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 121130 of 369 papers

TitleStatusHype
ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022Code0
A Simple Transformer-Based Model for Ego4D Natural Language Queries ChallengeCode0
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries ChallengeCode2
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization TasksCode0
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention0
SimOn: A Simple Framework for Online Temporal Action LocalizationCode1
EgoTaskQA: Understanding Human Tasks in Egocentric VideosCode1
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization0
Adaptive Perception Transformer for Temporal Action Localization0
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream0
Show:102550
← PrevPage 13 of 37Next →

No leaderboard results yet.