Deepti Ghadiyaram

Menlo Park, United States

Deepti is a research scientist at Facebook AI Applied Research (FAIAR), with a focus on computer vision and machine learning. Specifically, she works on problems pertaining to responsible and fair computer vision models, image and video understanding, and perceptual image and video quality assessment. She earned her Ph.D. in computer science from the University of Texas at Austin in 2017.

Deepti's Publications

June 14, 2020

RESEARCH

COMPUTER VISION

Don’t Judge an Object by Its Context: Learning to Overcome Contextual Bias

Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram

June 14, 2020

May 19, 2020

RESEARCH

COMPUTER VISION

ClusterFit: Improving Generalization of Visual Representations

Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan

May 19, 2020

June 16, 2020

COMPUTER VISION

From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality

Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan Bovik

June 16, 2020

May 01, 2019

RESEARCH

COMPUTER VISION

Large-scale weakly-supervised pre-training for video action recognition

Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Hen Wang, Dhruv Mahajan

May 01, 2019