2 Hits in 1.1 sec

DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks [article]

Unaiza Ahsan, Chen Sun, Irfan Essa
2018 arXiv   pre-print
We propose an action recognition framework using Gen- erative Adversarial Networks.  ...  Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information.  ...  Generative Adversarial Networks [4] have been used for semi-supervised feature learning particularly after the introduction of Deep Convolutional GANs (or DCGANs) [38] .  ... 
arXiv:1801.07230v1 fatcat:jadecr4slffrtezim3lrr2klva

t-EVA: Time-Efficient t-SNE Video Annotation [article]

Soroosh Poorgholi, Osman Semih Kayhan, Jan C. van Gemert
2020 arXiv   pre-print
Placing the same actions from different videos near each other in the two-dimensional space based on feature similarity helps the annotator to group-label video clips.  ...  In this work, we propose a time-efficient video annotation method using spatio-temporal feature similarity and t-SNE dimensionality reduction to speed up the annotation process massively.  ...  .: Discrimnet: Semi-supervised action recognition from videos using generative adversarial networks. CoRR abs/1801.07230 (2018), 2.  ... 
arXiv:2011.13202v1 fatcat:4zsyhvyayveepld4ucoypqm2u4