activity
20152022
most citedBlending Diverse Physical Priors with Neural Networks

33 citations · 54 across the 6 of their papers we have counts for

collaborators

10 papers

cs.CV2021

Towards Rotation Invariance in Object Detection

Agastya Kalra, Guy Stoppi, Bradley Brown +2

Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation…

cs.ET2021

Physics-AI Symbiosis

Bahram Jalali, Achuta Kadambi, Vwani Roychowdhury

The phenomenal success of physics in explaining nature and designing hardware is predicated on efficient computational models. A universal codebook of physical laws defines the com…

cs.CV20215 cited

Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation

Yunhao Ba, Zhen Wang, Kerim Doruk Karinca +2

Camera-based remote photoplethysmography (rPPG) provides a non-contact way to measure physiological signals (e.g., heart rate) using facial videos. Recent deep learning architectur…

eess.IV2020

Diverse R-PPG: Camera-Based Heart Rate Estimation for Diverse Subject Skin-Tones and Scenes

Pradyumna Chari, Krish Kabra, Doruk Karinca +7

Heart rate (HR) is an essential clinical measure for the assessment of cardiorespiratory instability. Since communities of color are disproportionately affected by both COVID-19 an…

eess.IV20192 cited

Enhancing Passive Non-Line-of-Sight Imaging Using Polarization Cues

Kenichiro Tanaka, Yasuhiro Mukaigawa, Achuta Kadambi

This paper presents a method of passive non-line-of-sight (NLOS) imaging using polarization cues. A key observation is that the oblique light has a different polarimetric signal. I…

cs.CV20195 cited

Visual Physics: Discovering Physical Laws from Videos

Pradyumna Chari, Chinmay Talegaonkar, Yunhao Ba +1

In this paper, we teach a machine to discover the laws of physics from video streams. We assume no prior knowledge of physics, beyond a temporal stream of bounding boxes. The probl…