Actionness Ranking with Lattice Conditional Ordinal Random Fields

By Caiming Xiong, Ran Xu, Jason J. Corso. 2014

87 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Extraction

Citations in the corpus

Towards Automatic Learning of Procedures From Web Instructional Videos (2017, background): “These works all emphasize instantaneous or short term actions, which clearly play a role in understanding short or structured videos (Chen et al. 2014).”
Towards Weakly-Supervised Action Localization (2016, background): “In [12], proposals are based on an actionness measure [24], which requires localized training samples.”
Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization (2017, background): “A large number of works have successfully tackled the task of action recognition [8,9,28,38,42] and spatio-temporal localization [10,18,27,30,33,39].”
Encouraging LSTMs to Anticipate Actions Very Early (2017, background): “This is in contrast to existing methods that typically extract either global representations for the entire image [6, 41, 42, 7] or video sequence [35, 14], thus not focusing on the action itself, or localize the feature extraction process to the action itself via dense trajectories [39, 38, 9], opt”
Action Tubelet Detector for Spatio-Temporal Action Localization (2017, unknown): “More recently, some approaches [17, 34, 38] rely on an actionness measure [4], i.”
SST: Single-Stream Temporal Action Proposals (2017, unknown): “[4, 12, 16, 34, 37, 39].”
Joint action recognition and pose estimation from video (2015, methodology): “Many methods for action recognition bypass body poses and achieve promising results by using coarse/mid-level features for action classification on some datasets[6, 10, 26, 12, 18, 2, 33, 30].”
AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture (2017, methodology): “3The term actionness [2] is used to denote the possibility of an action being present within a 3D region proposal.”
Human Action Localization with Sparse Spatial Supervision (2017, background): “In [18], proposals are based on an actionness measure [30] which requires localized training samples.”
A Review of Human Activity Recognition Methods (2015, methodology): “Chen et al. (2014) addressed the problem of identifying and localizing human actions using CRFs.”
Predicting the Where and What of Actors and Actions through Online Action Localization (2016, methodology): “There have been few similar recent methods for quantifying actionness [3, 42], which yield fewer regions of interest in videos.”
Fast action proposals for human action detection and search (2015, methodology): “In [34], “actionness” is measured based on lattice conditional ordinal random fields.”
Efficient Action Detection in Untrimmed Videos via Multi-task Learning (2016, background): “This temporal actionness is related to but different from the spatial actionness introduced in [1].”