NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning

Alexander Richard, Hilde Kuehne, Ahsan Iqbal, Juergen Gall

URL

Proceedings: CVPR

Year: 2018

Peer Reviewed : No

Results: 
Breakfast Dataset /BF Action seg. weakly (MoF): 43% (NN-Viterbi )
Hollywood Extended /HE Action alignment weakly (IoD): 48.7% (NN-Viterbi)