% generated by bibtexbrowser % % Encoding: UTF-8 @inproceedings{Golkov-et-al-miccai2015-qDL, author = {V. Golkov and A. Dosovitskiy and P. Sämann and J. I. Sperl and T. Sprenger and M. Czisch and M. I. Menzel and P. A. Gómez and A. Haase and T. Brox and D. Cremers}, title = {{q-Space} Deep Learning for Twelve-Fold Shorter and Model-Free Diffusion {MRI} Scans}, booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)}, month = {oct}, year = {2015}, address = {Munich, Germany}, keywords = {magnetic resonance imaging, diffusion MRI, deep learning, q-space deep learning, machine learning, model-free diffusion MRI, segmentation, medical imaging, deep learning}, } @inproceedings{flownet-iccv-15, author = {A. Dosovitskiy and P. Fischer and E. Ilg and P. Haeusser and C. Hazirbas and V. Golkov and P. van der Smagt and D. Cremers and T. Brox}, title = {{FlowNet: Learning Optical Flow with Convolutional Networks}}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, keywords = {deep learning, optical-flow}, year = {2015}, month = {dec}, doi = {10.1109/ICCV.2015.316}, } @inproceedings{stark-gcpr15, author = {F. Stark and C. Hazirbas and R. Triebel and D. Cremers}, title = {CAPTCHA Recognition with Active Deep Learning}, booktitle = {GCPR Workshop on New Challenges in Neural Computation}, year = {2015}, address = {Aachen, Germany}, keywords = {deep learning}, } @inproceedings{Golkov-et-al-nips2016, author = {V. Golkov and M. J. Skwark and A. Golkov and A. Dosovitskiy and T. Brox and J. Meiler and D. Cremers}, title = {Protein Contact Prediction from Amino Acid Co-Evolution Using Convolutional Networks for Graph-Valued Images}, booktitle = {Annual Conference on Neural Information Processing Systems (NIPS)}, month = {dec}, year = {2016}, address = {Barcelona, Spain}, keywords = {computational structural biology, deep learning, convolutional networks, graph-valued images, deep learning, biology}, award = {Oral Presentation (acceptance rate: under 2%)}, } @article{Golkov-et-al-tmi2016, author = {V. Golkov and A. Dosovitskiy and J. I. Sperl and M. I. Menzel and M. Czisch and P. Sämann and T. Brox and D. Cremers}, title = {{q-Space} Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion {MRI} Scans}, year = {2016}, journal = {IEEE Transactions on Medical Imaging}, volume = {35}, issue = {5}, keywords = {magnetic resonance imaging, diffusion MRI, deep learning, q-space deep learning, machine learning, model-free diffusion MRI, segmentation, medical imaging, deep learning}, issuetitle = {Special Issue on Deep Learning}, award = {Special Issue on Deep Learning}, } @inproceedings{hazirbasma2016fusenet, author = {C. Hazirbas and L. Ma and C. Domokos and D. Cremers}, title = {{FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture}}, booktitle = {Asian Conference on Computer Vision}, year = {2016}, month = {november}, keywords = {segmentation, deep learning}, } @inproceedings{walch16spatialstms, author = {F. Walch and C. Hazirbas and L. Leal-Taixé and T. Sattler and S. Hilsenbeck and D. Cremers}, title = {Image-based localization using LSTMs for structured feature correlation}, month = {October}, year = {2017}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, keywords = {deep learning}, } @inproceedings{sahand2016drive, author = {S. Sharifzadeh and I. Chiotellis and R. Triebel and D. Cremers}, title = {Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks}, year = {2016}, publisher = {NIPS Workshops}, month = {December}, keywords = {autonomous driving, reinforcement learning, artificial intelligence, DQN, deep learning}, } @inproceedings{Peeken-et-al-2017, author = {J.C. Peeken and C. Knie and V. Golkov and K. Kessel and F. Pasa and Q. Khan and M. Seroglazov and J. Kukačka and T. Goldberg and L. Richter and J. Reeb and