SOTAVerified

Action Localization

Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.

Papers

Showing 151160 of 369 papers

TitleStatusHype
LocATe: End-to-end Localization of Actions in 3D with Transformers0
Point3D: tracking actions as moving points with 3D CNNs0
OpenTAL: Towards Open Set Temporal Action LocalizationCode1
Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge PropagationCode1
When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in VlogsCode0
ActionFormer: Localizing Moments of Actions with TransformersCode2
OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos0
TVNet: Temporal Voting Network for Action LocalizationCode0
Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization0
Everything at Once - Multi-Modal Fusion Transformer for Video RetrievalCode1
Show:102550
← PrevPage 16 of 37Next →

No leaderboard results yet.