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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 61–70 of 118 papers

Title	Date	Tasks	Status	Hype
DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog	Dec 18, 2019	AI AgentDecoder	CodeCode Available	0
Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline	Dec 5, 2019	Language ModellingRepresentation Learning	CodeCode Available	1
TAB-VCR: Tags and Attributes based VCR Baselines	Dec 1, 2019	AttributeQuestion Answering	CodeCode Available	0
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs	Nov 26, 2019	AllVisual Dialog	CodeCode Available	0
Two Causal Principles for Improving Visual Dialog	Nov 24, 2019	Visual DialogVocal Bursts Valence Prediction	CodeCode Available	0
An Annotated Corpus of Reference Resolution for Interpreting Common Grounding	Nov 18, 2019	Coreference ResolutionGoal-Oriented Dialog	CodeCode Available	1
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue	Nov 17, 2019	feature selectionQuestion Answering	CodeCode Available	0
Visual Dialogue State Tracking for Question Generation	Nov 12, 2019	Dialogue State TrackingQuestion Generation	CodeCode Available	1
Video Dialog via Progressive Inference and Cross-Transformer	Nov 1, 2019	Answer GenerationQuestion Answering	—Unverified	0
TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines	Oct 31, 2019	AttributeQuestion Answering	CodeCode Available	0

Show:10 25 50

← PrevPage 7 of 12Next →

All datasets Visual Dialog v1.0 test-std VisDial v0.9 val VisDial v1.0 test-std BlendedSkillTalk ConvAI2 EmpatheticDialogues Image-Chat Wizard of Wikipedia

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Single	NDCG (x 100)	78.7	—	Unverified
2	P1P2+Distill+Ensemble	NDCG (x 100)	77.92	—	Unverified
3	Ensemble + Fine-tuning	NDCG (x 100)	76.43	—	Unverified
4	ensemble, finetune	NDCG (x 100)	76.17	—	Unverified
5	VD-PCR	NDCG (x 100)	76.14	—	Unverified
6	Ensemble	NDCG (x 100)	75.35	—	Unverified
7	Ensemble + Finetune	NDCG (x 100)	74.88	—	Unverified
8	bert-double-stream-finetuning	NDCG (x 100)	74.62	—	Unverified
9	CE-finetuned, single model	NDCG (x 100)	74.47	—	Unverified
10	2	NDCG (x 100)	73.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	9xFGA (VGG)	MRR	68.92	—	Unverified
2	DAN	MRR	66.38	—	Unverified
3	CorefNMN (ResNet-152)	MRR	64.1	—	Unverified
4	CoAtt	MRR	63.98	—	Unverified
5	CorefNMN	MRR	63.6	—	Unverified
6	DualVD	MRR	62.94	—	Unverified
7	SF-QIH-se-2	MRR	62.42	—	Unverified
8	HCIAE-NP-ATT	MRR	62.22	—	Unverified
9	HieCoAtt-QI	MRR	57.88	—	Unverified
10	AMEM	R@1	48.53	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	5xFGA + LS	NDCG	64.04	—	Unverified
2	5xFGA + LS*+	MRR	0.71	—	Unverified
3	Two-Step	MRR	0.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Modal BlenderBot	BLEU-4	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Modal BlenderBot	BLEU-4	1.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Modal BlenderBot	BLEU-4	1.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Modal BlenderBot	BLEU-4	40	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Multi-Modal BlenderBot	BLEU-4	2.2	—	Unverified