霍 達

D3

Research Summary

Research is comprehensive understanding about the content of images. It includes object detection, and image captioning. Especially, we focus on understanding the semantic information of an image, considering the action between objects and the different scales of objects.

Main Research Fields

• Object Detection
• Image Captioning
• Image Encryption

Keywords

• Small Object Detection
• Image Captioning
• DNA coding and Chaotic map

Research theme

• Small Object Detection on Birds
• Image Captioning Considering Action Information
• Learning Semantic for Multiscale Objects

Selected Publications

• Da Huo, Marc A. Kastner, Tingwei Liu, Yasutomo Kawanishi, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide. Small Object Detection for Birds with Swin Transformer. MVA, 2023.
• Yuki Kondo, Norimichi Ukita, Takayuki Yamaguchi, Hao-Yu Hou, Mu-Yi Shen, Chia-Chi Hsu, En-Ming Huang, Yu-Chen Huang, Yu-Cheng Xia, Chien-Yao Wang, Chun-Yi Lee, Da Huo, Marc A. Kastner, Tingwei Liu, Yasutomo Kawanishi, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide, Yosuke Shinya, Guang Liang, Syusuke Yasui. MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results. MVA, 2023.
• Da Huo, Marc A. Kastner, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide. Image captioning considering relations of objects. MIRU, 2023.
• Yiming Wang, Marc A. Kanster, Da Huo, Takahiro Komamizu, Takatsugu Hirayama, Ichiro Ide. Evoked Emotion Distribution Learning through Analysis of Temporal User Comments in Social Media Videos. MVE, 2023.
• Da Huo, Marc A. Kastner, Takahiro Komamizu, Ichiro Ide. Action Semantic Alignment for Image Captioning. MIPR, 2022.