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/ActionMamba(InternVideo2-6B)

ActionMamba(InternVideo2-6B)

Reported on 56 benchmarks across 4 tasks · 1 paper · 32 SOTA

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

Computer Vision42 results

VideoonHACS
Average-mAP· 2024-03-14
44.56
best: 45.8 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonHACS
mAP@0.5· 2024-03-14
64.02
best: 66.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonHACS
mAP@0.75· 2024-03-14
45.71
best: 47.2 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonHACS
mAP@0.95· 2024-03-14
13.34
best: 14.3 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonFineAction
mAP· 2024-03-14
29.04
best: 29.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonFineAction
mAP IOU@0.5· 2024-03-14
45.44
best: 46.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonFineAction
mAP IOU@0.75· 2024-03-14
28.82
best: 29.5 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonFineAction
mAP IOU@0.95· 2024-03-14
6.79
best: 7.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonHACS
Average-mAP· 2024-03-14
44.56
best: 45.8 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonHACS
mAP@0.5· 2024-03-14
64.02
best: 66.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonHACS
mAP@0.75· 2024-03-14
45.71
best: 47.2 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonHACS
mAP@0.95· 2024-03-14
13.34
best: 14.3 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonFineAction
mAP· 2024-03-14
29.04
best: 29.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonFineAction
mAP IOU@0.5· 2024-03-14
45.44
best: 46.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonFineAction
mAP IOU@0.75· 2024-03-14
28.82
best: 29.5 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonFineAction
mAP IOU@0.95· 2024-03-14
6.79
best: 7.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonHACS
Average-mAP· 2024-03-14
44.56
best: 45.8 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonHACS
mAP@0.5· 2024-03-14
64.02
best: 66.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonHACS
mAP@0.75· 2024-03-14
45.71
best: 47.2 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonHACS
mAP@0.95· 2024-03-14
13.34
best: 14.3 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonFineAction
mAP· 2024-03-14
29.04
best: 29.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonFineAction
mAP IOU@0.5· 2024-03-14
45.44
best: 46.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonFineAction
mAP IOU@0.75· 2024-03-14
28.82
best: 29.5 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonFineAction
mAP IOU@0.95· 2024-03-14
6.79
best: 7.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· 2024-03-14
72.72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
mAP IOU@0.3· 2024-03-14
86.89
best: 89.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
mAP IOU@0.4· 2024-03-14
83.09
best: 86.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
mAP IOU@0.5· 2024-03-14
76.9
best: 80.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
mAP IOU@0.6· 2024-03-14
65.91
best: 71 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
VideoonTHUMOS’14
mAP IOU@0.7· 2024-03-14
50.82
best: 56.1 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2024-03-14
72.72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2024-03-14
86.89
best: 89.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2024-03-14
83.09
best: 86.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2024-03-14
76.9
best: 80.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2024-03-14
65.91
best: 71 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2024-03-14
50.82
best: 56.1 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2024-03-14
72.72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2024-03-14
86.89
best: 89.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2024-03-14
83.09
best: 86.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2024-03-14
76.9
best: 80.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2024-03-14
65.91
best: 71 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2024-03-14
50.82
best: 56.1 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626

Methodology14 results

Zero-Shot LearningonHACS
Average-mAP· 2024-03-14
44.56
best: 45.8 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonHACS
mAP@0.5· 2024-03-14
64.02
best: 66.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonHACS
mAP@0.75· 2024-03-14
45.71
best: 47.2 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonHACS
mAP@0.95· 2024-03-14
13.34
best: 14.3 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonFineAction
mAP· 2024-03-14
29.04
best: 29.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonFineAction
mAP IOU@0.5· 2024-03-14
45.44
best: 46.4 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonFineAction
mAP IOU@0.75· 2024-03-14
28.82
best: 29.5 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonFineAction
mAP IOU@0.95· 2024-03-14
6.79
best: 7.6 (RDFA-S6 (InternVideo2-6B))
SOTA
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· 2024-03-14
72.72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· 2024-03-14
86.89
best: 89.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· 2024-03-14
83.09
best: 86.7 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· 2024-03-14
76.9
best: 80.9 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.6· 2024-03-14
65.91
best: 71 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.7· 2024-03-14
50.82
best: 56.1 (AdaTAD (VideoMAEv2-giant))
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding arXiv:2403.09626