no code implementations • 8 Sep 2023 • Hannes Fassold
Manifold learning is an emerging research domain of machine learning.
no code implementations • 28 Aug 2023 • Hannes Fassold
The standard recipe applied in transfer learning is to finetune a pretrained model on the task-specific dataset with different hyperparameter settings and pick the model with the highest accuracy on the validation dataset.
no code implementations • 4 Apr 2023 • Hannes Fassold, Karlheinz Gutjahr, Anna Weber, Roland Perko
Monitoring the movement and actions of humans in video in real-time is an important task.
no code implementations • 7 Jul 2022 • Gabriele Lagani, Claudio Gennaro, Hannes Fassold, Giuseppe Amato
Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop).
no code implementations • 19 Apr 2022 • Hannes Fassold
A good optical flow estimation is crucial in many video analysis and restoration algorithms employed in application fields like media industry, industrial inspection and automotive.
no code implementations • 3 Mar 2022 • Hannes Fassold
We propose AdaFamily, a novel method for training deep neural networks.
1 code implementation • 25 Oct 2021 • Hannes Fassold
In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming.
no code implementations • 25 Oct 2021 • Hannes Fassold
We present a novel method for detecting speaking persons in video, by extracting facial landmarks with a neural network and analysing these landmarks statistically over time
no code implementations • 1 Aug 2021 • Hannes Fassold, Antonis Karakottas, Dorothea Tsatsou, Dimitrios Zarpalas, Barnabas Takacs, Christian Fuhrhop, Angelo Manfredi, Nicolas Patz, Simona Tonoli, Iana Dulskaia
Spherical 360{\deg} video is a novel media format, rapidly becoming adopted in media production and consumption of immersive media.
no code implementations • 2 Sep 2020 • Hannes Fassold
We describe our method for automatic generation of a visually interesting camera path (automatic cinematography)from a 360 video.
no code implementations • 14 Oct 2019 • Hannes Fassold, Ridouane Ghermi
The automatic detection and tracking of general objects (like persons, animals or cars), text and logos in a video is crucial for many video understanding tasks, and usually real-time processing as required.
no code implementations • 22 Jul 2019 • Hannes Fassold
Omnidirectional (360{\deg}) video has got quite popular because it provides a highly immersive viewing experience.