Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/LOCATE

LOCATE

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

VideoonFBMS-59
mIoU· 2023-08-22
68.8
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
VideoonSegTrack-v2
mIoU· 2023-08-22
79.9
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
VideoonDAVIS 2016
Contour Accuracy· 2023-08-22
88.7
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
Video Object SegmentationonFBMS-59
mIoU· 2023-08-22
68.8
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
Video Object SegmentationonSegTrack-v2
mIoU· 2023-08-22
79.9
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
Video Object SegmentationonDAVIS 2016
Contour Accuracy· 2023-08-22
88.7
SOTA
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
VideoonDAVIS 2016
mIoU· 2023-08-22
80.9
best: 84.5 (VOSwL (Mask+Language))
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239
Video Object SegmentationonDAVIS 2016
mIoU· 2023-08-22
80.9
best: 84.5 (VOSwL (Mask+Language))
LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training arXiv:2308.11239