SOTAVerified

Visual Dialog

Visual Dialog requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the task is to answer the question.

Papers

Showing 76100 of 118 papers

TitleStatusHype
What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog0
What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions0
How to Fool Systems and Humans in Visually Grounded Interaction: A Case Study on Adversarial Attacks on Visual Dialog0
ICCV23 Visual-Dialog Emotion Explanation Challenge: SEU_309 Team Technical Report0
Image-Question-Answer Synergistic Network for Visual Dialog0
Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning0
Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation0
LAVIS: A Library for Language-Vision Intelligence0
Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts0
Learning to Ground Visual Objects for Visual Dialog0
Factor Graph AttentionCode0
Reasoning Visual Dialogs with Structural and Partial ObservationsCode0
Visual Dialogue without Vision or DialogueCode0
Recursive Visual Attention in Visual DialogCode0
Collecting Visually-Grounded Dialogue with A Game Of SortsCode0
Examining Cooperation in Visual Dialog ModelsCode0
CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual DialogCode0
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented GuesserCode0
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsCode0
SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation SpaceCode0
Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic RepresentationCode0
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual DialogueCode0
SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation SpaceCode0
Learning Goal-Oriented Visual Dialog via Tempered Policy GradientCode0
Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable SceneCode0
Show:102550
← PrevPage 4 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SingleNDCG (x 100)78.7Unverified
2P1P2+Distill+EnsembleNDCG (x 100)77.92Unverified
3Ensemble + Fine-tuningNDCG (x 100)76.43Unverified
4ensemble, finetuneNDCG (x 100)76.17Unverified
5VD-PCRNDCG (x 100)76.14Unverified
6EnsembleNDCG (x 100)75.35Unverified
7Ensemble + FinetuneNDCG (x 100)74.88Unverified
8bert-double-stream-finetuningNDCG (x 100)74.62Unverified
9CE-finetuned, single modelNDCG (x 100)74.47Unverified
102NDCG (x 100)73.36Unverified
#ModelMetricClaimedVerifiedStatus
19xFGA (VGG)MRR68.92Unverified
2DANMRR66.38Unverified
3CorefNMN (ResNet-152)MRR64.1Unverified
4CoAttMRR63.98Unverified
5CorefNMNMRR63.6Unverified
6DualVDMRR62.94Unverified
7SF-QIH-se-2MRR62.42Unverified
8HCIAE-NP-ATTMRR62.22Unverified
9HieCoAtt-QIMRR57.88Unverified
10AMEMR@148.53Unverified
#ModelMetricClaimedVerifiedStatus
15xFGA + LSNDCG64.04Unverified
25xFGA + LS*+MRR0.71Unverified
3Two-StepMRR0.7Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Modal BlenderBotBLEU-41Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Modal BlenderBotBLEU-41.1Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Modal BlenderBotBLEU-41.5Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Modal BlenderBotBLEU-440Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-Modal BlenderBotBLEU-42.2Unverified