1 code implementation • 19 Jul 2023 • Junaid Ahmed Ghauri, Eric Müller-Budack, Ralph Ewerth
In this paper, we adopt state-of-the-art deep learning methods for the classification of visualization types and perspectives in patent images.
1 code implementation • 26 May 2021 • Hussain Kanafani, Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth
Our evaluation shows that we obtain state-of-the-art results on both datasets, while also highlighting the shortcomings of previous work with regard to the evaluation methodology.
2 code implementations • 23 Apr 2021 • Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth
The proposed architecture utilizes an attention mechanism before fusing motion features and features representing the (static) visual content, i. e., derived from an image classification model.
Ranked #1 on Supervised Video Summarization on TvSum
1 code implementation • 26 Oct 2020 • Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth
Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.