B. Rost and F. Pfeiffer and D. Cremers and F. Nüsslin and S.E. Combs}, title = {Establishment of an interdisciplinary workflow of machine learning-based Radiomics in sarcoma patients}, year = {2017}, booktitle = {23. Jahrestagung der Deutschen Gesellschaft für Radioonkologie (DEGRO)}, keywords = {deep learning, medical imaging}, } @inproceedings{Golkov-et-al-arxiv2017-function3d, author = {V. Golkov and M. J. Skwark and A. Mirchev and G. Dikov and A. R. Geanes and J. Mendenhall and J. Meiler and D. Cremers}, title = {{3D} Deep Learning for Biological Function Prediction from Physical Fields}, booktitle = {International Conference on 3D Vision (3DV)}, year = {2020}, journal = {arXiv preprint arXiv:1704.04039}, eprint = {1704.04039}, eprinttype = {arXiv}, keywords = {computational structural biology, deep learning, convolutional networks, protein function, QSAR, deep learning, biology}, } @inproceedings{haeusser-cvpr17, author = {P. Haeusser and A. Mordvintsev and D. Cremers}, title = {Learning by Association - A versatile semi-supervised training method for neural networks}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, keywords = {semi-supervised, deep learning, neural networks, association, associative_learning}, titleurl = {haeusser_cvpr_17.pdf}, } @inproceedings{meinhardt17learning, author = {T. Meinhardt and M. Moeller and C. Hazirbas and D. Cremers}, title = {Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems}, month = {October}, year = {2017}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, keywords = {deep learning}, } @inproceedings{hazirbas18ddff, author = {C. Hazirbas and S. G. Soyer and M. C. Staab and L. Leal-Taixé and D. Cremers}, title = {{Deep Depth From Focus}}, year = {2018}, month = {December}, booktitle = {Asian Conference on Computer Vision (ACCV)}, keywords = {deep learning}, } @inproceedings{osvosCVPR2017, address = {Honolulu, USA}, author = {S. Caelles and K.-K. Maninis and J. Pont-Tuset and L. Leal-Taixé and D. Cremers and L. V Gool}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, title = {{One-Shot Video Object Segmentation}}, year = {2017}, keywords = {deep learning}, } @inproceedings{kurach2017, author = {K. Kurach and S. Gelly and M. Jastrzebski and P. Haeusser and O. Teytaud and D. Vincent and O. Bousquet}, title = {Better Text Understanding Through Image-To-Text Transfer}, booktitle = {arxiv:1705.08386}, arxiv = {arxiv:1705.08386}, year = {2017}, month = {May}, keywords = {Multimodal, Text, Embeddings, deep learning, associative_learning}, titleurl = {kurach2017.pdf}, } @inproceedings{haeusser_iccv_17, author = {P. Haeusser and T. Frerix and A. Mordvintsev and D. Cremers}, title = {Associative Domain Adaptation}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, year = {2017}, keywords = {semi-supervised, deep learning, neural networks, association, domain adaptation, associative_learning}, titleurl = {haeusser_iccv_17.pdf}, } @inproceedings{brahimi2022arxiv, title = {{SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering}}, author = {M Brahimi and B Haefner and T Yenamandra and B Goldluecke and D Cremers}, booktitle = {{IEEE Winter Conference on Applications of Computer Vision (WACV)}}, month = {January}, address = {Hawaii, USA}, year = {2024}, eprint = {2212.04968}, eprinttype = {arXiv}, eprintclass = {cs.CV}, titleurl = {brahimi2022arxiv.pdf}, keywords = {d-reconstruction,photometry,deep learning,geometry processing}, } @article{Kukacka-et-al-2017, author = {J. Kukačka and V. Golkov and D. Cremers}, title = {Regularization for Deep Learning: A Taxonomy}, year = {2017}, journal = {arXiv preprint arXiv:1710.10686}, eprint = {1710.10686}, eprinttype = {arXiv}, keywords = {deep learning, neural networks, regularization, data augmentation, network