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/SgMg (Video-Swin-B)

SgMg (Video-Swin-B)

Reported on 32 benchmarks across 2 tasks · 1 paper · 22 SOTA

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

Computer Vision32 results

Instance SegmentationonA2D Sentences
AP· uses extra data· 2023-07-25
0.585
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
Precision@0.7· uses extra data· 2023-07-25
0.767
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
Precision@0.8· uses extra data· 2023-07-25
0.617
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
Precision@0.9· uses extra data· 2023-07-25
0.259
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
AP· uses extra data· 2023-07-25
0.45
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
IoU mean· uses extra data· 2023-07-25
0.725
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
IoU overall· uses extra data· 2023-07-25
0.737
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
Precision@0.5· uses extra data· 2023-07-25
0.972
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
Precision@0.6· uses extra data· 2023-07-25
0.917
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
Precision@0.7· uses extra data· 2023-07-25
0.714
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
Precision@0.8· uses extra data· 2023-07-25
0.225
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
AP· uses extra data· 2023-07-25
0.585
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
Precision@0.7· uses extra data· 2023-07-25
0.767
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
Precision@0.8· uses extra data· 2023-07-25
0.617
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
Precision@0.9· uses extra data· 2023-07-25
0.259
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
AP· uses extra data· 2023-07-25
0.45
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
IoU mean· uses extra data· 2023-07-25
0.725
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
IoU overall· uses extra data· 2023-07-25
0.737
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
Precision@0.5· uses extra data· 2023-07-25
0.972
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
Precision@0.6· uses extra data· 2023-07-25
0.917
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
Precision@0.7· uses extra data· 2023-07-25
0.714
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
Precision@0.8· uses extra data· 2023-07-25
0.225
SOTA
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
IoU mean· uses extra data· 2023-07-25
0.72
best: 0.725 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
IoU overall· uses extra data· 2023-07-25
0.799
best: 0.807 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
Precision@0.5· uses extra data· 2023-07-25
0.843
best: 0.851 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonA2D Sentences
Precision@0.6· uses extra data· 2023-07-25
0.822
best: 0.827 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Instance SegmentationonJ-HMDB
Precision@0.9· uses extra data· 2023-07-25
0.003
best: 0.4 (HINet)
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
IoU mean· uses extra data· 2023-07-25
0.72
best: 0.725 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
IoU overall· uses extra data· 2023-07-25
0.799
best: 0.807 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
Precision@0.5· uses extra data· 2023-07-25
0.843
best: 0.851 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonA2D Sentences
Precision@0.6· uses extra data· 2023-07-25
0.822
best: 0.827 (SOC (Video-Swin-B))
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537
Referring Expression SegmentationonJ-HMDB
Precision@0.9· uses extra data· 2023-07-25
0.003
best: 0.4 (HINet)
Spectrum-guided Multi-granularity Referring Video Object Segmentation arXiv:2307.13537