Multimodal Input-Dependent Object Query Initialization for LiDAR-Camera 3D Object Detection with Transformers

3D object detection models that exploit both LiDAR and camera sensor features are top performers in large-scale autonomous driving benchmarks. A transformer is a popular network architecture used for this task, in which so-called object queries act as candidate objects. Initializing these object queries based on current sensor inputs leads to...

Image Search Engine for Digital History: A deep learning approach

This research investigates and describes an image search engine for digital history using deep learning technologies. It is part of the Engineering Historical Memory research, contributing to a multilingual and transcultural approach to decode-encode the treasure of human experience and transmit it to the next generation of world citizens. The...