Issued Patents 2021
Showing 1–20 of 20 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 11195048 | Generating descriptions of image relationships | Trung Bui, Hao Tan, Franck Dernoncourt, Mohit Bansal | 2021-12-07 |
| 11184558 | System for automatic video reframing | Lu Zhang, Jianming Zhang, Radomir Mech | 2021-11-23 |
| 11158055 | Utilizing a neural network having a two-stream encoder architecture to generate composite digital images | Jianming Zhang, He Zhang, Federico Perazzi | 2021-10-26 |
| 11152032 | Robust tracking of objects in videos | Zhihong Ding, Xiaohui Shen, Michael Kaplan, Jonathan Brandt | 2021-10-19 |
| 11144784 | Text-to-visual machine learning embedding techniques | Pranav Vineet Aggarwal, Baldo Faieta, Saeid Motiian | 2021-10-12 |
| 11138257 | Object search in digital images | Midhun Harikumar, Pramod Srinivasan, Jianming Zhang, Daniel Miranda, Baldo Faieta | 2021-10-05 |
| 11126890 | Robust training of large-scale object detectors with a noisy dataset | Mingyang Ling, Jianming Zhang, Jason Wen Yong Kuen, Federico Perazzi, Brett Butterfield +1 more | 2021-09-21 |
| 11127139 | Enhanced semantic segmentation of images | Jianming Zhang | 2021-09-21 |
| 11107219 | Utilizing object attribute detection models to automatically select instances of detected objects in images | Scott Cohen, Mingyang Ling | 2021-08-31 |
| 11069030 | Aesthetics-guided image enhancement | Xiaohui Shen, Xin Lu, Sarah A. Kong, I-Ming Pao, Yingcong Chen | 2021-07-20 |
| 11055566 | Utilizing a large-scale object detector to automatically select objects in digital images | Khoi Pham, Scott Cohen, Zhihong Ding, Walter Chang | 2021-07-06 |
| 11042798 | Regularized iterative collaborative feature learning from web and user behavior data | Jianchao Yang, Hailin Jin, Chen Fang | 2021-06-22 |
| 11024060 | Generating neutral-pose transformations of self-portrait images | Liqian MA, Jingwan Lu, Connelly Barnes, Alexei A. Efros | 2021-06-01 |
| 11023718 | Living body detection method and living body detection system | Zhao-Yuan Lin, Yao-Tsung Chang | 2021-06-01 |
| 11010893 | Image identifying method and image identifying device | Zhao-Yuan Lin, Yu-Jie Huang, Yi-Sheng Chao, Chun-Peng Hsu | 2021-05-18 |
| 10990877 | Frame selection based on a trained neural network | Xiaohui Shen, Radomir Mech, Jian Ren | 2021-04-27 |
| 10970599 | Learning copy space using regression and segmentation neural networks | Mingyang Ling, Alex Filipkowski, Jianming Zhang, Samarth Gulati | 2021-04-06 |
| 10963759 | Utilizing a digital canvas to conduct a spatial-semantic search for digital visual media | Mai Long, Jonathan Brandt, Hailin Jin, Chen Fang | 2021-03-30 |
| 10949744 | Recurrent neural network architectures which provide text describing images | Yufei Wang, Scott Cohen, Xiaohui Shen | 2021-03-16 |
| 10885608 | Super-resolution with reference images | Zhifei Zhang, Zhaowen Wang | 2021-01-05 |