architecture, loss function, dropout, residual learning, optimization}, } @inproceedings{Vasilev-et-al-2018, author = {A. Vasilev and V. Golkov and M. Meissner and I. Lipp and E. Sgarlata and V. Tomassini and D. K. Jones and D. Cremers}, title = {{q}-{S}pace Novelty Detection with Variational Autoencoders}, year = {2019}, booktitle = {{MICCAI} 2019 International Workshop on Computational Diffusion {MRI}}, eprint = {1806.02997}, eprinttype = {arXiv}, keywords = {deep learning, novelty detection, anomaly detection, neural networks, medical imaging, magnetic resonance imaging, diffusion MRI}, award = {Oral Presentation}, } @inproceedings{Swazinna-et-al-ismrm2019, author = {P. Swazinna and V. Golkov and I. Lipp and E. Sgarlata and V. Tomassini and D. K. Jones and D. Cremers}, title = {Negative-Unlabeled Learning for Diffusion {MRI}}, year = {2019}, booktitle = {International Society for Magnetic Resonance in Medicine ({ISMRM}) Annual Meeting}, keywords = {deep learning, machine learning, medical imaging, magnetic resonance imaging, diffusion MRI, weakly-supervised learning, positive-unlabeled learning, semi-supervised learning, localization}, } @inproceedings{Golkov-et-al-ismrm2018-global, author = {V. Golkov and P. Swazinna and M. M. Schmitt and Q. A. Khan and C. M. W. Tax and M. Serahlazau and F. Pasa and F. Pfeiffer and G. J. Biessels and A. Leemans and D. Cremers}, title = {{q-Space} Deep Learning for {A}lzheimer's Disease Diagnosis: Global Prediction and Weakly-Supervised Localization}, year = {2018}, booktitle = {International Society for Magnetic Resonance in Medicine ({ISMRM}) Annual Meeting}, keywords = {deep learning, machine learning, medical imaging, magnetic resonance imaging, diffusion MRI, weakly-supervised learning, localization}, } @article{Do-et-al-2018-pre-miRNA, author = {B. T. Do and V. Golkov and G. E. Gürel and D. Cremers}, title = {Precursor {microRNA} Identification Using Deep Convolutional Neural Networks}, year = {2018}, % howpublished = {Preprint}, journal = {bioRxiv preprint 414656}, keywords = {precursor microRNA, pre-miRNA, miRNA, deep learning, neural networks, machine learning, biology, gene regulation}, } @article{Golkov-et-al-2020-ROC, author = {V. Golkov and A. Becker and D. T. Plop and D. Čuturilo and N. Davoudi and J. Mendenhall and R. Moretti and J. Meiler and D. Cremers}, title = {Deep Learning for Virtual Screening: Five Reasons to Use {ROC} Cost Functions}, year = {2020}, journal = {arXiv preprint arXiv:2007.07029}, eprint = {2007.07029}, eprinttype = {arXiv}, keywords = {deep learning, drug discovery, virtual screening, neural networks, machine learning, QSAR, classification, receiver operating characteristic, biology, chemistry}, } @article{Aljalbout-et-al-2018, author = {E. Aljalbout and V. Golkov and Y. Siddiqui and M. Strobel and D. Cremers}, title = {Clustering with Deep Learning: Taxonomy and New Methods}, year = {2018}, journal = {arXiv preprint arXiv:1801.07648}, eprint = {1801.07648}, eprinttype = {arXiv}, keywords = {deep learning, clustering, cluster analysis, neural networks}, } @inproceedings{haeusser18associative, author = {P. Haeusser and J. Plapp and V. Golkov and E. Aljalbout and D. Cremers}, title = {Associative Deep Clustering - Training a Classification Network with no Labels}, booktitle = {Proc. of the German Conference on Pattern Recognition (GCPR)}, year = {2018}, month = {October}, titleurl = {haeusser18associative.pdf}, keywords = {Clustering, Embeddings, deep learning, associative_learning}, } @article{mayer18synthetic, author = {N Mayer and E Ilg and P Fischer and C Hazirbas and D Cremers and A Dosovitskiy and T Brox}, title = {What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?