Paper on image-clutter classification accepted at EUSIPCO-2025
A paper entitled “Classification of indoor clutter from images: Application to hoarding assessment,” co-authored by Zhenghao Sun, Jordana Muroff and Janusz Konrad is scheduled to be presented at the 33rd European Signal Processing Conference (EUSIPCO-2025) in Palermo, Italy, Sept. 8-12, 2025. This work is an extension of an earlier ResNet-18 based classifier by adopting the Visual Transformer to rate indoor clutter from images with up to 7% gains of classification accuracy.