Dr. Christian Wilms
Wissenschaftlicher Mitarbeiter
Computer Vision
Anschrift
Universität Hamburg
Fakultät für Mathematik, Informatik und Naturwissenschaften
Fachbereich Informatik
Arbeitsbereich CV
Vogt-Kölln-Straße 30
22527 Hamburg
Büro
Raum: R-108
Kontakt
Tel.: +49 40 428 83-2573
Forschungsinteressen
- Object recognition (object proposal generation, instance segmentation, object detection)
- Image segmentation
- Foundation models for segmentation
- Superpixel-based algorithms
- Applications of computer vision
Publikationen
2024
- Mykhailo Koshil, Tilman Wegener, Detlef Mentrup, Simone Frintrop, Christian Wilms: AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection, 2nd workshop on Vision-based InduStrial InspectiON (VISION) @ECCV, 2024, [PDF], [arxiv]
- Christian Wilms, Tim Rolff, Maris Hillemann, Robert Johanson, Simone Frintrop: SOS: Segment Object System for Open-World Instance Segmentation With Object Priors, European Conference on Computer Vision (ECCV), 2024, [PDF], [arxiv], [supp. mat.], [code], [video]
- André Peter Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop: Select High-Level Features: Efficient Experts from a Hierarchical Classification Network, 5th Workshop on practical ML for limited/low resource settings (PML4LRS) at ICLR 2024,[arxiv], [PDF]
- Robert Johanson*, Christian Wilms*, Ole Johannsen, Simone Frintrop: S³AD: Semi-supervised Small Apple Detection in Orchard Environments, Winter Conference on Applications of Computer Vision (WACV), 2024, [dataset], [PDF], [supp. mat.], [arxiv], [poster], [video]
2023
- André Peter Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop: Select High-Level Features: Efficient Experts from a Hierarchical Classification Network, 5th Workshop on practical ML for limited/low resource settings (PML4LRS) at ICLR 2024,[arxiv], [PDF]
- Noha Sarhan, Christian Wilms, Vanessa Closius, Ulf Brefeld, Simone Frintrop: Hands in Focus: Sign Language Recognition via Top-Down Attention, International Conference on Image Processing, ICIP 2023, [PDF]
- Tom Sanitz, Christian Wilms, Simone Frintrop: Small, but important: Traffic light proposals for detecting small traffic lights and beyond, International Conference on Computer Vision Systems (ICVS), 2023 [PDF]
- André Peter Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop: High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention, arXiv:2308.05128, 2023, [arXiv], [PDF]
2022
- Christian Wilms: Superpixels and Attention for High-quality Object Proposals in Complex Environments, Dissertation, 2022, [PDF]
- Christian Wilms, Alexander Michael Gerlach, Rüdiger Schmitz, and Simone Frintrop: Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask, arXiv:2203.11358, 2022, [arXiv]
- Christian Wilms, Robert Johanson, and Simone Frintrop: Localizing Small Apples in Complex Apple Orchard Environments, arXiv:2202.11372, 2022, [arXiv]
2021
- Christian Wilms, Simone Frintrop: DeepFH Segmentations for Superpixel-based Object Proposal Refinement, Image and Vision Computing (IMAVIS), 2021 [PDF]
2020
- Christian Wilms, Rafael Heid, Mohammad Araf Sadeghi, Andreas Ribbrock, Simone Frintrop: Which Airline is This? Airline Logo Detection in Real-World Weather Conditions, International Conference on Pattern Recognition (ICPR), 2020 [PDF]
- Christian Wilms, Simone Frintrop: Superpixel-based Refinement for Object Proposal Generation, International Conference on Pattern Recognition (ICPR), 2020 [webpage], [PDF]
2018
- Christian Wilms, Simone Frintrop: AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects, Asian Conference on Computer Vision (ACCV), 2018 [webpage], [PDF]
2017
- Christian Wilms, Simone Frintrop: Edge Adaptive Seeding for Superpixel Segmentation, Proc. of the German Conference on Pattern Recognition (GCPR), 2017 [webpage], [PDF]
2016
-
Benjamin Seppke, Leonie Dreschler-Fischer, Christian Wilms: Robust Superpixel Based Segmentation for Urbanization Monitoring by Means of Spectral Remote Sensing Images, in Proceedings of the DLT DGPF Symposium, Bern, 2016 [PDF]
- Benjamin Seppke, Leonie Dreschler-Fischer, Christian Wilms: A Robust Concurrent Approach for Road Extraction and Urbanization Monitoring Based on Superpixels Acquired from Spectral Remote Sensing Images, in Proceedings of the European Space Agency (ESA) Living Planet Symposium, 2016 [PDF]