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/MANET

MANET

Reported on 22 benchmarks across 2 tasks · 1 paper

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

Computer Vision22 results

Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
F· 2022-07-26
56.51
best: 76.1 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J· 2022-07-26
54.75
best: 71.7 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· 2022-07-26
55.63
best: 73.9 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
AP· 2022-07-26
0.471
best: 0.585 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
IoU mean· 2022-07-26
0.632
best: 0.725 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
IoU overall· 2022-07-26
0.726
best: 0.807 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
Precision@0.5· 2022-07-26
0.734
best: 0.851 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
Precision@0.6· 2022-07-26
0.682
best: 0.827 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
Precision@0.7· 2022-07-26
0.579
best: 0.767 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
Precision@0.8· 2022-07-26
0.389
best: 0.617 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Instance SegmentationonA2D Sentences
Precision@0.9· 2022-07-26
0.132
best: 0.259 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
F· 2022-07-26
56.51
best: 76.1 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J· 2022-07-26
54.75
best: 71.7 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· 2022-07-26
55.63
best: 73.9 (MPG-SAM 2)
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
AP· 2022-07-26
0.471
best: 0.585 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
IoU mean· 2022-07-26
0.632
best: 0.725 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
IoU overall· 2022-07-26
0.726
best: 0.807 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
Precision@0.5· 2022-07-26
0.734
best: 0.851 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
Precision@0.6· 2022-07-26
0.682
best: 0.827 (SOC (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
Precision@0.7· 2022-07-26
0.579
best: 0.767 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
Precision@0.8· 2022-07-26
0.389
best: 0.617 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622
Referring Expression SegmentationonA2D Sentences
Precision@0.9· 2022-07-26
0.132
best: 0.259 (SgMg (Video-Swin-B))
Multi-Attention Network for Compressed Video Referring Object Segmentation arXiv:2207.12622