San Jose, CA, United States of America

Mai Long

USPTO Granted Patents = 8 

Average Co-Inventor Count = 4.8

ph-index = 3

Forward Citations = 25(Granted Patents)


Location History:

  • San Jose, CA (US) (2021 - 2022)
  • Portland, OR (US) (2019 - 2023)

Company Filing History:


Years Active: 2019-2023

Loading Chart...
8 patents (USPTO):Explore Patents

Title: The Innovative Contributions of Mai Long

Introduction

Mai Long is a prominent inventor based in San Jose, California, known for his significant contributions to the field of digital imaging and machine learning. With a total of eight patents to his name, Long has made remarkable strides in developing advanced technologies that enhance the accuracy and efficiency of depth image generation and object selection in digital media.

Latest Patents

One of Mai Long's latest patents focuses on generating depth images utilizing a machine-learning model built from mixed digital image sources and multiple loss function sets. This innovative system describes implementations of a depth prediction system that generates accurate depth images from single input digital images. The depth prediction model enforces different sets of loss functions across mixed data sources to create a multi-branch architecture depth prediction model. This model robustly trains using various data sources that have different granularities of ground truth depth data. Additionally, the model employs different combinations of loss functions, including an image-level normalized regression loss function and pair-wise normal loss, among others.

Another notable patent involves utilizing interactive deep learning to select objects in digital visual media. This patent discloses systems and methods for selecting target objects within digital images using a multi-modal object selection neural network trained to accommodate multiple input modalities. The disclosed systems generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. The trained neural network, along with iterative user inputs, is utilized to select target objects in digital images, transforming user inputs into distance maps that identify pixels reflecting the target object.

Career Highlights

Mai Long is currently employed at Adobe, Inc., where he continues to push the boundaries of innovation in digital imaging technologies. His work at Adobe has allowed him to collaborate with other talented professionals in the field, further enhancing the impact of his inventions.

Collaborations

Some of Mai Long's notable coworkers include Hailin Jin and Zhe Lin, who contribute to the collaborative environment that fosters innovation at Adobe.

Conclusion

Mai Long's contributions to the field of digital imaging and machine learning exemplify the spirit of innovation. His patents not only advance technology but also pave the way for future developments in the industry.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…