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/ActionFormer (VideoMAE V2-g features)

ActionFormer (VideoMAE V2-g features)

Reported on 24 benchmarks across 4 tasks · 1 paper · 16 SOTA

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

Computer Vision18 results

VideoonTHUMOS’14
mAP IOU@0.3· uses extra data· 2023-03-29
84
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
VideoonTHUMOS’14
mAP IOU@0.5· uses extra data· 2023-03-29
73
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
VideoonTHUMOS’14
mAP IOU@0.6· uses extra data· 2023-03-29
63.5
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
VideoonTHUMOS’14
mAP IOU@0.7· uses extra data· 2023-03-29
47.7
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· uses extra data· 2023-03-29
84
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· uses extra data· 2023-03-29
73
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.6· uses extra data· 2023-03-29
63.5
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.7· uses extra data· 2023-03-29
47.7
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
mAP IOU@0.3· uses extra data· 2023-03-29
84
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
mAP IOU@0.5· uses extra data· 2023-03-29
73
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
mAP IOU@0.6· uses extra data· 2023-03-29
63.5
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
mAP IOU@0.7· uses extra data· 2023-03-29
47.7
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2023-03-29
69.6
best: 76.9 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
VideoonTHUMOS’14
mAP IOU@0.4· uses extra data· 2023-03-29
79.6
best: 86.7 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2023-03-29
69.6
best: 76.9 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· uses extra data· 2023-03-29
79.6
best: 86.7 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2023-03-29
69.6
best: 76.9 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Action LocalizationonTHUMOS’14
mAP IOU@0.4· uses extra data· 2023-03-29
79.6
best: 86.7 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727

Methodology6 results

Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· uses extra data· 2023-03-29
84
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· uses extra data· 2023-03-29
73
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.6· uses extra data· 2023-03-29
63.5
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.7· uses extra data· 2023-03-29
47.7
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2023-03-29
69.6
best: 76.9 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· uses extra data· 2023-03-29
79.6
best: 86.7 (AdaTAD (VideoMAEv2-giant))
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking arXiv:2303.16727