| Albert: A lite bert for self-supervised learning of language representations Z Lan, M Chen, S Goodman, K Gimpel, P Sharma, R Soricut ICLR 2020, 2020 | 3150 | 2020 |
| Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning P Sharma, N Ding, S Goodman, R Soricut ACL 2018, 2018 | 687 | 2018 |
| Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts S Changpinyo, P Sharma, N Ding, R Soricut CVPR 2021, 2021 | 88 | 2021 |
| Adaptable framework for cloud assisted augmented reality A Swaminathan, P Sharma, B Jiang, MR Chari, SD Spindola, PK Baheti, ... US Patent 9,633,447, 2017 | 81 | 2017 |
| Head pose estimation using RGBD camera P Sharma, A Swaminathan, R Rezaiifar, Q Xue US Patent 9,582,707, 2017 | 41 | 2017 |
| Rendering augmented reality based on foreground object P Sharma, R Rezaiifar US Patent 9,076,257, 2015 | 39 | 2015 |
| Generation of ghost-free high dynamic range images P Sharma, N Shroff, R Rezaiifar, C Sung US Patent 9,338,349, 2016 | 29 | 2016 |
| Neural naturalist: generating fine-grained image comparisons M Forbes, C Kaeser-Chen, P Sharma, S Belongie EMNLP 2019, 2019 | 27 | 2019 |
| Informative image captioning with external sources of information S Zhao, P Sharma, T Levinboim, R Soricut ACL 2019, 2019 | 23 | 2019 |
| Clue: Cross-modal coherence modeling for caption generation M Alikhani, P Sharma, S Li, R Soricut, M Stone ACL 2020, 2020 | 22 | 2020 |
| Method and apparatus for generating an all-in-focus image N Shroff, R Rezaiifar, P Sharma US Patent 9,344,619, 2016 | 21 | 2016 |
| Sensor api framework for cloud based applications P Sharma, A Swaminathan, C Brunner, MR Chari US Patent 10,248,184, 2019 | 15 | 2019 |
| Reference image selection for motion ghost filtering P Sharma, N Shroff, R Rezaiifar US Patent 10,382,674, 2019 | 14 | 2019 |
| Techniques for combining images with varying brightness degrees N Shroff, R Rezaiifar, P Sharma, WE Mantzel US Patent App. 14/254,770, 2015 | 14 | 2015 |
| Quality estimation for image captions based on large-scale human evaluations T Levinboim, A Thapliyal, P Sharma, R Soricut NAACL 2021, 2021 | 13 | 2021 |
| Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering S Changpinyo, B Pang, P Sharma, R Soricut EMNLP 2019, 2019 | 13 | 2019 |
| CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization A Akula, S Changpinyo, B Gong, P Sharma, SC Zhu, R Soricut EMNLP 2021, 2021 | 9 | 2021 |
| Reinforcing an image caption generator using off-line human feedback PH Seo, P Sharma, T Levinboim, B Han, R Soricut AAAI 2020, 2020 | 8 | 2020 |
| Detecting and compensating for motion between a flash and a no-flash image N Shroff, R Rezaiifar, C Sung, P Sharma US Patent 9,495,762, 2016 | 6 | 2016 |
| Understanding Guided Image Captioning Performance across Domains EG Ng, B Pang, P Sharma, R Soricut CoNLL 2021, 2021 | 4 | 2021 |
Radu SoricutGoogleVerified email at google.com
