Axel Pinz

Graz University of Technology — Austria

Engineering · Physical Sciences

37h-index11.2kcitations269works0.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Robotics and Sensor-Based Localization(59), Advanced Image and Video Retrieval Techniques(50), Advanced Vision and Imaging(41), Image Retrieval and Classification Techniques(29), Industrial Vision Systems and Defect Detection(29)

Publications269 total

A Robust Affine Matching Algorithm Using an Exponentially Decreasing Distance Function
TUGraz OPEN Library (Graz University of Technology)·2020Open Access
A Spatiotemporal Generative Adversarial Network to Generate Human Action Video
TUGraz OPEN Library (Graz University of Technology)·2020Open Access
Synthesizing human-like sketches from natural images using a conditional\n convolutional decoder
arXiv (Cornell University)·2020Open Access
Synthesizing human-like sketches from natural images using a conditional convolutional decoder
arXiv (Cornell University)·2020Open Access
Synthesizing human-like sketches from natural images using a conditional convolutional decoder
2020· 18 cited
Representing Objects in Video as Space-Time Volumes by Combining Top-Down and Bottom-Up Processes
2020
Deep Insights into Convolutional Networks for Video Recognition
International Journal of Computer Vision·2019· 28 citedOpen Access
Automated qualitative and quantitative assessment of posterior capsule opacification by Automated Quantification of After-Cataract II (AQUA II) system
BMC Ophthalmology·2019· 11 citedOpen Access
What have We Learned from Deep Representations for Action Recognition?
2018· 23 cited
What have we learned from deep representations for action recognition?
arXiv (Cornell University)·2018· 30 citedOpen Access
Detect to Track and Track to Detect
2017· 57 citedOpen Access
Spatiotemporal Multiplier Networks for Video Action Recognition
2017· 693 cited
Temporal Residual Networks for Dynamic Scene Recognition
2017· 87 cited
Radiometry Propagation to Large 3D Point Clouds from Sparsely Sampled Ground Truth
Lecture notes in computer science·2017
Spatiotemporal Residual Networks for Video Action Recognition
arXiv (Cornell University)·2016· 494 citedOpen Access
Spatiotemporal Residual Networks for Video Action Recognition
arXiv (Cornell University)·2016· 184 citedOpen Access
Convolutional Two-Stream Network Fusion for Video Action Recognition
2016· 2.7k cited
The 3D-PITOTI Project with a Focus on Multi-Scale 3D Reconstruction using Semi-Autonomous UAVs
2016
Convolutional Two-Stream Network Fusion for Video Action Recognition
arXiv (Cornell University)·2016· 371 citedOpen Access
Dynamic Scene Recognition with Complementary Spatiotemporal Features
IEEE Transactions on Pattern Analysis and Machine Intelligence·2016· 29 cited
page 1 of 14Next →

Frequent Co-authors

Christoph Feichtenhofer(13), Richard P. Wildes(9), Andrew Zisserman(8), Andreas Opelt(6), Lucas Paletta(5), Horst Bischof(4), Miguel Ribo(4), Manfred Prantl(4), Peter Lang(4), Aleš Leonardis(3), Oliver Findl(3), Wolf Buehl(3), Hannes Siegl(3), Hermann Borotschnig(3), Harald Ganster(3), Michael Fussenegger(2), Peter Auer(2), Gerald Schweighofer(2), Stefan Bernögger(2), Rupert Menapace(2)