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 1120 of 369 papers

TitleStatusHype
Temporal Action Localization with Cross Layer Task Decoupling and RefinementCode1
Open-Vocabulary Action Localization with Iterative Visual PromptingCode1
Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action LocalizationCode1
HAT: History-Augmented Anchor Transformer for Online Temporal Action LocalizationCode1
Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action LocalizationCode1
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent MechanismCode1
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming VideosCode1
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action LocalizationCode1
Referring Atomic Video Action RecognitionCode1
EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action UnderstandingCode1
Show:102550
← PrevPage 2 of 37Next →

No leaderboard results yet.