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 301–325 of 369 papers

TitleStatusHype
Representation Learning on Visual-Symbolic Graphs for Video Understanding—0
Spatio-Temporal Action Localization in a Weakly Supervised Setting—0
Temporal Unet: Sample Level Human Action Recognition using WiFiCode0
Weakly Supervised Gaussian Networks for Action Detection—0
RefineLoc: Iterative Refinement for Weakly-Supervised Action LocalizationCode0
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos—0
Exploring Frame Segmentation Networks for Temporal Action Localization—0
Spatio-temporal Action Recognition: A Survey—0
Cricket stroke extraction: Towards creation of a large-scale cricket actions dataset—0
Learning Discriminative Motion Features Through Detection—0
Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries—0
A Perceptual Prediction Framework for Self Supervised Event SegmentationCode0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization—0
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization—0
What do I Annotate Next? An Empirical Study of Active Learning for Action Localization—0
AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos—0
Actor-Centric Relation Network—0
Diagnosing Error in Temporal Action DetectorsCode0
A Better Baseline for AVA—0
AutoLoc: Weakly-supervised Temporal Action LocalizationCode0
Spatio-Temporal Instance Learning: Action Tubes from Class Supervision—0
A flexible model for training action localization with varying levels of supervisionCode0
YH Technologies at ActivityNet Challenge 2018—0
Modeling Spatio-Temporal Human Track Structure for Action Localization—0
Show:102550
← PrevPage 13 of 15Next →

No leaderboard results yet.