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 110 of 369 papers

TitleStatusHype
The Surprising Effectiveness of Multimodal Large Language Models for Video Moment RetrievalCode2
ActionFormer: Localizing Moments of Actions with TransformersCode2
Structured Attention Composition for Temporal Action LocalizationCode2
Test-Time Zero-Shot Temporal Action LocalizationCode2
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries ChallengeCode2
Temporal Action Localization with Enhanced Instant DiscriminabilityCode2
NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023Code2
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming VideosCode1
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020Code1
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual ActionsCode1
Show:102550
← PrevPage 1 of 37Next →

No leaderboard results yet.