The 2017 DAVIS Challenge on Video Object Segmentation
This provides a standardized benchmark for researchers in computer vision to evaluate and advance video object segmentation methods, though it is incremental as it builds on existing initiatives.
The paper introduces the 2017 DAVIS Challenge, a dataset, benchmark, and competition for video object segmentation, building on the DAVIS dataset to foster new state-of-the-art techniques, with results analyzed from participants.
We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation. Following the footsteps of other successful initiatives, such as ILSVRC and PASCAL VOC, which established the avenue of research in the fields of scene classification and semantic segmentation, the DAVIS Challenge comprises a dataset, an evaluation methodology, and a public competition with a dedicated workshop co-located with CVPR 2017. The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated VIdeo Segmentation), which has fostered the development of several novel state-of-the-art video object segmentation techniques. In this paper we describe the scope of the benchmark, highlight the main characteristics of the dataset, define the evaluation metrics of the competition, and present a detailed analysis of the results of the participants to the challenge.