DAVIS (Densely Annotated VIdeo Segmentation)
Introduced by Perazzi et al. in A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
The Densely Annotation Video Segmentation dataset (DAVIS) is a high quality and high resolution densely annotated video segmentation dataset under two resolutions, 480p and 1080p. There are 50 video sequences with 3455 densely annotated frames in pixel level. 30 videos with 2079 frames are for training and 20 videos with 1376 frames are for validation.
Source: TENet: Triple Excitation Network for Video Salient Object DetectionBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
DAVIS (no YouTube-VOS training)
|
HMMN
|
|||
|
DAVIS
|
ICL CFR-1
|
|||
|
DAVIS
|
DMT
|
|||
|
DAVIS sigma40
|
ReViD
|
|||
|
DAVIS sigma50
|
ReViD
|
|||
|
DAVIS sigma30
|
ReViD
|
|||
|
DAVIS sigma20
|
ReViD
|
|||
|
DAVIS 2017
|
MiVOS
|
|||
|
DAVIS sigma10
|
ReViD
|
|||
|
DAVIS 2017
|
AOC-MF
|
|||
|
DAVIS
|
DBVI
|
|||
|
DAVIS 2017
|
DMVFN
|
|||
|
DAVIS
|
TAPIR
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
