Tingyu Lin

Projektass.(FWF) / MSc

Role

PreDoc Researcher
Computer Vision, E193-01

Contact

Publications

DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification / Lin, T., Dadras, A., Kleber, F., & Sablatnig, R. (2025). DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification. In SUMAC ’25: Proceedings of the 7th International Workshop on analySis, Understanding and proMotion of heritAge Contents (pp. 13–21). The Association for Computing Machinery. https://doi.org/10.1145/3746273.3760209
Project: VaCoViCu2 (2023–2027)
Rule-of-Thirds Detection with Interpretable Geometric Features / Dadras, A., Lin, T., Sablatnig, R., & Seidl, M. (2025). Rule-of-Thirds Detection with Interpretable Geometric Features. In SUMAC ’25: Proceedings of the 7th International Workshop on analySis, Understanding and proMotion of heritAge Contents (pp. 69–78). Association for Computing Machinery. https://doi.org/10.1145/3746273.3760202
Project: VaCoViCu2 (2023–2027)
A Robust and Efficient Framework for Inferring Mutual Gaze in Historical Video Data / Lin, T., Stippel, C., Kleber, F., & Sablatnig, R. (2025, February 12). A Robust and Efficient Framework for Inferring Mutual Gaze in Historical Video Data [Conference Presentation]. 28th Computer Vision Winter Workshop, Graz, Austria.
Project: VaCoViCu2 (2023–2027)
Enhancing Historical Image Retrieval with Compositional Cues / Lin, T., & Sablatnig, R. (2025). Enhancing Historical Image Retrieval with Compositional Cues. In B. Nessler, J. Piater, & P. M. Roth (Eds.), Austrian Symposium on AI, Robotics, and Vision (AIRoV) : Proceedings : March 26–27, 2024, University of Innbruck (pp. 169–178). innsbruck university press.
Project: VaCoViCu2 (2023–2027)
Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents / Sterzinger, R., Lin, T., & Sablatnig, R. (2025). Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents. In Pattern Recognition and Computer Vision : 8th Asian Conference on Pattern Recognition, ACPR 2025, Gold Coast, QLD, Australia, November 10–13, 2025, Proceedings, Part I (pp. 116–130).
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation / Yan, W., Liu, H., wang, yunkun, Li, Y., Chen, Q., Wang, W., Lin, T., Zhao, W., Zhu, L., Sundaram, H., & Deng, S. (2024). CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 5511–5558). https://doi.org/10.18653/v1/2024.acl-long.301