This inventor holds 4 USPTO granted patents and 1 published patent application. Top assignees: Disney Enterprises, Inc., Fudan University. Active years: 2018-2023.
Location History:
- College Park, MD (US) (2020)
- Shanghai, CN (2018 - 2023)
Company Filing History:
Years Active: 2018-2023
Title: Innovations of Zuxuan Wu in Video Recognition and Image Processing
Introduction
Zuxuan Wu is a prominent inventor based in Shanghai, China. He has made significant contributions to the fields of video recognition and image processing. With a total of 4 patents, his work focuses on developing advanced methods and systems that enhance the capabilities of machine learning models.
Latest Patents
One of Zuxuan Wu's latest patents is titled "Method and system for generating adversarial attacks on video recognition models." This invention discloses a method for generating adversarial attacks on a video recognition model. The process includes generating the content of bullet-screen comments (BSCs) by an image captioning model for a clean video sample. It also involves creating an adversarial video sample by inserting the BSCs into the clean video sample. The adversarial video sample is then used to attack the video recognition model, with rewards received from the environment. The position and transparency of BSCs are optimized by a reinforced learning (RL) agent based on the received rewards. This iterative process continues until a predefined condition is met.
Another notable patent is "Weakly-supervised spatial context networks to recognize features within an image." This invention encompasses systems, methods, and articles of manufacture for training a convolutional neural network for feature recognition within digital images. A spatial context neural network is trained using multiple patches cropped from various digital images. The network comprises two convolutional neural networks that predict and compute feature representations for specified portions of digital images. The refined second convolutional neural network is then utilized to recognize features within a third digital image.
Career Highlights
Zuxuan Wu has worked with notable organizations such as Disney Enterprises, Inc. and Fudan University. His experience in these institutions has allowed him to develop and refine his innovative ideas in the realm of technology and research.
Collaborations
Zuxuan Wu has collaborated with esteemed colleagues, including Leonid Sigal and Yanwei Fu. These partnerships have contributed to the advancement of his research and the successful development of his patents.
Conclusion
Zuxuan Wu's innovative work in video recognition and image processing showcases his expertise and dedication to advancing technology. His patents reflect a commitment to enhancing machine learning models and their applications in real-world scenarios.