Soyun Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Soyun Choi has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Sungeun Hong
Sungkyunkwan University, Seoul, Republic of Korea
4 shared publications - Youjia Zhang
Department of Electrical and Computer Engineering Inha University South Korea
4 shared publications
Latest Publications
- 17 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 162
Memory-efficient cross-modal attention for RGB-X segmentation and crowd counting
- 17 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 162
Memory-efficient cross-modal attention for RGB-X segmentation and crowd counting
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 217-225
Intra-inter Modal Attention Blocks for RGB-D Semantic Segmentation
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 217-225
Open AccessIntra-inter Modal Attention Blocks for RGB-D Semantic Segmentation
- 23 February 2023
- Published by Springer Nature
- p. 22-40
Spatio-Channel Attention Blocks for Cross-modal Crowd Counting
- 23 February 2023
- Published by Springer Nature
- p. 22-40
Spatio-Channel Attention Blocks for Cross-modal Crowd Counting
- Open Access
Spatio-channel Attention Blocks for Cross-modal Crowd Counting
Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the feasibility of other modalities such as thermal and depth images. The inherently significant differences between the different modalities and the diversity of design choices for model architectures make cross-modal crowd counting more challenging. In this paper, we propose Cross-modal Spatio-Channel Attention (CSCA) blocks, which can be easily integrated into any modality-specific architecture. The CSCA blocks first spatially capture global functional correlations among multi-modality with less overhead through spatial-wise cross-modal attention. Cross-modal features with spatial attention are subsequently refined through adaptive channel-wise feature aggregation. In our experiments, the proposed block consistently shows significant performance improvement across various backbone networks, resulting in state-of-the-art results in RGB-T and RGB-D crowd counting.
Open AccessSpatio-channel Attention Blocks for Cross-modal Crowd Counting
Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the feasibility of other modalities such as thermal and depth images. The inherently significant differences between the different modalities and the diversity of design choices for model architectures make cross-modal crowd counting more challenging. In this paper, we propose Cross-modal Spatio-Channel Attention (CSCA) blocks, which can be easily integrated into any modality-specific architecture. The CSCA blocks first spatially capture global functional correlations among multi-modality with less overhead through spatial-wise cross-modal attention. Cross-modal features with spatial attention are subsequently refined through adaptive channel-wise feature aggregation. In our experiments, the proposed block consistently shows significant performance improvement across various backbone networks, resulting in state-of-the-art results in RGB-T and RGB-D crowd counting.