HyperAI

Temporal Action Localization On Multithumos 1

Métriques

Average mAP
mAP IOU@0.1
mAP IOU@0.2
mAP IOU@0.3
mAP IOU@0.4
mAP IOU@0.5
mAP IOU@0.6
mAP IOU@0.7
mAP IOU@0.8
mAP IOU@0.9

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Average mAP
mAP IOU@0.1
mAP IOU@0.2
mAP IOU@0.3
mAP IOU@0.4
mAP IOU@0.5
mAP IOU@0.6
mAP IOU@0.7
mAP IOU@0.8
mAP IOU@0.9
Paper TitleRepository
PointTAD23.542.339.7 35.830.924.918.512.05.61.4PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
MS-TCT16.2---------MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
DualDETR (I3D-rgb)32.6453.42-47.41-35.18-20.18-4.02Dual DETRs for Multi-Label Temporal Action Detection-
TriDet (VideoMAEv2)37.5-57.7--42.7-24.3--Temporal Action Localization with Enhanced Instant Discriminability
TriDet (I3D-rgb)30.7-49.1--34.3-17.8--Temporal Action Localization with Enhanced Instant Discriminability
PDAN17.3---------PDAN: Pyramid Dilated Attention Network for Action Detection
TemporalMaxer29.949.147.544.339.433.426.517.49.12.24TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization
MLAD14.2---------Modeling Multi-Label Action Dependencies for Temporal Action Localization
0 of 8 row(s) selected.