TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Visual Dialog	VisDial v0.9 val	CorefNMN	MRR	63.6	# 5
Visual Dialog	VisDial v0.9 val	CorefNMN	Mean Rank	4.53	# 10
Visual Dialog	VisDial v0.9 val	CorefNMN	R@1	50.24	# 9
Visual Dialog	VisDial v0.9 val	CorefNMN	R@10	88.51	# 9
Visual Dialog	VisDial v0.9 val	CorefNMN	R@5	79.81	# 10
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	MRR	64.1	# 3
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	Mean Rank	4.45	# 8
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	R@1	50.92	# 7
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	R@10	88.81	# 8
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	R@5	80.18	# 9
Common Sense Reasoning	Visual Dialog v0.9	NMN [kottur2018visual]	1 in 10 R@5	80.1	# 1
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	NDCG (x 100)	54.70	# 37
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	MRR (x 100)	61.50	# 19
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	R@1	47.55	# 19
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	R@5	78.10	# 17
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	R@10	88.80	# 16
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	Mean	4.40	# 23

🦡 Badges

Include the markdown at the top of your GitHub README.md file to showcase the performance of the model.

Badges are live and will be dynamically updated with the latest ranking of this paper.

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/visual-coreference-resolution-in-visual/common-sense-reasoning-on-visual-dialog-v0-9)](https://paperswithcode.com/sota/common-sense-reasoning-on-visual-dialog-v0-9?p=visual-coreference-resolution-in-visual)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/visual-coreference-resolution-in-visual/visual-dialog-on-visdial-v09-val)](https://paperswithcode.com/sota/visual-dialog-on-visdial-v09-val?p=visual-coreference-resolution-in-visual)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/visual-coreference-resolution-in-visual/visual-dialog-on-visual-dialog-v1-0-test-std)](https://paperswithcode.com/sota/visual-dialog-on-visual-dialog-v1-0-test-std?p=visual-coreference-resolution-in-visual)`

Visual Coreference Resolution in Visual Dialog using Neural Module Networks

ECCV 2018 • Satwik Kottur • José M. F. Moura • Devi Parikh • Dhruv Batra • Marcus Rohrbach

Visual dialog entails answering a series of questions grounded in an image, using dialog history as context. In addition to the challenges found in visual question answering (VQA), which can be seen as one-round dialog, visual dialog encompasses several more... (read more)

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Code

Add Remove Mark official

facebookresearch/corefnmn

Tasks

Add Remove

COMMON SENSE REASONING

COREFERENCE RESOLUTION

VISUAL DIALOG

VISUAL QUESTION ANSWERING

Datasets

COCO

CLEVR

Visual Question Answering

GuessWhat?!

VisDial

Results from the Paper

Edit

Ranked #1 on Common Sense Reasoning on Visual Dialog v0.9

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Visual Dialog	VisDial v0.9 val	CorefNMN	MRR	63.6	# 5	Compare
			Mean Rank	4.53	# 10	Compare
			R@1	50.24	# 9	Compare
			R@10	88.51	# 9	Compare
			R@5	79.81	# 10	Compare
Visual Dialog	VisDial v0.9 val	CorefNMN (ResNet-152)	MRR	64.1	# 3	Compare
			Mean Rank	4.45	# 8	Compare
			R@1	50.92	# 7	Compare
			R@10	88.81	# 8	Compare
			R@5	80.18	# 9	Compare
Common Sense Reasoning	Visual Dialog v0.9	NMN [kottur2018visual]	1 in 10 R@5	80.1	# 1	Compare
Visual Dialog	Visual Dialog v1.0 test-std	CorefNMN (ResNet-152)	NDCG (x 100)	54.70	# 37	Compare
			MRR (x 100)	61.50	# 19	Compare
			R@1	47.55	# 19	Compare
			R@5	78.10	# 17	Compare
			R@10	88.80	# 16	Compare
			Mean	4.40	# 23	Compare

Methods used in the Paper

Add Remove

METHOD	TYPE
Memory Network	Working Memory Models

Visual Coreference Resolution in Visual Dialog using Neural Module Networks

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods used in the Paper Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods used in the Paper

Add Remove