Picture for Axel Pinz

Axel Pinz

Synthesizing human-like sketches from natural images using a conditional convolutional decoder

Add code
Mar 16, 2020
Figure 1 for Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Figure 2 for Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Figure 3 for Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Figure 4 for Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Viaarxiv icon

Detect to Track and Track to Detect

Add code
Mar 07, 2018
Figure 1 for Detect to Track and Track to Detect
Figure 2 for Detect to Track and Track to Detect
Figure 3 for Detect to Track and Track to Detect
Figure 4 for Detect to Track and Track to Detect
Viaarxiv icon

What have we learned from deep representations for action recognition?

Add code
Jan 04, 2018
Figure 1 for What have we learned from deep representations for action recognition?
Figure 2 for What have we learned from deep representations for action recognition?
Figure 3 for What have we learned from deep representations for action recognition?
Figure 4 for What have we learned from deep representations for action recognition?
Viaarxiv icon

Spatiotemporal Residual Networks for Video Action Recognition

Add code
Nov 07, 2016
Figure 1 for Spatiotemporal Residual Networks for Video Action Recognition
Figure 2 for Spatiotemporal Residual Networks for Video Action Recognition
Figure 3 for Spatiotemporal Residual Networks for Video Action Recognition
Figure 4 for Spatiotemporal Residual Networks for Video Action Recognition
Viaarxiv icon

Convolutional Two-Stream Network Fusion for Video Action Recognition

Add code
Sep 26, 2016
Figure 1 for Convolutional Two-Stream Network Fusion for Video Action Recognition
Figure 2 for Convolutional Two-Stream Network Fusion for Video Action Recognition
Figure 3 for Convolutional Two-Stream Network Fusion for Video Action Recognition
Figure 4 for Convolutional Two-Stream Network Fusion for Video Action Recognition
Viaarxiv icon

Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data

Add code
Oct 01, 2013
Figure 1 for Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Figure 2 for Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Figure 3 for Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Figure 4 for Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
Viaarxiv icon