Search Results for author: Junaid Ahmed Ghauri

Found 4 papers, 4 papers with code

Classification of Visualization Types and Perspectives in Patents

1 code implementation19 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.

Classification Retrieval

Unsupervised Video Summarization via Multi-source Features

1 code implementation26 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.

Unsupervised Video Summarization

Supervised Video Summarization via Multiple Feature Sets with Parallel Attention

2 code implementations23 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.

Automated Feature Engineering Multimodal Deep Learning +1

Classification of Important Segments in Educational Videos using Multimodal Features

1 code implementation26 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.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.