76 citations · 179 across the 9 of their papers we have counts for
6 papers · 2 filters
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
Alexandros Stergiou, Ronald Poppe
Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics…
Class Feature Pyramids for Video Explanation
Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis +3
Deep convolutional networks are widely used in video action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While 3D convolution…
Multitask Learning to Improve Egocentric Action Recognition
Georgios Kapidis, Ronald Poppe, Elsbeth van Dam +2
In this work we employ multitask learning to capitalize on the structure that exists in related supervised tasks to train complex neural networks. It allows training a network for…
Light Field Saliency Detection with Deep Convolutional Networks
Jun Zhang, Yamei Liu, Shengping Zhang +2
Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light. The detection of salient regions in a light f…
Egocentric Hand Track and Object-based Human Action Recognition
Georgios Kapidis, Ronald Poppe, Elsbeth van Dam +2
Egocentric vision is an emerging field of computer vision that is characterized by the acquisition of images and video from the first person perspective. In this paper we address t…
Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis +3
Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve stat…