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 7180 of 369 papers

TitleStatusHype
E^2TAD: An Energy-Efficient Tracking-based Action DetectorCode1
Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic EventsCode1
Localizing the Common Action Among a Few VideosCode1
Modeling Multi-Label Action Dependencies for Temporal Action LocalizationCode1
Learning Sparse 2D Temporal Adjacent Networks for Temporal Action LocalizationCode1
MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports ActionsCode1
OpenTAL: Towards Open Set Temporal Action LocalizationCode1
Open-Vocabulary Action Localization with Iterative Visual PromptingCode1
Bottom-Up Temporal Action Localization with Mutual RegularizationCode1
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action LocalizationCode1
Show:102550
← PrevPage 8 of 37Next →

No leaderboard results yet.