NUS-WIDE

Dataset Information
Modalities
Images
Introduced
2009
License
Unknown
Homepage
Official Website
Contents

Overview

The NUS-WIDE dataset contains 269,648 images with a total of 5,018 tags collected from Flickr. These images are manually annotated with 81 concepts, including objects and scenes.

Source: Parallel Grid Pooling for Data Augmentation

Image Source: Li et al

Variants: NUS-WIDE

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Multi-Label Classification MLD-TResNet-L-AAM[448x448] Combining Metric Learning and Attention … 2022-09-14
Multi-Label Classification Q2L-CvT(resolution 384, ImageNet-21K pretrained) Query2Label: A Simple Transformer Way … 2021-07-22
Multi-Label Classification Q2L-TResL(resoluition 448) Query2Label: A Simple Transformer Way … 2021-07-22
Multi-Label Classification Q2L-R101(resolution 448) Query2Label: A Simple Transformer Way … 2021-07-22
Multi-Label Classification MSRN Multi-layered Semantic Representation Network for … 2021-06-22
Multi-Label Classification TResNet-L (resolution 448) Asymmetric Loss For Multi-Label Classification 2020-09-29
Multi-Label Classification MS-CMA Cross-Modality Attention with Semantic Graph … 2019-12-17
Image Retrieval DTQ Deep Triplet Quantization 2019-02-01
Multi-Label Classification S-CLs Multi-Label Image Classification via Knowledge … 2018-09-16
Multi-Label Classification SRN Learning Spatial Regularization with Image-level … 2017-02-20

Research Papers

Recent papers with results on this dataset:

External Links: