Domain-adaptive person re-identification via domain alignment and mutual pseudo-label refinement von Zhu, Songhao, Luo, Tao

Volltext

Combining multiscale learning and attention mechanism densely connected network for single image deraining von Chen, Hui, Zhu, Songhao

Volltext

Occluded pedestrian re-identification via Res-ViT double-branch hybrid network von Zhao, Yunbin, Zhu, Songhao

Volltext

An approach to improve SSD through mask prediction of multi-scale feature maps von Sun, Peng, Zhao, Yaqin, Zhu, Songhao

Volltext

Pitch contours curve frequency domain fitting with vocabulary matching based music generation von Lang, Runnan, Zhu, Songhao, Wang, Dongsheng

Volltext

Cross-modality person re-identication with triple-attentive feature aggregation von Huang, Pan, Zhu, Songhao, Wang, Dongsheng, Liang, Zhiwei

Volltext

ARM: a lightweight module to amend facial expression representation von Shi, Jiawei, Zhu, Songhao, Wang, Dongsheng, Liang, Zhiwei

Volltext

Simultaneous Localization and Mapping in a Hybrid Robot and Camera Network System von Liang, Zhiwei, Zhu, Songhao, Fang, Fang, Jin, Xin

Volltext

A vanishing theorem for the canonical blow-ups of Grassmann manifolds von Fang, Hanlong, Zhu, Songhao

Volltext

Multi-level similarity transfer and adaptive fusion data augmentation for few-shot object detection von Zhu, Songhao, Wang, Yi

Volltext

Statistical background model-based target detection von Li, Xiangxiang, Zhu, Songhao, Chen, Lingling

Volltext

Few-shot object detection via data augmentation and distribution calibration von Zhu, Songhao, Zhang, Kai

Volltext

Scene Segmentation and Semantic Representation for High-Level Retrieval von Zhu, Songhao, Liu, Yuncai

Volltext

SMFRNet: Complex Scene Lane Detection With Start Point-Guided Multi-Dimensional Feature Refinement von Tan, Shaohan, Zhang, Yixuan, Zhu, Songhao

Volltext

Semi-Supervised Learning Model Based Efficient Image Annotation von Songhao Zhu, Songhao Zhu, Yuncai Liu, Yuncai Liu

Volltext

Multi-branch blind-spot network with multi-class replacement refinement for self-supervised image denoising von Zhu, Songhao, Ji, Kangkang

Volltext

Subdomain alignment based open-set domain adaptation image classification von Ji, Kangkang, Zhang, Qingliang, Zhu, Songhao

Volltext

CTFCD: Channel transformer based on full convolutional decoder for single image deraining von Tan, Shaohan, Chen, Hui, Zhu, Songhao

Volltext

Image annotation using high order statistics in non-Euclidean spaces von Zhu, Songhao, Hu, Juanjuan, Wang, Baoyun, Shen, Shuhan

Volltext

Attention-calibration based double-branch cross-domain person re-identification von Ji, Kangkang, Huang, Pan, Zhu, Songhao

Volltext