期刊论文

Liang, XM

英文

Signal, Image and Video Processing

1863-1703

2025

19

5

1-10

10.1007/s11760-025-03969-0

This work was supported by the National Natural Science Foundation of China (61772179), Hunan Provincial Natural Science Foundation of China (2022JJ50016,2023JJ50095), and the Science and Technology Plan Project of Hunan Province (2016TP1020). Scientific Research Fund of Hunan Provincial Education Department (21B0649), Double First-Class University Project of Hunan Province (Xiangjiaotong [2018]469,[2020]248), Postgraduate Scientific Research Innovation Project of Hunan Province (CX20221285).

本校为第一且通讯机构

Pose transfer refers to transferring a given person’s pose to the target pose. We present a context-driven omni-dimensional dynamic pose transfer model to address the issue of regular convolutional networks being unable to manage complicated changes. First, we construct a dynamic convolution module to extract rich contextual features. This module dynamically adjusts to the differences in input data during the convolution process, enhancing the adaptability of features. Second, a feature fusion block (FFBlock) is built by merging multiscale cha...