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/GLEE-Pro

GLEE-Pro

Reported on 61 benchmarks across 12 tasks · 1 paper · 33 SOTA

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

Computer Vision49 results

VideoonRefer-YouTube-VOS
F· uses extra data· 2023-12-14
72.9
best: 75.7 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonRefer-YouTube-VOS
J· uses extra data· 2023-12-14
68.2
best: 71.8 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonRefer-YouTube-VOS
J&F· uses extra data· 2023-12-14
70.6
best: 73.7 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
HOTA (com)· uses extra data· 2023-12-14
48.7
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
HOTA (unc)· uses extra data· 2023-12-14
26.9
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
mAP (all)· uses extra data· 2023-12-14
19.2
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
mAP (com)· uses extra data· 2023-12-14
24.8
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
mAP (unc)· uses extra data· 2023-12-14
17.7
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Multi-Object TrackingonTAO
AssocA· uses extra data· 2023-12-14
46.2
best: 52.4 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Multi-Object TrackingonTAO
LocA· uses extra data· 2023-12-14
66.2
best: 71.8 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Multi-Object TrackingonTAO
TETA· uses extra data· 2023-12-14
47.2
best: 55.3 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object TrackingonTAO
AssocA· uses extra data· 2023-12-14
46.2
best: 52.4 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object TrackingonTAO
LocA· uses extra data· 2023-12-14
66.2
best: 71.8 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object TrackingonTAO
TETA· uses extra data· 2023-12-14
47.2
best: 55.3 (AED (Co-DETR))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefCOCO
IoU· uses extra data· 2023-12-14
80
best: 81 (DETRIS)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
F· uses extra data· 2023-12-14
72.9
best: 76.1 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J· uses extra data· 2023-12-14
68.2
best: 71.7 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· uses extra data· 2023-12-14
70.6
best: 73.9 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonUVO
ARmask· uses extra data· 2023-12-14
72.6
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonRefer-YouTube-VOS
F· uses extra data· 2023-12-14
72.9
best: 75.7 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonRefer-YouTube-VOS
J· uses extra data· 2023-12-14
68.2
best: 71.8 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonRefer-YouTube-VOS
J&F· uses extra data· 2023-12-14
70.6
best: 73.7 (FindTrack)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
HOTA (com)· uses extra data· 2023-12-14
48.7
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
HOTA (unc)· uses extra data· 2023-12-14
26.9
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
mAP (all)· uses extra data· 2023-12-14
19.2
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
mAP (com)· uses extra data· 2023-12-14
24.8
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
mAP (unc)· uses extra data· 2023-12-14
17.7
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefCOCO
IoU· uses extra data· 2023-12-14
80
best: 81 (DETRIS)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
F· uses extra data· 2023-12-14
72.9
best: 76.1 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J· uses extra data· 2023-12-14
68.2
best: 71.7 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F· uses extra data· 2023-12-14
70.6
best: 73.9 (MPG-SAM 2)
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Instance SegmentationonOVIS validation
AP75· uses extra data· 2023-12-14
55.5
best: 63.5 (CAVIS(VIT-L, Offline))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Instance SegmentationonOVIS validation
mask AP· uses extra data· 2023-12-14
50.4
best: 57.1 (DVIS-DAQ(VIT-L, Offline))
SOTA
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
VideoonBURST-val
HOTA (all)· uses extra data· 2023-12-14
31.2
best: 61.2 (Cutie (base, MEGA, 600 pixels))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Multi-Object TrackingonTAO
ClsA· uses extra data· 2023-12-14
29.1
best: 41.7 (AED (Co-DETR))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object TrackingonTAO
ClsA· uses extra data· 2023-12-14
29.1
best: 41.7 (AED (Co-DETR))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object DetectiononCOCO test-dev
box mAP· 2023-12-14
62.3
best: 66 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object DetectiononCOCO minival
box AP· uses extra data· 2023-12-14
62
best: 66 (PE_spatial (DETA))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2023-12-14
55.7
best: 68 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonCOCO minival
mask AP· uses extra data· 2023-12-14
54.2
best: 56.6 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonCOCO test-dev
mask AP· uses extra data· 2023-12-14
54.5
best: 57.1 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonLVIS v1.0 val
mask AP· uses extra data· 2023-12-14
49.9
best: 60.7 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefCoCo val
Overall IoU· uses extra data· 2023-12-14
80
best: 85.41 (DeRIS-L)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2023-12-14
69.6
best: 79.4 (MLCD-Seg-7B)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Instance SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2023-12-14
72.9
best: 79.9 (MLCD-Seg-7B)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Video Object SegmentationonBURST-val
HOTA (all)· uses extra data· 2023-12-14
31.2
best: 61.2 (Cutie (base, MEGA, 600 pixels))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefCoCo val
Overall IoU· uses extra data· 2023-12-14
80
best: 85.41 (DeRIS-L)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2023-12-14
69.6
best: 79.4 (MLCD-Seg-7B)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
Referring Expression SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2023-12-14
72.9
best: 79.9 (MLCD-Seg-7B)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158

Methodology12 results

3DonCOCO test-dev
box mAP· 2023-12-14
62.3
best: 66 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
3DonCOCO minival
box AP· uses extra data· 2023-12-14
62
best: 66 (PE_spatial (DETA))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
3DonLVIS v1.0 val
box AP· uses extra data· 2023-12-14
55.7
best: 68 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D ClassificationonCOCO test-dev
box mAP· 2023-12-14
62.3
best: 66 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D ClassificationonCOCO minival
box AP· uses extra data· 2023-12-14
62
best: 66 (PE_spatial (DETA))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D ClassificationonLVIS v1.0 val
box AP· uses extra data· 2023-12-14
55.7
best: 68 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D Object DetectiononCOCO test-dev
box mAP· 2023-12-14
62.3
best: 66 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D Object DetectiononCOCO minival
box AP· uses extra data· 2023-12-14
62
best: 66 (PE_spatial (DETA))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
2D Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2023-12-14
55.7
best: 68 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
16konCOCO test-dev
box mAP· 2023-12-14
62.3
best: 66 (Co-DETR)
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
16konCOCO minival
box AP· uses extra data· 2023-12-14
62
best: 66 (PE_spatial (DETA))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158
16konLVIS v1.0 val
box AP· uses extra data· 2023-12-14
55.7
best: 68 (Co-DETR (single-scale))
General Object Foundation Model for Images and Videos at Scale arXiv:2312.09158