Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a universal-domain dataset, its restricted accessibility and limited range of evaluation use cases challenge its role as the sole resource. Therefore, we introduce BirdSet, a large-scale benchmark data set for audio classification focusing on avian bioacoustics. BirdSet surpasses AudioSet with over 6,800 recording hours ($\uparrow17\%$) from nearly 10,000 classes ($\uparrow18\times$) for training and more than 400 hours ($\uparrow7\times$) across eight strongly labeled evaluation datasets. It serves as a versatile resource for use cases such as multi-label classification, covariate shift or self-supervised learning. We benchmark six well-known DL models in multi-label classification across three distinct training scenarios and outline further evaluation use cases in audio classification. We host our dataset on Hugging Face for easy accessibility and offer an extensive codebase to reproduce our results.

Predicting the performance of individual components of information retrieval systems, in particular the complex interactions between those components, is still challenging. Therefore, professionals are needed for the implementation and configuration of retrieval systems and retrieval components. Our web-based application, called Xtrieval Web Lab, enables newcomers and learners to gain practical knowledge about the information retrieval process. They can arrange a multitude of components of retrieval systems and evaluate them with real world data without utilizing a programming language. Game mechanics guide the learners in their discovery process and motivate them.

We propose an adaptive system, which automates the workflow of combining low resolution (S)VHS archive material and today's high resolution footage in one video, to assist professional video editors. During this process, old footage of an aspect ratio of 4:3 needs to be cropped in order to use the Full-HD 16:9 screen space, whilst the overall aesthetics and content of the source video should be preserved. If done manually, this is an extensive and time consuming task. The challenge is to automatically adjust the framing according to the depicted content. Our approach aims at an automated detection of the most interesting regions of the source footage for adaptive cropping based on various visual features of representative key frames.