Discriminative convolutional Fisher vector network for action recognition

Posted on Sat 05 August 2017 in research • Tagged with human action recognition, deep learningLeave a comment

We uploaded our paper entitled Discriminative convolutional Fisher vector network for action recognition to arXiv. You can check out the paper by following this link.

Abstract

Discriminative convolutional Fisher vector network for action recognition

Petar Palasek, Ioannis Patras

In this work we propose a novel neural network architecture for the …

Continue reading

New publication added!

Posted on Sat 05 August 2017 in research • Tagged with human pose estimation, deep learningLeave a comment

Our work on Deep globally constrained MRFs for Human Pose Estimation was accepted at the International Conference on Computer Vision (ICCV 2017) which will be held from October 22nd to 29th, 2017 in Venice, Italy.

Abstract

Deep globally constrained MRFs for Human Pose Estimation

Ioannis Marras, Petar Palasek, Ioannis Patras …

Continue reading

New publication added!

Posted on Tue 06 June 2017 in research • Tagged with background modelling, deep learningLeave a comment

Our work on Background Modelling Based on Generative Unet was accepted at the Analysis of video and audio "in the Wild" Workshop , an international workshop organised in conjuction with IEEE AVSS 2017, that will be held on August 29 in Lecce, Italy.

Abstract

Background Modelling Based on Generative Unet

Ye …

Continue reading