Convolutional Two-Stream Network Fusion for Video Action Recognition
- Christoph Feichtenhofer, A. Pinz, Andrew Zisserman
- Computer ScienceComputer Vision and Pattern Recognition
- 22 April 2016
A new ConvNet architecture for spatiotemporal fusion of video snippets is proposed, and its performance on standard benchmarks where this architecture achieves state-of-the-art results is evaluated.
Generic object recognition with boosting
- A. Opelt, A. Pinz, M. Fussenegger, P. Auer
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 March 2006
This paper presents a complete framework that starts with the extraction of various local regions of either discontinuity or homogeneity, and uses Boosting to learn a subset of feature vectors (weak hypotheses) and to combine them into one final hypothesis for each visual category.
Spatiotemporal Residual Networks for Video Action Recognition
- Christoph Feichtenhofer, A. Pinz, R. Wildes
- Computer ScienceNIPS
- 7 November 2016
The novel spatiotemporal ResNet is introduced and evaluated using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.
Detect to Track and Track to Detect
- Christoph Feichtenhofer, A. Pinz, Andrew Zisserman
- Computer ScienceIEEE International Conference on Computer Vision
- 11 October 2017
This paper sets up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression, and introduces correlation features that represent object co-occurrences across time to aid the ConvNet during tracking.
Weak Hypotheses and Boosting for Generic Object Detection and Recognition
- A. Opelt, M. Fussenegger, A. Pinz, P. Auer
- Computer ScienceEuropean Conference on Computer Vision
- 11 May 2004
The first stage of a new learning system for object detection and recognition using Boosting as the underlying learning technique and the inclusion of features from segmented re- gions and even spatial relationships leads us a significant step towards generic object recognition.
Spatiotemporal Multiplier Networks for Video Action Recognition
- Christoph Feichtenhofer, A. Pinz, R. Wildes
- Computer ScienceComputer Vision and Pattern Recognition
- 1 July 2017
A general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features that combines the appearance and motion pathways of a two-stream architecture by motion gating and is trained end-to-end.
Robust Pose Estimation from a Planar Target
- G. Schweighofer, A. Pinz
- MathematicsIEEE Transactions on Pattern Analysis and Machine…
- 1 December 2006
It is shown that pose ambiguities - two distinct local minima of the according error function - exist even for cases with wide angle lenses and close range targets, and a new algorithm for unique and robust pose estimation from a planar target is developed.
A Boundary-Fragment-Model for Object Detection
- A. Opelt, A. Pinz, Andrew Zisserman
- Computer ScienceEuropean Conference on Computer Vision
- 7 May 2006
The BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance, and to achieve this with less supervision (such as the number of training images).
Multispectral classification of Landsat-images using neural networks
- H. Bischof, W. Schneider, A. Pinz
- Mathematics, Environmental ScienceIEEE Transactions on Geoscience and Remote…
- 1 May 1992
Three-layer back-propagation networks for classification of Landsat TM data on a pixel-by-pixel basis is reported and it is shown that the neural network is able to perform better than the maximum likelihood classifier.
Automated Melanoma Recognition
- H. Ganster, A. Pinz, Reinhard Röhrer, E. Wildling, M. Binder, H. Kittler
- Computer ScienceIEEE Trans. Medical Imaging
- 1 March 2001
A system for the computerized analysis of images obtained from ELM to enhance the early recognition of malignant melanoma and delivers a sensitivity of 87% with a specificity of 92%.
...
...