TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Video Instance Segmentation

Video Instance Segmentation

27 benchmarks148 papers

The goal of video instance segmentation is simultaneous detection, segmentation and tracking of instances in videos. In words, it is the first time that the image instance segmentation problem is extended to the video domain.

To facilitate research on this new task, a large-scale benchmark called YouTube-VIS, which consists of 2,883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks is built.

Benchmarks

Video Instance Segmentation on OVIS validation

mask APAP75AP50AR1AR10APhoAPmoAPso

Video Instance Segmentation on YouTube-VIS validation

mask APAP50AP75AR1AR10

Video Instance Segmentation on YouTube-VIS 2021

mask APAP50AP75AR1AR10

Video Instance Segmentation on Youtube-VIS 2022 Validation

mAP_LAP50_LAP75_LAR1_LAR10_L

Video Instance Segmentation on BDD100K val

mMOTSA

Video Instance Segmentation on HQ-YTVIS

Tube-Boundary AP

Video Instance Segmentation on YouTube-VIS

mask AP

Video Instance Segmentation on Youtube-VIS (trained with no video masks)

AP