Email: matthias.springsteintibeu
Phone: +49 511 762-19916
Postal address: Welfengarten 1 B, 30167 Hannover
Address for visitors: Lange Laube 28, 30159 Hannover, Room: 2.09
My research focuses on web-supervised learning regarding visual concepts and incremental learning approaches. The objective is to minimize efforts for manually labeling training data which might also enable and improve domain adaptation for visual concept models. This requires, for instance, automatic acquisition of visual information from user-generated content such as Flickr and YouTube. In general, I am interested in deep learning, concept detection, and training data augmentation.
2023
-
M. Springstein, M. Stamatakis, M. Plank, J. Sittel, R. Mauer, O. Bulgakowa, R. Ewerth, and E. Müller-Budack:
TIB AV-Analytics: A Web-based Platform for Scholarly Video Analysis and Film Studies
In: ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023, pp. 3195–3199. ACM, 2023.
https://doi.org/10.1145/3539618.3591820 -
J. Theiner, N. Nommensen, J. Rhotert, M. Springstein, E. Müller-Budack, and R. Ewerth:
Analyzing Results of Depth Estimation Models With Monocular Criteria
In: Explainable AI for Computer Vision Workshop co-located with the IEEE/CFV Conference on Computer Vision and Pattern Recognition, XAI4CV@CVPR 2023, Vancouver, Canada, June 19, pp. 3738-3742. IEEE/CVF, 2023.
2021
-
E. Müller-Budack, K. Pustu-Iren, S. Diering, M. Springstein, and R. Ewerth:
Image Analytics in Web Archives
The Past Web: Exploring Web Archives, pp. 141–151. Springer International Publishing, 2021.
https://doi.org/10.1007/978-3-030-63291-5_11 -
E. Müller-Budack, M. Springstein, S. Hakimov, K. Mrutzek, and R. Ewerth:
Ontology-driven Event Type Classification in Images
In: IEEE Winter Conference on Applications of Computer Vision, WACV 2021, Virtual Event, January 3-8, 2021, pp. 2927–2937. IEEE, 2021.
https://doi.org/10.1109/WACV48630.2021.00297 -
M. Springstein, E. Müller-Budack, and R. Ewerth:
Unsupervised Training Data Generation of Handwritten Formulas using Generative Adversarial Networks with Self-Attention
In: Workshop on Multi-Modal Pre-Training for Multimedia Understanding co-located with the International Conference on Multimedia Retrieval, MMPT@ICMR 2021, Virtual Event, August 21, 2021, pp. 46–54. ACM, 2021.
https://doi.org/10.1145/3463945.3469059 -
M. Springstein, E. Müller-Budack, and R. Ewerth:
QuTI! Quantifying Text-Image Consistency in Multimodal Documents
In: International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021, Virtual Event, July 11-15, 2021, pp. 2575–2579. ACM, 2021.
- https://doi.org/10.1145/3404835.3462796
2020
-
C. Otto, M. Springstein, A. Anand, and R. Ewerth:
Characterization and Classification of Semantic Image-Text Relations
International Journal of Multimedia Information Retrieval, 9(1), pp. 31–45, 2020.
- https://doi.org/10.1007/s13735-019-00187-6
2019
-
C. Otto, M. Springstein, A. Anand, and R. Ewerth:
Understanding, Categorizing and Predicting Semantic Image-Text Relations
In: International Conference on Multimedia Retrieval, ICMR 2019, Ottawa, ON, Canada, June 10-13, 2019, pp. 168–176. ACM, 2019.
Best Paper Award
- https://doi.org/10.1145/3323873.3325049
2017
-
R. Ewerth, M. Springstein, E. Müller, A. Balz, J. Gehlhaar, T. Naziyok, K. Dembczynski, and E. Hüllermeier:
Estimating relative depth in single images via rankboost
In: IEEE International Conference on Multimedia and Expo, ICME 2017, Hong Kong, China, July 10-14, 2017, pp. 919–924. IEEE Computer Society, 2017.
https://doi.org/10.1109/ICME.2017.8019434 -
M. Mühling, N. Korfhage, E. Müller, C. Otto, M. Springstein, T. Langelage, U. Veith, R. Ewerth, and B. Freisleben:
Deep learning for content-based video retrieval in film and television production
Multimedia Tools and Applications, 76(21), pp. 22169–22194, 2017.
https://doi.org/10.1007/s11042-017-4962-9 -
E. Müller, M. Springstein, and R. Ewerth:
"When Was This Picture Taken?" - Image Date Estimation in the Wild
In: European Conference on Information Retrieval, ECIR 2017, Aberdeen, UK, April 8-13, 2017, pp. 619–625, 2017.
https://doi.org/10.1007/978-3-319-56608-5_57