}, booktitle = {International Journal of Computer Vision}, volume = {41}, number = {8}, pages = {1797--1812}, year = {2018}, month = {September}, eprint = {arXiv:1801.06397}, keywords = {deep learning, optical-flow}, } @inproceedings{yang2018dvso, author = {N. Yang and R. Wang and J. Stueckler and D. Cremers}, title = {Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry}, booktitle = {European Conference on Computer Vision (ECCV)}, year = {2018}, month = {September}, award = {Oral Presentation}, keywords = {dso, dvso, deep learning, monocular depth estimation, semi-supervised learning, slam, visual odometry, vslam}, } @inproceedings{wenzel18corl, author = {P. Wenzel and Q. Khan and D. Cremers and L. Leal-Taixé}, booktitle = {Conference on Robot Learning ({CoRL})}, title = {Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using {GANs}}, year = {2018}, keywords = {deep learning}, } @article{Pasa-et-al-2019, author = {F. Pasa and V. Golkov and F. Pfeiffer and D. Cremers and D. Pfeiffer}, title = {Efficient Deep Network Architectures for Fast Chest {X}-Ray Tuberculosis Screening and Visualization}, journal = {Scientific Reports}, year = {2019}, volume = {9}, number = {1}, pages = {6268}, issn = {2045-2322}, doi = {10.1038/s41598-019-42557-4}, url = {https://www.nature.com/articles/s41598-019-42557-4}, keywords = {medical imaging, deep learning}, } @article{Schuchardt-et-al-2019, author = {J. Schuchardt and V. Golkov and D. Cremers}, title = {Learning to Evolve}, year = {2019}, journal = {arXiv preprint arXiv:1905.03389}, eprint = {1905.03389}, eprinttype = {arXiv}, keywords = {evolutionary algorithms, evolutionary computation, genetic algorithms, deep learning, neural networks, reinforcement learning}, } @article{gn-net-2020, author = {L. von Stumberg and P. Wenzel and Q. Khan and D. Cremers}, title = {{GN-Net}: The Gauss-Newton Loss for Multi-Weather Relocalization}, journal = {{IEEE} Robotics and Automation Letters ({RA-L})}, year = {2020}, volume = {5}, number = {2}, pages = {890-897}, keywords = {gn-net, vslam, deep learning}, } @inproceedings{control-across-weathers-19, author = {Q. Khan and P. Wenzel and D. Cremers and L. Leal-Taixé}, title = {Towards Generalizing Sensorimotor Control Across Weather Conditions}, booktitle = {Proceedings of the {IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})}, year = {2019}, keywords = {deep learning}, } @article{Della-Libera-et-al-2019, author = {L. Della Libera and V. Golkov and Y. Zhu and A. Mielke and D. Cremers}, title = {Deep Learning for {2D and 3D} Rotatable Data: An Overview of Methods}, year = {2019}, journal = {arXiv preprint arXiv:1910.14594}, eprint = {1910.14594}, eprinttype = {arXiv}, keywords = {deep learning, neural networks, 2D, 3D, rotations, invariance, equivariance}, } @inproceedings{yang20d3vo, author = {N. Yang and L. von Stumberg and R. Wang and D. Cremers}, title = {D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, eprint = {2003.01060}, eprinttype = {arXiv}, eprintclass = {cs.CV}, award = {Oral Presentation}, keywords = {dso,dvso, deep learning, monocular depth estimation, semi-supervised learning, slam, visual odometry,d3vo, vslam}, } @inproceedings{liu2020effective, title = {Effective Version Space Reduction for Convolutional Neural Networks}, author = {J Liu and I Chiotellis and R Triebel and D Cremers}, journal = {arXiv preprint arXiv:2006.12456}, year = {2020}, booktitle = {European Conference on Machine Learning and Data Mining (ECML-PKDD)}, keywords = {deep learning, active learning, convolutional neural networks}, } @inproceedings{wenzel2020fourseasons, title = {{4Seasons}: A Cross-Season Dataset for Multi-Weather {SLAM} in Autonomous Driving}, author = {P. Wenzel and R. Wang and N. Yang and Q. Cheng and Q. Khan and L. von Stumberg and N. Zeller and D. Cremers}, booktitle = {Proceedings of the German Conference on Pattern Recognition ({GCPR})}, year = {2020}, keywords = {vslam,4seasons, deep learning}, } @article{fabbro2020, title = {Speech Synthesis and Control Using Differentiable {DSP}}, author = {G Fabbro and V Golkov and T Kemp and D Cremers}, year = {2020}, journal = {arXiv preprint arXiv:2010.15084}, eprint = {2010.15084}, eprinttype = {arXiv}, primaryclass = {eess.AS}, keywords = {speech synthesis, neural vocoder, text-to-speech, digital signal processing, neural networks, deep learning}, } @inproceedings{lm-reloc-2020, author = {L. von Stumberg and P. Wenzel and N. Yang and D. Cremers}, title = {LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization}, booktitle = {International Conference on 3D Vision (3DV)}, year = {2020}, keywords = {lm-reloc, slam, structure-from-motion, direct method, mapping, vslam, deep learning}, } @inproceedings{wimbauer2020monorec, title = {MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera}, author = {F. Wimbauer and N. Yang and L. von Stumberg and N. Zeller and D Cremers}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, eprint = {2011.11814}, eprinttype = {arXiv}, eprintclass = {cs.CV}, keywords = {monorec, dvso, d3vo, mvs, deep learning, SLAM, vslam, reconstruction}, } @article{chiotellis2020noge, title = {Neural Online Graph Exploration}, author = {I Chiotellis and D Cremers}, year = {2020}, journal = {arXiv preprint arXiv:2012.03345}, eprint = {2012.03345}, archiveprefix = {arXiv}, primaryclass = {cs.LG}, keywords = {deep learning, exploration, graph neural networks, learning on graphs, artificial intelligence}, } @article{mueller2021, title = {Rotation-Equivariant Deep Learning for Diffusion {MRI}}, author = {P. Müller and V. Golkov and V. Tomassini and D. Cremers}, year = {2021}, journal = {arXiv preprint}, eprint = {2102.06942}, eprinttype = {arXiv}, primaryclass = {cs.CV}, keywords = {deep learning, diffusion MRI, equivariant deep learning, rotation-equivariance, magnetic resonance imaging, multiple sclerosis, image segmentation, medical imaging}, } @inproceedings{Mueller2021-ISMRM, title = {Rotation-Equivariant Deep Learning for Diffusion {MRI} (short version)}, author = {P. Müller and V. Golkov and V. Tomassini and D. Cremers}, year = {2021}, booktitle = {International Society for Magnetic Resonance in Medicine ({ISMRM}) Annual Meeting}, keywords = {deep learning, diffusion MRI, equivariant deep learning, rotation-equivariance, magnetic resonance imaging, multiple sclerosis, image segmentation, medical imaging}, } @inproceedings{selfcontrol-aistats-2021, author = {Q. Khan and P. Wenzel and D. Cremers}, title = {Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry}, booktitle = {International Conference on Artificial Intelligence and Statistics ({AISTATS})}, year = {2021}, keywords = {deep learning}, } @inproceedings{yan2021soe, author = {Y. Xia and Y. Xu and S. Li and R. Wang and J. Du and D. Cremers and U. Stilla}, title = {SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, award = {Oral Presentation}, keywords = {SLAM, localization, re-localization, 3D learning, dh3d, vslam, deep learning}, } @inproceedings{wenzel2021icra, author = {P. Wenzel and T. Schön and L. Leal-Taixé and D. Cremers}, title = {Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning}, keywords = {deep learning}, booktitle = {Proceedings of the {IEEE} International Conference on Robotics and Automation ({ICRA})}, year = {2021}, } @inproceedings{tomani2021falcon, author = {C Tomani and F Buettner}, title = {Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration}, booktitle = {InThirty-FifthAAAIConferenceonArtificialIntelligence(AAAI-2021)}, year = {2021}, eprint = {2012.10923}, eprinttype = {arXiv}, keywords = {deep