Flickr30k

Edit

Introduced by Young et al. in From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions

The Flickr30k dataset contains 31,000 images collected from Flickr, together with 5 reference sentences provided by human annotators.

Source: Guiding Long-Short Term Memory for Image Caption Generation

Homepage

Benchmarks

Add a new result Link an existing benchmark

TREND	TASK	DATASET VARIANT	BEST MODEL	PAPER	CODE
	Image Retrieval	Flickr30K 1K test	SGRAF
	Cross-Modal Retrieval	Flickr30k	ALIGN
	Node Classification	Flickr	DEMO-Net
	Phrase Grounding	Flickr30k	COCO_ELMo_PNASNet
	Image Captioning	Flickr30k Captions test	Unified VLP
	Text-Image Retrieval	Flickr30k	VisualSparta

Show all 6 benchmarks

Collapse benchmarks

Samples

Source: Dual-Path Convolutional Image-Text Embedding with Instance Loss .

Usage

License

Custom (research-only, non-commercial)

Modalities

Images
Texts

Languages

English

Tasks

Phrase Grounding

Text-Image Retrieval

Cross-Modal Retrieval

Video Description

Similar Datasets

Multi30k

COCO Captions

Conceptual Captions

COCO

Flickr30K Entities