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 311320 of 369 papers

TitleStatusHype
Learning Discriminative Motion Features Through Detection0
Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries0
A Perceptual Prediction Framework for Self Supervised Event SegmentationCode0
BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization0
What do I Annotate Next? An Empirical Study of Active Learning for Action Localization0
AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos0
Actor-Centric Relation Network0
Diagnosing Error in Temporal Action DetectorsCode0
Show:102550
← PrevPage 32 of 37Next →

No leaderboard results yet.