ImagesVideos

DAVIS 2017

Introduced in The 2017 DAVIS Challenge on Video Object Segmentation2016

About this Dataset

DAVIS17 is a dataset for video object segmentation. It contains a total of 150 videos - 60 for training, 30 for validation, 60 for testing

Source: Siam R-CNN: Visual Tracking by Re-Detection Image Source: https://www.researchgate.net/figure/LucidTracker-qualitative-results-on-DAVIS-17-test-dev-set-Frames-sampled-along-the_fig5_331792902

Source: The 2017 DAVIS Challenge on Video Object Segmentation

Dataset Variants

DAVIS 2017DAVIS 2017 (test-dev)DAVIS 2017 (val)DAVIS-2017

Papers1

The 2017 DAVIS Challenge on Video Object Segmentation

The scope of the benchmark, the main characteristics of the dataset, the evaluation metrics of the competition, and a detailed analysis of the results of the participants to the challenge are described.

Tasks

EDIT

Semantic Segmentation Video Object Segmentation Video Prediction Referring Expression Segmentation Semi-Supervised Video Object Segmentation Unsupervised Video Object Segmentation Interactive Video Object Segmentation

Similar Datasets

MNIST

CelebA

JFT-300M

Statistics

Papers

1

Tasks

6

Introduced

2016

License

Annotations under CC BY-SA 4.0

Modalities

ImagesVideos