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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 181–190 of 369 papers

TitleStatusHype
Learning to track for spatio-temporal action localization—0
LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization—0
Localizing Actions from Video Labels and Pseudo-Annotations—0
Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder—0
Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action Localization—0
Localizing Unseen Activities in Video via Image Query—0
LocATe: End-to-end Localization of Actions in 3D with Transformers—0
LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization—0
Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization—0
Low-Fidelity Video Encoder Optimization for Temporal Action Localization—0
Show:102550
← PrevPage 19 of 37Next →

No leaderboard results yet.