Online action detection

57 citations recorded by the source corpus.

How researchers see this paper

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

PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “Recently, there are also several works focus on collecting different datasets of action type like TV-series [9], Movies [16] and Olympic Games [15].”
RED: Reinforced Encoder-Decoder Networks for Action Anticipation (2017, methodology): “The TVSeries Dataset [1] is a realistic, large-scale dataset for temporal action detection; it contains 16 hours of videos (27 episodes) from six recent popular TV series.”
Gaussian Temporal Awareness Networks for Action Localization (2019, background): “One fundamental challenge that underlies the success of these advances is action detection in videos from both temporal aspect [6, 9, 17, 30, 39, 43] and spatiotemporal aspect [11, 18].”
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction (2016, methodology): “Early, online action prediction has been studied using dynamic bag of words [30], structured SVMs [9], hierarchical representations [19], LSTMs and Fisher vectors [3].”
Real-Time Online Action Detection Forests Using Spatio-Temporal Contexts (2016, background): “Online action detection (OAD) refers to the task of simultaneously localizing actions and identifying their classes from streamed input sequences [11, 16, 26, 25, 52].”