DAVIS-17
Emerging5papers using it
2018first seen
DAVIS-17 is a benchmark dataset used to evaluate Zero-Shot Video Object Segmentation (ZS-VOS) performance, containing a collection of video sequences with annotated object instances.
Papers using DAVIS-17 (5)
- Structure Matters: Revisiting Boundary Refinement in Video Object SegmentationStudying Image Diffusion Features for Zero-Shot Video Object
SegmentationLearning Dynamic Network Using a Reuse Gate Function in Semi-supervised
Video Object SegmentationFlowVOS: Weakly-Supervised Visual Warping for Detail-Preserving and
Temporally Consistent Single-Shot Video Object SegmentationVideo Object Segmentation with Language Referring Expressions