learning}, } @inproceedings{tomani2021posthoc, author = {C Tomani and S Gruber and ME Erdem and D Cremers and F Buettner}, title = {Post-hoc Uncertainty Calibration for Domain Drift Scenarios}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, award = {Oral Presentation}, eprint = {2012.10988}, eprinttype = {arXiv}, keywords = {deep learning}, } @inproceedings{tomani2021pts, title = {Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration}, author = {C Tomani and D Cremers and F Buettner}, year = {2022}, booktitle = {European Conference on Computer Vision (ECCV)}, eprint = {2102.12182}, eprinttype = {arXiv}, keywords = {deep learning}, } @article{tomani2022challenger, title = {Challenger: Training with Attribution Maps}, author = {C Tomani and D Cremers}, year = {2022}, journal = {arXiv preprint}, eprint = {2205.15094}, eprinttype = {arXiv}, primaryclass = {cs.LG}, keywords = {deep learning}, } @inproceedings{tomani2023dac, title = {Beyond In-Domain Scenarios: Robust Density-Aware Calibration}, author = {C Tomani and F Waseda and Y Shen and D Cremers}, booktitle = {Proceedings of the 40th International Conference on Machine Learning (ICML)}, year = {2023}, eprint = {2302.05118}, eprinttype = {arXiv}, keywords = {deep learning}, } @article{tomani2023qualityaware, title = {Quality Control at Your Fingertips: Quality-Aware Translation Models}, author = {C Tomani and D Vilar and M Freitag and C Cherry and S Naskar and M Finkelstein and D Cremers}, year = {2023}, journal = {arXiv preprint}, eprint = {2310.06707}, eprinttype = {arXiv}, primaryclass = {cs.LG}, keywords = {deep learning}, } @article{tomani2024abstentionllms, title = {Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations}, author = {C Tomani and K Chaudhuri and I Evtimov and D Cremers and M Ibrahim}, year = {2024}, journal = {arXiv preprint}, eprint = {2404.10960}, eprinttype = {arXiv}, primaryclass = {cs.LG}, keywords = {deep learning}, } @article{mozes2021, title = {Scene Graph Generation for Better Image Captioning?}, author = {M. Mozes and M. Schmitt and V. Golkov and H. Schütze and D. Cremers}, year = {2021}, journal = {arXiv preprint}, eprint = {2109.11398}, eprinttype = {arXiv}, primaryclass = {cs.CV}, keywords = {deep learning, computer vision, natural language processing, image captioning, scene graphs, attention mechanism}, } @phdthesis{Golkov-PhDthesis, author = {V. Golkov}, title = {Deep learning and variational analysis for high-dimensional and geometric biomedical data}, school = {Department of Informatics, Technical University of Munich, Germany}, year = {2021}, topic = {deep learning, medical imaging, protein structure prediction, neural networks, machine learning, calculus of variations, diffusion MRI, magnetic resonance imaging}, keywords = {deep learning, medical imaging, protein structure prediction, neural networks, machine learning, calculus of variations, diffusion MRI, magnetic resonance imaging}, } @inproceedings{schnaus21bayesian, author = {D Schnaus and J Lee and R Triebel}, booktitle = {Bayesian Deep Learning NeurIPS 2021 Workshop}, year = {2021}, title = {Kronecker-Factored Optimal Curvature}, keywords = {deep learning, bayesian deep learning}, } @article{Brunner2022, author = {C. Brunner and A. Duensing and C. Schröder and M. Mittermair and V. Golkov and M. Pollanka and D. Cremers and R. Kienberger}, title = {Deep Learning in Attosecond Metrology}, journal = {Optics Express}, year = {2022}, keywords = {attosecond metrology, photoelectron spectroscopy, deep learning, physics, attosecond streak camera, streaking, Neural networks; Phase retrieval; Photoelectron spectra; Power spectra; Streak cameras; Time resolved spectroscopy}, volume = {30}, number = {9}, pages = {15669--15684}, publisher = {OSA}, url = {https://opg.optica.org/OE/abstract.cfm?uri=OE-30-9-15669}, doi = {10.1364/OE.452108}, award = {Editor's Pick}, } @inproceedings{pccontrol_2022, title = {Lateral Ego-Vehicle Control Without Supervision Using Point Clouds}, author = {F Müller and Q Khan and D Cremers}, booktitle = {Pattern Recognition and Artificial Intelligence}, publisher = {Springer International Publishing}, keywords = {deep learning}, pages = {477--488}, isbn = {978-3-031-09037-0}, year = {2022}, } @inproceedings{pathfinding_2022, title = {Biologically Inspired Neural Path Finding}, author = {L Hang and Q Khan and V Tresp and D Cremers}, booktitle = {Brain Informatics}, publisher = {Springer International Publishing}, keywords = {deep learning}, year = {2022}, } @inproceedings{ventriloquist_2022, title = {Ventriloquist-Net: Leveraging Speech Cues for Emotive Talking Head Generation}, author = {D Das and Q Khan and D Cremers}, booktitle = {IEEE International Conference on Image Processing}, keywords = {deep learning}, year = {2022}, } @inproceedings{wang2021epfgnn, author = {Y Wang and Y Shen and D Cremers}, title = {Explicit pairwise factorized graph neural network for semi-supervised node classification}, booktitle = {UAI}, year = {2021}, eprint = {2107.13059}, eprinttype = {arXiv}, eprintclass = {cs.LG}, keywords = {deep learning, graph neural network}, } @inproceedings{hsu2022gats, title = {What Makes Graph Neural Networks Miscalibrated?}, author = {HHH Hsu and Y Shen and C Tomani and D Cremers}, booktitle = {NeurIPS}, year = {2022}, eprint = {2210.06391}, eprinttype = {arXiv}, eprintclass = {cs.LG}, keywords = {deep learning, graph neural network, calibration}, } @inproceedings{shen2022dca, title = {Deep Combinatorial Aggregation}, author = {Y Shen and D Cremers}, booktitle = {NeurIPS}, year = {2022}, eprint = {2210.06436}, eprinttype = {arXiv}, eprintclass = {cs.LG}, keywords = {deep learning, uncertainty-aware learning}, } @inproceedings{hsu2022a, title = {A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs}, author = {HHH Hsu and Y Shen and D Cremers}, booktitle = {NeurIPS 2022 Workshop: New Frontiers in Graph Learning}, year = {2022}, eprint = {2210.15575}, eprinttype = {arXiv}, eprintclass = {cs.LG}, keywords = {deep learning, graph neural network, uncertainty estimation, calibration}, } @article{nndriving2023, title = {Learning vision based autonomous lateral vehicle control without supervision}, author = {Q Khan and I Sülö and M Öcal and D Cremers}, journal = {Applied Intelligence}, pages = {1--13}, year = {2023}, publisher = {Springer}, keywords = {intelligent driving, neural networks, deep learning}, } @inproceedings{wimbauer2023behind, title = {Behind the Scenes: Density Fields for Single View Reconstruction}, author = {F Wimbauer and N Yang and C Rupprecht and D Cremers}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, eprinttype = {arXiv}, eprint = {2301.07668}, eprintclass = {cs.CV}, keywords = {depth prediction, volumetric, nerf, mvs, deep learning, SLAM, vslam, reconstruction}, titleurl = {wimbauer2023behind.png}, } @article{Wimmer2023, title = {Scale-Equivariant Deep Learning for 3D Data}, author = {T Wimmer and V Golkov and HN Dang and M Zaiss and A Maier and D Cremers}, year = {2023}, journal = {arXiv preprint}, eprint = {2304.05864}, eprinttype = {arXiv}, primaryclass = {cs.CV}, keywords = {deep learning, equivariant deep learning, scale-equivariance, magnetic resonance imaging, image segmentation, medical imaging}, } @article{dang2023, title = {Joint {MR} sequence optimization beats pure neural network approaches for spin-echo {MRI} super-resolution}, author = {HN Dang and V Golkov and T Wimmer and D Cremers and A Maier and M Zaiss}, journal = {arXiv preprint arXiv:2305.07524}, year = {2023}, keywords = {medical imaging, magnetic