A5100605733- Human Motion and Animation
- Human Pose and Action Recognition
- Hand Gesture Recognition Systems
- Cybercrime and Law Enforcement Studies
- Advanced Image and Video Retrieval Techniques
- Chemical Synthesis and Analysis
- Embedded Systems Design Techniques
- Video Analysis and Summarization
- Click Chemistry and Applications
- Advanced Malware Detection Techniques
- Advanced Vision and Imaging
- Digital Rights Management and Security
- Image Retrieval and Classification Techniques
- Video Coding and Compression Technologies
- Digital and Cyber Forensics
- Cyclopropane Reaction Mechanisms
Huawei Technologies (China)
2023
Xi'an Jiaotong University
2013-2021
Shandong University of Political Science and Law
2006
The art of communication beyond speech there are gestures. automatic co-speech gesture generation draws much attention in computer animation. It is a challenging task due to the diversity gestures and difficulty matching rhythm semantics corresponding speech. To address these problems, we present DiffuseStyleGesture, diffusion model based speech-driven approach. generates high-quality, speech-matched, stylized, diverse on given speeches arbitrary length. Specifically, introduce cross-local...
Cybercriminals pose a significant threat to blockchain trading security, causing $40.9 billion in losses 2024. However, the lack of an effective real-world address dataset hinders advancement cybercrime detection research. The anti-cybercrime efforts researchers from broader fields, such as statistics and artificial intelligence, are blocked by data scarcity. In this paper, we present Real-CATS, Real-world Cryptocurrency Addresses with Transaction profileS, serving practical training ground...
The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted a lack of data volume and generalizability across different motion capture standards. In addition, it is challenging task due to the weak correlation between speech gestures. To address these problems, we present UnifiedGesture, novel diffusion model-based speech-driven synthesis approach, trained multiple datasets with...
The art of communication beyond speech there are gestures. automatic co-speech gesture generation draws much attention in computer animation. It is a challenging task due to the diversity gestures and difficulty matching rhythm semantics corresponding speech. To address these problems, we present DiffuseStyleGesture, diffusion model based speech-driven approach. generates high-quality, speech-matched, stylized, diverse on given speeches arbitrary length. Specifically, introduce cross-local...
Greatness in simplicity: A general, straightforward, and atom-economical protocol to synthesize vinyl triflimides has been developed. broad spectrum of terminal internal alkynes could be used generate various di- trisubstituted triflimides. The conducted on a gram scale with both alkynes. Preliminarily attempts probe the unprecedented reactivity disclosed some its unique chemical properties. More information can found Communication by Y. Wang et al. (DOI: 10.1002/chem.202102369).