1 code implementation • 27 Feb 2024 • Yancong Lin, Holger Caesar
We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations.
no code implementations • 12 Oct 2023 • Jiarong Wei, Yancong Lin, Holger Caesar
By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced.
1 code implementation • ICCV 2023 • Silvia L. Pintea, Yancong Lin, Jouke Dijkstra, Jan C. van Gemert
A number of computer vision deep regression approaches report improved results when adding a classification loss to the regression loss.
1 code implementation • CVPR 2022 • Yancong Lin, Ruben Wiersma, Silvia L. Pintea, Klaus Hildebrandt, Elmar Eisemann, Jan C. van Gemert
Deep learning has improved vanishing point detection in images.
no code implementations • 23 Dec 2021 • Yancong Lin, Silvia-Laura Pintea, Jan van Gemert
Experiments on both synthetic and real-world datasets show the benefit of our proposed changes for improved data efficiency and inference speed.
no code implementations • 17 Aug 2021 • Andrea Alfieri, Yancong Lin, Jan C. van Gemert
Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel.
no code implementations • 9 Jun 2021 • Yancong Lin, Silvia-Laura Pintea, Jan van Gemert
Current work on lane detection relies on large manually annotated datasets.
1 code implementation • ECCV 2020 • Yancong Lin, Silvia L. Pintea, Jan C. van Gemert
Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features.
Ranked #3 on Line Segment Detection on wireframe dataset