resonance imaging, pulse sequences, super-resolution, deep learning}, eprint = {2305.07524}, eprinttype = {arXiv}, } @inproceedings{zaiss2023, title = {{GPT4MR}: Exploring {GPT-4} as an {MR} Sequence and Reconstruction Programming Assistant}, author = {M Zaiss and HN Dang and V Golkov and J Rajput and D Cremers and F Knoll and A Maier}, year = {2023}, keywords = {medical imaging, magnetic resonance imaging, pulse sequences, deep learning, large language models, prompt engineering}, url = {https://docs.google.com/document/d/1iy6AaTWCpGjfVc5Z0ar7VXWyJyNq3PlY2NYoeKCD0T4/}, booktitle = {European Society for Magnetic Resonance in Medicine and Biology ({ESMRMB}) Annual Meeting}, award = {Oral Presentation}, } @inproceedings{muhle2023learning, title = {Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares}, author = {D Muhle and L Koestler and KM Jatavallabhula and D Cremers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, eprint = {2305.09527}, eprinttype = {arXiv}, eprintclass = {cs.CV}, pages = {13102--13112}, year = {2023}, keywords = {pnec, vo, vslam, deep learning}, } @inproceedings{lidarsynthesis2023, title = {LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels}, booktitle = {IEEE 26th International Conference on Intelligent Transportation Systems}, author = {J Schmidt and Q Khan and D Cremers}, year = {2023}, keywords = {neural networks, deep learning, lidar }, } @inproceedings{multiagent2023, title = {Multi Agent Navigation in Unconstrained Environments Using a Centralized Attention Based Graphical Neural Network Controller}, booktitle = {IEEE 26th International Conference on Intelligent Transportation Systems}, author = {Y Ma and Q Khan and D Cremers}, year = {2023}, keywords = {neural networks, deep learning, multi-agent control}, } @article{vehiclepursuit2023, author = {J Pan and C Zhou and M Gladkova and Q Khan and D Cremers}, title = {Robust Autonomous Vehicle Pursuit without Expert Steering Labels}, journal = {{IEEE} Robotics and Automation Letters ({RA-L})}, year = {2023}, volume = {8}, number = {10}, pages = {6595 - 6602}, keywords = {vehicle pursuit, deep learning}, } @inproceedings{xia2023casspr, author = {Y Xia and M Gladkova and R Wang and Q Li and U Stilla and JF. Henriques and D Cremers}, title = {CASSPR: Cross Attention Single Scan Place Recognition}, eprint = {2211.12542}, eprinttype = {arXiv}, eprintclass = {cs.CV}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, year = {2023}, keywords = {lidar, place recognition, deep learning}, } @inproceedings{xia2024text2loc, title = {Text2Loc: 3D Point Cloud Localization from Natural Language}, author = {Y Xia and L Shi and Z Ding and JF Henriques and D Cremers}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, keywords = {3d localization, deep learning, LiDAR point cloud}, year = {2024}, } @inproceedings{compreason2024, title = {Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining}, booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV}, author = {U Sahin and H Li and Q Khan and D Cremers and T Volker}, year = {2024}, keywords = {neural networks, deep learning, Large Language Models}, } @article{multivehicle2023, title = {Multi-vehicle trajectory prediction and control at intersections using state and intention information}, author = {D Zhu and Q Khan and D Cremers}, journal = {Neurocomputing}, pages = {127220}, year = {2024}, publisher = {Elsevier}, keywords = {deep learning}, } @inproceedings{brahimi2024sparse, author = {M Brahimi and B Haefner and Z Ye and B Goldluecke and D Cremers}, title = {Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, titleurl = {brahimi2024sparseeprint=2404.00098}, eprinttype = {arXiv}, eprintclass = {cs.CV}, keywords = {d-reconstruction,photometry,deep learning,geometry processing}, }