← Search

Matthias Kummerer

2 accepted papers

2018

Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics

ECCV 2018poster

Dozens of new models on fixation prediction are published every year and compared on open benchmarks such as MIT300 and LSUN. However, progress in the field can be difficult to judge because models are compared using a variety of inconsistent metrics. Here we show that no single saliency map can per…

2017

Understanding Low- and High-Level Contributions to Fixation Prediction

ICCV 2017poster

Understanding where people look in images is an important problem in computer vision. Despite significant research, it remains unclear to what extent human fixations can be predicted by low-level (contrast) compared to high-level (presence of objects) image features. Here we address this problem by…

Cited by 374PDFScholar