5 papers
Doppio: A Dataset for Contactless Weight Estimation of Falling Particles
Simon Kiefhaber, Jan-Martin O. Steitz, Julia Grabinski +5
Measuring the mass of powder, including falling particles, is a common task in industrial applications. While scales are effective for static measurements, many applications requir…
Adapters Strike Back
Jan-Martin O. Steitz, Stefan Roth
Adapters provide an efficient and lightweight mechanism for adapting trained transformer models to a variety of different tasks. However, they have often been found to be outperfor…
TxT: Crossmodal End-to-End Learning with Transformers
Jan-Martin O. Steitz, Jonas Pfeiffer, Iryna Gurevych +1
Reasoning over multiple modalities, e.g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains. Despite the widespread success of end-to-end…
xGQA: Cross-Lingual Visual Question Answering
Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath +4
Recent advances in multimodal vision and language modeling have predominantly focused on the English language, mostly due to the lack of multilingual multimodal datasets to steer m…
Multi-view X-ray R-CNN
Jan-Martin O. Steitz, Faraz Saeedan, Stefan Roth
Motivated by the detection of prohibited objects in carry-on luggage as a part of avionic security screening, we develop a CNN-based object detection approach for multi-view X-ray…