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/MAST

MAST

Reported on 17 benchmarks across 5 tasks · 2 papers · 2 SOTA

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

Computer Vision25 results

VideoonDAVIS 2017 (val)
F-measure (Mean)· 2020-02-18
67.6
best: 93.4 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
F-measure (Recall)· 2020-02-18
77.7
best: 94.6 (STCN)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
J&F· 2020-02-18
65.5
best: 90.7 (SAM2)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
Jaccard (Mean)· 2020-02-18
63.3
best: 87.5 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
Jaccard (Recall)· 2020-02-18
73.2
best: 91.4 (ISVOS (MS))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
F-measure (Mean)· uses extra data· 2020-02-18
67.6
best: 93.4 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
F-measure (Recall)· uses extra data· 2020-02-18
77.7
best: 94.6 (STCN)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
J&F· uses extra data· 2020-02-18
65.5
best: 90.7 (SAM2)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
Jaccard (Mean)· uses extra data· 2020-02-18
63.3
best: 87.5 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
VideoonDAVIS 2017 (val)
Jaccard (Recall)· uses extra data· 2020-02-18
73.2
best: 91.4 (ISVOS (MS))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-02-18
67.6
best: 93.4 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Recall)· 2020-02-18
77.7
best: 94.6 (STCN)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-02-18
65.5
best: 90.7 (SAM2)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-02-18
63.3
best: 87.5 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Recall)· 2020-02-18
73.2
best: 91.4 (ISVOS (MS))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· uses extra data· 2020-02-18
67.6
best: 93.4 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Recall)· uses extra data· 2020-02-18
77.7
best: 94.6 (STCN)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
J&F· uses extra data· 2020-02-18
65.5
best: 90.7 (SAM2)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· uses extra data· 2020-02-18
63.3
best: 87.5 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Recall)· uses extra data· 2020-02-18
73.2
best: 91.4 (ISVOS (MS))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-02-18
67.6
best: 93.4 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Recall)· 2020-02-18
77.7
best: 94.6 (STCN)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-02-18
65.5
best: 90.7 (SAM2)
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-02-18
63.3
best: 87.5 (Cutie+ (base))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Recall)· 2020-02-18
73.2
best: 91.4 (ISVOS (MS))
MAST: A Memory-Augmented Self-supervised Tracker arXiv:2002.07793

Knowledge Base1 result

Text SummarizationonHow2 300h
ROUGE-L· 2020-10-15
43.23
SOTA
MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention arXiv:2010.08021

Natural Language Processing1 result

Abstractive Text SummarizationonHow2 300h
ROUGE-L· 2020-10-15
43.23
SOTA
MAST: Multimodal Abstractive Summarization with Trimodal Hierarchical Attention arXiv:2010.08021