DAVIS 2016

Video object segmentation dataset

DAVIS16 is a dataset for video object segmentation which consists of 50 videos in total (30 videos for training and 20 for testing). Per-frame pixel-wise annotations are offered.

View this Dataset

View author website

Task

Video Object Segmentation

Annotation Types

Instance Segmentation

Items

Classes

Labels

Models using this dataset

Last updated on

January 20, 2022

Licensed under

Unknown

Star

View this Dataset