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 321330 of 369 papers

TitleStatusHype
A Perceptual Prediction Framework for Self Supervised Event SegmentationCode0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
RefineLoc: Iterative Refinement for Weakly-Supervised Action LocalizationCode0
DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving VideosCode0
ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022Code0
Action Search: Spotting Actions in Videos and Its Application to Temporal Action LocalizationCode0
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity RecognitionCode0
Deep Concept-wise Temporal Convolutional Networks for Action LocalizationCode0
ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action LocalizationCode0
Show:102550
← PrevPage 33 of 37Next →

No leaderboard results yet.