Zobrazeno 1 - 10
of 1 128
pro vyhledávání: '"Fassold A"'
Autor:
Fassold, Hannes
Deploying Large Language Models (LLMs) on mobile devices makes all the capabilities of natural language processing available on the device. An important use case of LLMs is question answering, which can provide accurate and contextually relevant answ
Externí odkaz:
http://arxiv.org/abs/2404.15851
Autor:
Fassold, Hannes
Manifold learning is an emerging research domain of machine learning. In this work, we give an introduction into manifold learning and how it is employed for important application fields in multimedia.
Comment: Accepted for ICVSP 2023 conference
Comment: Accepted for ICVSP 2023 conference
Externí odkaz:
http://arxiv.org/abs/2310.12986
Autor:
Fassold, Hannes
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. Unfortunately, this leads t
Externí odkaz:
http://arxiv.org/abs/2309.08610
Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize fo
Externí odkaz:
http://arxiv.org/abs/2304.01567
Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training samples to ach
Externí odkaz:
http://arxiv.org/abs/2207.03172
Autor:
Fassold, Hannes
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. In this work, we investigate how well optical flow algorithms perfor
Externí odkaz:
http://arxiv.org/abs/2204.08791
Autor:
Fassold, Hannes
We propose AdaFamily, a novel method for training deep neural networks. It is a family of adaptive gradient methods and can be interpreted as sort of a blend of the optimization algorithms Adam, AdaBelief and AdaMomentum. We perform experiments on st
Externí odkaz:
http://arxiv.org/abs/2203.01603
Autor:
Lagani, Gabriele a, ⁎, Falchi, Fabrizio a, Gennaro, Claudio a, Fassold, Hannes b, Amato, Giuseppe a
Publikováno v:
In Neurocomputing 28 August 2024 595
Autor:
Fassold, Hannes
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
Comment: Accepted for MMSP 2021
Comment: Accepted for MMSP 2021
Externí odkaz:
http://arxiv.org/abs/2110.13806
Autor:
Fassold, Hannes
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. This strategy makes sure that the optimizer puts its focus in the later training
Externí odkaz:
http://arxiv.org/abs/2110.13058