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
Test-Time Zero-Shot Temporal Action LocalizationCode2
Temporal Action Localization with Enhanced Instant DiscriminabilityCode2
NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023Code2
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries ChallengeCode2
Structured Attention Composition for Temporal Action LocalizationCode2
ActionFormer: Localizing Moments of Actions with TransformersCode2
Zero-Shot Temporal Interaction Localization for Egocentric VideosCode1
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long VideosCode1
XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and GlassesCode1
Show:102550
← PrevPage 1 of 37Next →

No leaderboard results yet.