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 326–350 of 369 papers

TitleStatusHype
Modeling Spatio-Temporal Human Track Structure for Action Localization—0
One-Shot Action Localization by Learning Sequence Matching Network—0
Pointly-Supervised Action Localization—0
VideoCapsuleNet: A Simplified Network for Action Detection—0
Rethinking the Faster R-CNN Architecture for Temporal Action Localization—0
Precise Temporal Action Localization by Evolving Temporal Proposals—0
Guess Where? Actor-Supervision for Spatiotemporal Action LocalizationCode0
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal LocalizationCode0
Weakly Supervised Action Localization by Sparse Temporal Pooling NetworkCode0
Unsupervised Action Discovery and Localization in Videos—0
Exploring Temporal Preservation Networks for Precise Temporal Action Localization—0
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions—0
Localizing Actions from Video Labels and Pseudo-Annotations—0
Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017—0
Detecting Parts for Action Localization—0
Action Search: Spotting Actions in Videos and Its Application to Temporal Action LocalizationCode0
Generic Tubelet Proposals for Action Localization—0
Action Tubelet Detector for Spatio-Temporal Action LocalizationCode0
Temporal Action Localization by Structured Maximal Sums—0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and DetectionCode0
TURN TAP: Temporal Unit Regression Network for Temporal Action ProposalsCode0
CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed VideosCode0
Efficient Action Detection in Untrimmed Videos via Multi-Task Learning—0
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition—0
Show:102550
← PrevPage 14 of 15Next →

No leaderboard results yet.