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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–369 of 369 papers

TitleStatusHype
Distributed Adaptive Learning of Graph Signals—0
Tubelets: Unsupervised action proposals from spatiotemporal super-voxels—0
VideoLSTM Convolves, Attends and Flows for Action RecognitionCode0
Predicting the Where and What of Actors and Actions Through Online Action Localization—0
Temporal Action Localization With Pyramid of Score Distribution Features—0
What If We Do Not Have Multiple Videos of the Same Action? -- Video Action Localization Using Web Images—0
Beyond Caption To Narrative: Video Captioning With Multiple Sentences—0
Human Action Localization with Sparse Spatial Supervision—0
Spot On: Action Localization from Pointly-Supervised Proposals—0
DAP3D-Net: Where, What and How Actions Occur in Videos?—0
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNsCode0
Action Localization in Videos Through Context Walk—0
Learning to track for spatio-temporal action localization—0
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web ImagesCode0
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks—0
Action Localization with Tubelets from Motion—0
Efficient Action Localization with Approximately Normalized Fisher Vectors—0
Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization—0
Max-Margin Structured Output Regression for Spatio-Temporal Action Localization—0
Show:102550
← PrevPage 15 of 15Next →

No leaderboard results yet.