Issued Patents All Time
Showing 1–25 of 77 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12417391 | Modular adaptation for cross-domain few-shot learning | Xiao Lin, Meng Ye, Yunye Gong, Giedrius T. Burachas, Yi Yao +1 more | 2025-09-16 |
| 12411879 | Instruction-guided visual embeddings and feedback-based learning in large vision-language models | Yangyi Chen, Karan Sikka, Michael A. Cogswell | 2025-09-09 |
| 12374101 | Error-based explanations for artificial intelligence behavior | Arijit Ray, Michael A. Cogswell, Yi Yao, Giedrius T. Burachas, Kamran Alipour | 2025-07-29 |
| 12367420 | User targeted content generation using multimodal embeddings | Karan Sikka, Arijit Ray, Xiao Lin, Yi Yao | 2025-07-22 |
| 12340335 | Automated collaboration skills assessment | Svati Dhamija, Amir Tamrakar, Nonye M. Alozie, Elizabeth McBride, Anirudh Som +2 more | 2025-06-24 |
| 12282606 | VPA with integrated object recognition and facial expression recognition | Amir Tamrakar, Girish Acharya, William S. Mark, Greg Ho, Jihua Huang +13 more | 2025-04-22 |
| 12236330 | Analysis and design of dynamical system controllers using neural differential equations | Anirban Roy, Susmit Jha | 2025-02-25 |
| 11934793 | System and method for content comprehension and response | Karan Sikka, Yi Yao, Yunye Gong, Stephanie Nunn, Pritish SAHU +3 more | 2024-03-19 |
| 11790213 | Identifying complex events from hierarchical representation of data set features | Yi Yao, Pallabi Ghosh | 2023-10-17 |
| 11610384 | Zero-shot object detection | Karan Sikka, Ankan Bansal | 2023-03-21 |
| 11238631 | Align-to-ground, weakly supervised phrase grounding guided by image-caption alignment | Karan Sikka, Samyak Datta | 2022-02-01 |
| 11210572 | Aligning symbols and objects using co-attention for understanding visual content | Karan Sikka, Karuna Ahuja, Anirban Roy | 2021-12-28 |
| 11055555 | Zero-shot object detection | Karan Sikka, Ankan Bansal | 2021-07-06 |
| 10884503 | VPA with integrated object recognition and facial expression recognition | Amir Tamrakar, Girish Acharya, William S. Mark, Greg Ho, Jihua Huang +13 more | 2021-01-05 |
| 10824916 | Weakly supervised learning for classifying images | Karan Sikka, Parneet Kaur | 2020-11-03 |
| 10679063 | Recognizing salient video events through learning-based multimodal analysis of visual features and audio-based analytics | Hui Cheng, Elizabeth Shriberg, Harpreet Singh Sawhney, Jingen Liu, Ishani Chakraborty +4 more | 2020-06-09 |
| 10303768 | Exploiting multi-modal affect and semantics to assess the persuasiveness of a video | Behjat Siddiquie, David Chisholm, Elizabeth Shriberg | 2019-05-28 |
| 10268900 | Real-time detection, tracking and occlusion reasoning | Qian Yu, Amir Tamrakar, Harpreet Singh Sawhney, Jiejie Zhu, Omar Javed +3 more | 2019-04-23 |
| 10198509 | Classification, search and retrieval of complex video events | Hui Cheng, Harpreet Singh Sawhney, Qian Yu, Jingen Liu, Amir Tamrakar +2 more | 2019-02-05 |
| 10068024 | Method and apparatus for correlating and viewing disparate data | Harpreet Singh Sawhney, Jayakrishnan Eledath, Mayank Bansal, Hui Cheng | 2018-09-04 |
| 9977972 | 3-D model based method for detecting and classifying vehicles in aerial imagery | Saad Khan, Hui Cheng, Dennis Lee Matthies, Harpreet Singh Sawhney, Sang-Hack Jung +2 more | 2018-05-22 |
| 9916520 | Automated food recognition and nutritional estimation with a personal mobile electronic device | Weiyu Zhang, Qian Yu, Harpreet Singh Sawhney | 2018-03-13 |
| 9904852 | Real-time object detection, tracking and occlusion reasoning | Qian Yu, Amir Tamrakar, Harpreet Singh Sawhney, Jiejie Zhu, Omar Javed +3 more | 2018-02-27 |
| 9875445 | Dynamic hybrid models for multimodal analysis | Mohamed R. Amer, Behjat Siddiquie, Colleen Richey, Saad Khan, Hapreet S. Sawhney +1 more | 2018-01-23 |
| 9734730 | Multi-modal modeling of temporal interaction sequences | Behjat Siddiquie, Saad Khan, Jeffrey Lubin, Harpreet Singh Sawhney | 2017-08-15 |