Mathias Zinnen

Mathias Zinnen

Auto-generated profile, based on publicly available information

Mathias Zinnen

Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen Germany

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2023
Verified
Conference Paper
Open access
MZMathias Zinnen
Mathias Zinnen
AHAzhar Hussian
Azhar Hussian
HTHang Tran
Hang Tran
PMPrathmesh Madhu
Prathmesh Madhu
AMAndreas Maier
Andreas Maier
VCVincent Christlein
Vincent Christlein
Smell gestures play a crucial role in the investigation of past smells in the visual arts yet their automated recognition poses significant challenges. This paper introduces the SniffyArt dataset, consisting of 1941 individuals represented in 441 historical artworks. Each person is annotated with a tightly fitting bounding box, 17 pose keypoints, and a gesture label. By integrating these annotations, the dataset enables the development of hybrid classification approaches for smell gesture recognition. The dataset's high-quality human pose estimation keypoints are achieved through the merging of five separate sets of keypoint annotations per person. The paper also presents a baseline analysis, evaluating the performance of representative algorithms for detection, keypoint estimation, and classification tasks, showcasing the potential of combining keypoint estimation with smell gesture classification. The SniffyArt dataset lays a solid foundation for future research and the exploration of multi-task approaches leveraging pose keypoints and person boxes to advance human gesture and olfactory dimension analysis in historical artworks.

25 June 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
MZMathias Zinnen
Mathias Zinnen
PMPrathmesh Madhu
Prathmesh Madhu
ILInger Leemans
Inger Leemans
PBPeter Bell
Peter Bell
AHAzhar Hussian
Azhar Hussian
VCVincent Christlein
Vincent Christlein

28 October 2024
Verified
Conference Paper
Open access
HHHaiting Huang
Haiting Huang
MZMathias Zinnen
Mathias Zinnen
SLShumei Liu
Shumei Liu
AMAndreas Maier
Andreas Maier
VCVincent Christlein
Vincent Christlein
Large-scale photographic datasets like ImageNet and Places365 have significantly improved scene classification performance in natural images. However, scene classification in artistic imagery remains underexplored until recently. We propose a multi-step transfer learning technique that gradually adapts scene recognition algorithms from photographs to artistic scene representations. Our experiments demonstrate that integrating a stylized version of Places365, and fine-tuning with a weakly supervised artistic scene dataset, drastically increases scene recognition performance in artworks.We evaluate our method using two state-of-the-art scene recognition methods and analyze the impact of our adaptations with a series of ablation studies.

26 December 2024 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
MZMathias Zinnen
Mathias Zinnen
AHAzhar Hussian
Azhar Hussian
AMAndreas Maier
Andreas Maier
VCVincent Christlein
Vincent Christlein
The automatic recognition of sensory gestures in artworks provides the opportunity to open up methods of computational humanities to modern paradigms like sensory studies or everyday history. We introduce SensoryArt, a dataset of multisensory gestures in historical artworks, annotated with person boxes, pose estimation key points and gesture labels. We analyze algorithms for each label type and explore their combination for gesture recognition without intermediate supervision. These combined algorithms are evaluated for their ability to recognize and localize depicted persons performing sensory gestures. Our experiments show that direct detection of smell gestures is the most effective method for both detecting and localizing gestures. After applying post-processing, this method outperforms even image-level classification algorithms in image-level classification metrics, despite not being the primary training objective. This work aims to open up the field of sensory history to the computational humanities and provide humanities-based scholars with a solid foundation to complement their methodological toolbox with quantitative methods.


28 February 2025 in Information Fusion
Verified
Journal Article
Open access
TGThomas Gorges
Thomas Gorges
TSTeresa Scholz
Teresa Scholz
SSStefan Saloman
Stefan Saloman
MZMathias Zinnen
Mathias Zinnen
JHJuliane Hoffmann
Juliane Hoffmann
VCVincent Christlein
Vincent Christlein