Temporal Action Localization
Temporal Action Localization is a sub-task in the field of computer vision that aims to detect activities within video streams and output their start and end timestamps. This task provides critical support for applications such as video analysis, surveillance, and content retrieval by accurately pinpointing when actions occur in a video. Closely related to Temporal Action Proposal Generation, it can effectively enhance the accuracy and efficiency of video understanding.
THUMOS’14
TSP
ActivityNet-1.3
AVFusion
HACS
TriDet (SlowFast)
FineAction
BMN (i3d feaure)
MultiTHUMOS
TriDet (VideoMAEv2)
CrossTask
VideoCLIP
EPIC-KITCHENS-100
AdaTAD (verb, VideoMAE-L)
MUSES
TemporalMaxer
ActivityNet-1.2
DeepMetricLearner
Ego4D MQ test
ActionFormer (SlowFast+Omnivore+EgoVLP)
Ego4D MQ val
MEXaction2
S-CNN
THUMOS'14
AVFusion
THUMOS14
BasicTAD (R50-SlowOnly)