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 125 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
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
Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action LocalizationCode1
HAT: History-Augmented Anchor Transformer for Online 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
SFMViT: SlowFast Meet ViT in Chaotic WorldCode1
UniAV: Unified Audio-Visual Perception for Multi-Task Video Event LocalizationCode1
ASTRA: An Action Spotting TRAnsformer for Soccer VideosCode1
Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action LocalizationCode1
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based ApproachCode1
Show:102550
← PrevPage 1 of 15Next →

No leaderboard results yet.