| 10852749 |
Learning good features for visual odometry |
Quoc-Huy Tran, Hyo Jin Kim |
2020-12-01 |
| 10853656 |
Surveillance system with activity recognition |
Kihyuk Sohn, Xiang Yu |
2020-12-01 |
| 10853655 |
Mobile device with activity recognition |
Kihyuk Sohn, Xiang Yu |
2020-12-01 |
| 10853654 |
Video representation of first-person videos for activity recognition without labels |
Kihyuk Sohn, Xiang Yu |
2020-12-01 |
| 10853627 |
Long-tail large scale face recognition by non-linear feature level domain adaptation |
Xiang Yu, Xi Yin, Kihyuk Sohn |
2020-12-01 |
| 10832084 |
Dense three-dimensional correspondence estimation with multi-level metric learning and hierarchical matching |
Quoc-Huy Tran, Mohammed E. Fathy Salem, Muhammad Zeeshan Zia, Paul Vernaza |
2020-11-10 |
| 10832440 |
Temporal multi-scale clockwork memory networks for object detection in videos |
Samuel Schulter, Wongun Choi, Tuan Hung Vu |
2020-11-10 |
| 10810469 |
Extracting material properties from a single image |
Kalyan Sunkavalli, Zhengqin Li |
2020-10-20 |
| 10796135 |
Long-tail large scale face recognition by non-linear feature level domain adaptation |
Xiang Yu, Xi Yin, Kihyuk Sohn |
2020-10-06 |
| 10796134 |
Long-tail large scale face recognition by non-linear feature level domain adaptation |
Xiang Yu, Xi Yin, Kihyuk Sohn |
2020-10-06 |
| 10762359 |
Computer aided traffic enforcement using dense correspondence estimation with multi-level metric learning and hierarchical matching |
Quoc-Huy Tran, Mohammed E. F. Salem, Muhammad Zeeshan Zia, Paul Vernaza |
2020-09-01 |
| 10740596 |
Video security system using a Siamese reconstruction convolutional neural network for pose-invariant face recognition |
Xiang Yu, Kihyuk Sohn |
2020-08-11 |
| 10740595 |
Long-tail large scale face recognition by non-linear feature level domain adaption |
Xiang Yu, Xi Yin, Kihyuk Sohn |
2020-08-11 |
| 10733756 |
Online flow guided memory networks for object detection in video |
Wongun Choi, Samuel Schulter, Tuan Hung Vu |
2020-08-04 |
| 10706336 |
Recognition in unlabeled videos with domain adversarial learning and knowledge distillation |
Kihyuk Sohn, Xiang Yu |
2020-07-07 |
| 10706582 |
Real-time monocular structure from motion |
Shiyu Song |
2020-07-07 |
| 10678257 |
Generating occlusion-aware bird eye view representations of complex road scenes |
Samuel Schulter, Paul Vernaza, Menghua Zhai |
2020-06-09 |
| 10679075 |
Dense correspondence estimation with multi-level metric learning and hierarchical matching |
Quoc-Huy Tran, Mohammed E. F. Salem, Muhammad Zeeshan Zia, Paul Vernaza |
2020-06-09 |
| 10678256 |
Generating occlusion-aware bird eye view representations of complex road scenes |
Samuel Schulter, Paul Vernaza, Menghua Zhai |
2020-06-09 |
| 10635950 |
Surveillance system for recognition in unlabeled videos with domain adversarial learning and knowledge distillation |
Kihyuk Sohn, Xiang Yu |
2020-04-28 |
| 10595037 |
Dynamic scene prediction with multiple interacting agents |
Wongun Choi, Paul Vernaza, Namhoon Lee |
2020-03-17 |
