Issued Patents All Time
Showing 25 most recent of 45 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12395685 | Highly efficient model for video quality assessment | Miao Yin, Qifei Wang, Boqing Gong, Neil Birkbeck, Balineedu Chowdary Adsumilli | 2025-08-19 |
| 12373954 | Transformer for efficient image segmentation | Chenglin Yang, Jianming Zhang, He Zhang, Zijun Wei, Zhe Lin | 2025-07-29 |
| 12356027 | Optimal format selection for video players based on predicted visual quality using machine learning | Yue Guo, Balineedu Chowdary Adsumilli | 2025-07-08 |
| 12347116 | Generating alpha mattes utilizing deep learning | Qihang Yu, Jianming Zhang, He Zhang, Zhe Lin, Ning Xu | 2025-07-01 |
| 12333731 | Transformer for efficient image segmentation | Chenglin Yang, Jianming Zhang, He Zhang, Zijun Wei, Zhe Lin | 2025-06-17 |
| 12299844 | Learning parameters for an image harmonization neural network to generate deep harmonized digital images | He Zhang, Yifan Jiang, Jianming Zhang, Kalyan Sunkavalli, Sarah A. Kong +3 more | 2025-05-13 |
| 12273521 | Obtaining video quality scores from inconsistent training quality scores | Balineedu Chowdary Adsumilli | 2025-04-08 |
| 12260557 | Object selection for images using image regions | Zijun Wei, Jianming Zhang, He Zhang | 2025-03-25 |
| 12250383 | Dynamic parameter selection for quality-normalized video transcoding | Balineedu Chowdary Adsumilli | 2025-03-11 |
| 12230024 | Systems and techniques for retraining models for video quality assessment and for transcoding using the retrained models | Hossein Talebi, Peyman Milanfar, Feng Yang, Balineedu Chowdary Adsumilli | 2025-02-18 |
| 12223439 | Visual-semantic representation learning via multi-modal contrastive training | Xin Yuan, Zhe Lin, Jason Wen Yong Kuen, Jianming Zhang, Ajinkya Gorakhnath Kale +1 more | 2025-02-11 |
| 12217382 | Multi-scale transformer for image analysis | Junjie Ke, Feng Yang, Qifei Wang, Peyman Milanfar | 2025-02-04 |
| 12206914 | Methods, systems, and media for determining perceptual quality indicators of video content items | Balineedu Chowdary Adsumilli, Junjie Ke, Hossein Talebi, Joong Yim, Neil Birkbeck +2 more | 2025-01-21 |
| 12165292 | Generating an image mask for a digital image by utilizing a multi-branch masking pipeline with neural networks | He Zhang, Seyed Morteza Safdarnejad, Zijun Wei, Jianming Zhang, Salil Tambe +1 more | 2024-12-10 |
| 12148074 | Object-to-object harmonization for digital images | He Zhang, Jeya Maria Jose Valanarasu, Jianming Zhang, Jose Ignacio Echevarria Vallespi, Kalyan Sunkavalli +3 more | 2024-11-19 |
| 12079725 | Convolutional neural networks with adjustable feature resolutions at runtime | Zhe Lin, Siyuan Qiao, Jianming Zhang | 2024-09-03 |
| 12020400 | Upsampling and refining segmentation masks | Chih-Yao Hsieh | 2024-06-25 |
| 11983632 | Generating and utilizing pruned neural networks | Shikun Liu, Zhe Lin, Jianming Zhang, Federico Perazzi | 2024-05-14 |
| 11935217 | Generating deep harmonized digital images | He Zhang, Yifan Jiang, Jianming Zhang, Kalyan Sunkavalli, Sarah A. Kong +3 more | 2024-03-19 |
| 11887270 | Multi-scale transformer for image analysis | Junjie Ke, Feng Yang, Qifei Wang, Peyman Milanfar | 2024-01-30 |
| 11875510 | Generating refined segmentations masks via meticulous object segmentation | Chenglin Yang, Jianming Zhang, He Zhang, Zhe Lin | 2024-01-16 |
| 11854244 | Labeling techniques for a modified panoptic labeling neural network | Sohrab Amirghodsi, Zhe Lin, Tianshu Yu, Connelly Barnes, Elya Shechtman | 2023-12-26 |
| 11854165 | Debanding using a novel banding metric | Balineedu Chowdary Adsumilli, Feng Yang | 2023-12-26 |
| 11710042 | Shaping a neural network architecture utilizing learnable sampling layers | Shikun Liu, Zhe Lin, Jianming Zhang, Federico Perazzi | 2023-07-25 |
| 11663481 | Neural network architecture pruning | Shikun Liu, Zhe Lin, Jianming Zhang, Federico Perazzi | 2023-05-30 |