1 code implementation • CVPR 2023 • Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada
Conventional architectures encode entire scene contents at a fixed rate regardless of their temporal characteristics.
Ranked #5 on Object Detection on GEN1 Detection
1 code implementation • CVPR 2021 • Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada
This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture.
no code implementations • 30 Jul 2020 • Kento Doi, Ryuhei Hamaguchi, Shun Iwase, Rio Yokota, Yutaka Matsuo, Ken Sakurada
To cope with the difficulty, we introduce a deep graph matching network that establishes object correspondence between an image pair.
no code implementations • CVPR 2019 • Ryuhei Hamaguchi, Ken Sakurada, Ryosuke Nakamura
The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.
3 code implementations • 1 Sep 2017 • Ryuhei Hamaguchi, Aito Fujita, Keisuke Nemoto, Tomoyuki Imaizumi, Shuhei Hikosaka
One of such difficulties is that objects are small and crowded in remote sensing imagery.