiding Visual Question Generation—0
Semantically Distributed Robust Optimization for Vision-and-Language InferenceCode0
Improving Users' Mental Model with Attention-directed Counterfactual Edits—0
MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants—0
Beyond Accuracy: A Consolidated Tool for Visual Question Answering BenchmarkingCode0
Asking questions on handwritten document collections—0
Breaking Down Questions for Outside-Knowledge VQA—0
PRNet: A Progressive Regression Network for No-Reference User-Generated-Content Video Quality Assessment—0
Crossformer: Transformer with Alternated Cross-Layer Guidance—0
How Much Can CLIP Benefit Vision-and-Language Tasks?—0
Variational Disentangled Attention for Regularized Visual Dialog—0
Measuring CLEVRness: Black-box Testing of Visual Reasoning Models—0
VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering—0
High Frame Rate Video Quality Assessment using VMAF and Entropic Differences—0
Multimodal Integration of Human-Like Attention in Visual Question Answering—0
How to find a good image-text embedding for remote sensing visual question answering?—0
Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question AnsweringCode0
Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question AnsweringCode0
Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation—0
TxT: Crossmodal End-to-End Learning with Transformers—0
Improved RAMEN: Towards Domain Generalization for Visual Question AnsweringCode0
Show:102550
← PrevPage 31 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