This inventor holds 1 USPTO granted patent. Top assignee: Nec Corporation. Active years: 2025.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2025
Title: Innovations of Cheng-En Wu in Multimodal Representation Learning
Introduction
Cheng-En Wu is an accomplished inventor based in Madison, WI (US). He has made significant contributions to the field of machine learning, particularly in the area of self-supervised multimodal representation learning. His innovative approach has the potential to enhance various applications in video analysis and processing.
Latest Patents
Cheng-En Wu holds a patent titled "Self-supervised multimodal representation learning with cascade positive example mining." This patent describes a method for model training and deployment that includes training a model to learn video representations using a self-supervised contrastive loss. The method involves progressive training in phases, resetting the learning rate schedule, and inheriting model weights from previous training phases. Additionally, it updates the trained model with multiple positive instances obtained from Cascade K-Nearest Neighbor mining, extracting features in different modalities to compute similarities between video sequences. The trained model is then fine-tuned for downstream tasks and deployed for target application inference.
Career Highlights
Cheng-En Wu is currently employed at NEC Corporation, where he continues to work on innovative solutions in the field of artificial intelligence and machine learning. His expertise in multimodal representation learning has positioned him as a key contributor to the company's research and development efforts.
Collaborations
Cheng-En Wu collaborates with talented individuals such as Farley Lai and Asim Kadav. Their combined expertise fosters a creative environment that drives innovation and enhances the development of cutting-edge technologies.
Conclusion
Cheng-En Wu's contributions to self-supervised multimodal representation learning exemplify the impact of innovative thinking in technology. His work not only advances the field of machine learning but also opens new avenues for practical applications in video analysis.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile