Matthias Kümmerer
Matthias Kümmerer
Tübingen AI Center, University Tuebingen
Email verificata su - Home page
Citata da
Citata da
SciPy 1.0: fundamental algorithms for scientific computing in Python
P Virtanen, R Gommers, TE Oliphant, M Haberland, T Reddy, ...
Nature methods 17 (3), 261-272, 2020
Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet
M Kümmerer, L Theis, M Bethge
arXiv preprint arXiv:1411.1045, 2014
Understanding low-and high-level contributions to fixation prediction
M Kummerer, TSA Wallis, LA Gatys, M Bethge
Proceedings of the IEEE international conference on computer vision, 4789-4798, 2017
DeepGaze II: Reading fixations from deep features trained on object recognition
M Kümmerer, TSA Wallis, M Bethge
arXiv preprint arXiv:1610.01563, 2016
Information-theoretic model comparison unifies saliency metrics
M Kümmerer, TSA Wallis, M Bethge
Proceedings of the National Academy of Sciences 112 (52), 16054-16059, 2015
Accurate, reliable and fast robustness evaluation
W Brendel, J Rauber, M Kümmerer, I Ustyuzhaninov, M Bethge
Advances in neural information processing systems 32, 2019
Saliency benchmarking made easy: Separating models, maps and metrics
M Kummerer, TSA Wallis, M Bethge
Proceedings of the European Conference on Computer Vision (ECCV), 770-787, 2018
DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling
A Linardos, M Kümmerer, O Press, M Bethge
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
DeepGaze III: Modeling free-viewing human scanpaths with deep learning
M Kümmerer, M Bethge, TSA Wallis
Journal of Vision 22 (5), 7-7, 2022
Mit/tübingen saliency benchmark
M Kümmerer, Z Bylinskii, T Judd, A Borji, L Itti, F Durand, A Oliva, ...
Tübingen saliency benchmark, 2020
State-of-the-art in human scanpath prediction
M Kümmerer, M Bethge
arXiv preprint arXiv:2102.12239, 2021
Attention to comics: Cognitive processing during the reading of graphic literature
J Laubrock, S Hohenstein, M Kümmerer
Empirical comics research, 239-263, 2018
Meaning maps and saliency models based on deep convolutional neural networks are insensitive to image meaning when predicting human fixations
MA Pedziwiatr, M Kümmerer, TSA Wallis, M Bethge, C Teufel
Cognition 206, 104465, 2021
Guiding human gaze with convolutional neural networks
LA Gatys, M Kümmerer, TSA Wallis, M Bethge
arXiv preprint arXiv:1712.06492, 2017
Deepgaze ii: Predicting fixations from deep features over time and tasks
M Kümmerer, T Wallis, M Bethge
Journal of Vision 17 (10), 1147-1147, 2017
Unsupervised object learning via common fate
M Tangemann, S Schneider, J Von Kügelgen, F Locatello, P Gehler, ...
arXiv preprint arXiv:2110.06562, 2021
Rdumb: A simple approach that questions our progress in continual test-time adaptation
O Press, S Schneider, M Kümmerer, M Bethge
Advances in Neural Information Processing Systems 36, 2024
Measuring the importance of temporal features in video saliency
M Tangemann, M Kümmerer, TSA Wallis, M Bethge
Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020
How close are we to understanding image-based saliency?
M Kümmerer, T Wallis, M Bethge
arXiv preprint arXiv:1409.7686, 2014
DeepGaze III: Using deep learning to probe interactions between scene content and scanpath history in fixation selection
M Kümmerer, TSA Wallis, M Bethge
2019 Conference on Cognitive Computational Neuroscience, 2019
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20