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 2130 of 369 papers

TitleStatusHype
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual ActionsCode1
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming VideosCode1
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020Code1
A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action LocalizationCode1
Convex Combination Consistency between Neighbors for Weakly-supervised Action LocalizationCode1
Cross-modal Consensus Network for Weakly Supervised Temporal Action LocalizationCode1
Actor-Context-Actor Relation Network for Spatio-Temporal Action LocalizationCode1
E^2TAD: An Energy-Efficient Tracking-based Action DetectorCode1
EgoTaskQA: Understanding Human Tasks in Egocentric VideosCode1
Background-Click Supervision for Temporal Action LocalizationCode1
Show:102550
← PrevPage 3 of 37Next →

No leaderboard results yet.