954 citations
- Nanjing UniversityCN10 papers
- Ural Federal UniversityRU10 papers
- Nanjing University of Posts and TelecommunicationsCN6 papers
- Chinese Academy of SciencesCN5 papers
- Nanjing University of Science and TechnologyCN4 papers
- M.N. Mikheev Institute of Metal PhysicsRU3 papers
- Pennsylvania State UniversityUS3 papers
- Dalian University of TechnologyCN2 papers
- Fudan UniversityCN2 papers
- Hong Kong University of Science and TechnologyHK2 papers
- Hubei Normal UniversityCN2 papers
- Institute of ElectrophysicsRU2 papers
59 papers
CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification
Xiaomei Yang, Xizhan Gao, Sijie Niu +4
This paper proposes a novel CLIP-driven modality-shared representation learning network named CLIP4VI-ReID for VI-ReID task, which consists of Text Semantic Generation (TSG), Infra…
Role of chromium oxides and carbides in strengthening CoCrFeNi multi-principle element alloys
Artur Olejarz, Wenyi Huo, Anna Kosinska +7
Multi-principal element alloys (MPEAs) can potentially offer exceptional material properties, but their complex, costly manufacturing limits their scalability. Chemical complexity…
Explosive growth of bistability in a cavity magnonic system
Meng-Xia Bi, Huawei Fan, Wenting Wu +3
We conduct a theoretical investigation into explosive growth of bistability in a cavity magnonic system incorporating magnetic nonlinearity. In this system, the coupling between th…
WaveInst: A Frequency-Domain Enhanced Network for Fine-Grained Thin Tree Trunk Extraction in Forest Scenes
Chenyang Fan, Xujie Zhu, Taige Luo +2
Analyzing tree morphology, particularly trunk and branch extraction, is valuable for genetic breeding and forestry management. Existing image-based deep learning methods tend to mi…
Nanoindentation responses of Fe-Cr alloys from room temperature to 600 °C
L. Kurpaska, M. Clozel, J. H. OConnell +9
In this work, the evolution of nanomechanical properties was studied systematically as a function of temperature, chemical, and microstructural complexity of different Fe-based all…
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition
Zhaoyu Chen, Xing Li, Qian Huang +3
Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balan…