DAVIS: Densely Annotated VIdeo Segmentation

In-depth analysis of the state-of-the-art in video object segmentation



A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross, and A. Sorkine-Hornung
Computer Vision and Pattern Recognition (CVPR) 2016
[PDF] [Supplemental] [BibTex]

author = {F. Perazzi and J. Pont-Tuset and B. McWilliams and L. Van Gool and M. Gross and A. Sorkine-Hornung},
title = {A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation},
booktitle = {Computer Vision and Pattern Recognition},
year = {2016}
Please cite this paper in your publications if it helps your research.


Over the years, datasets and benchmarks have proven their fundamental importance in computer vision research, enabling targeted progress and objective comparisons in many fields. At the same time, legacy datasets may impend the evolution of a field due to saturated algorithm performance and the lack of contemporary, high quality data. In this work we present a new benchmark dataset and evaluation methodology for the area of video object segmentation. The dataset, named DAVIS (Densely Annotated VIdeo Segmentation), consists of fifty high quality, Full HD video sequences, spanning multiple occurrences of common video object segmentation challenges such as occlusions, motion-blur and appearance changes. Each video is accompanied by densely annotated, pixel-accurate and per-frame ground truth segmentation. In addition, we provide a comprehensive analysis of several state-of-the-art segmentation approaches using three complementary metrics that measure the spatial extent of the segmentation, the accuracy of the silhouette contours and the temporal coherence. The results uncover strengths and weaknesses of current approaches, opening up promising directions for future works.

Preview of the Annotations

Benchmark State-of-the-Art

Display the evaluation of the current State-of-the-Art segmentation tecniques in DAVIS; using the three presented measures in our work.

Explore State-of-the-Art Results

Visualize the segmentation results for all state-of-the-Art techniques on all DAVIS images, right from your browser.


Download the DAVIS images and annotations, pre-computed results from all techniques, and the code to reproduce the evaluation.

Is your technique missing although it's published and the code is public? Let us know and we'll add it.