493 citations · 893 across the 5 of their papers we have counts for
6 papers
Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Moritz Kampelmühler, Axel Pinz
Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the fir…
What have we learned from deep representations for action recognition?
Christoph Feichtenhofer, Axel Pinz, Richard P. Wildes +1
As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they a…
Detect to Track and Track to Detect
Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman
Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this pape…
Spatiotemporal Residual Networks for Video Action Recognition
Christoph Feichtenhofer, Axel Pinz, Richard P. Wildes
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new techni…
Convolutional Two-Stream Network Fusion for Video Action Recognition
Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman
Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion…
Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Karla Brkić, Srđan Rašić, Axel Pinz +2
This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors…