About Me
I am a second year PhD student in Computer Science at Stanford University advised by Leonidas Guibas. My general interests lie in 3D computer vision and machine learning. I specialize in building geometric representations for objects over time.
I have interned with Toyota Research Institute (TRI), Nvidia, Second Genome, and Aptiv.
During my first year at Stanford, I rotated with Jure Leskovic and Serena Yeung.
I received my Bachelor's degree in computer science from MIT in 2020.
Research
SpOT: Spatiotemporal Modeling for 3D Object Tracking
C. Stearns, D. Rempe, J. Lie, R. Ambrus, Y. Yang, S. Zakharov,
V. Guizilini, and L. Guibas. ECCV 2022 Oral Presentation.
Abstract:
3D multi-object tracking aims to uniquely and consistently identify all mobile entities through time.
Despite the rich spatiotemporal information available in this setting, current 3D tracking methods primarily
rely on abstracted information and limited history, e.g. single-frame object bounding boxes.
In this work, we develop a holistic representation of traffic scenes that leverages both spatial
and temporal information of the actors in the scene. Specifically, we reformulate tracking as a
spatiotemporal problem by representing tracked objects as sequences of time-stamped points
and bounding boxes over a long temporal history. At each timestamp, we improve the location
and motion estimates of our tracked objects through learned refinement over the full sequence
of object history. By considering time and space jointly, our representation naturally encodes
fundamental physical priors such as object permanence and consistency across time. Our
spatiotemporal tracking framework achieves state-of-the-art performance on the Waymo and
nuScenes benchmarks.
Gamma Frequency Sensory Stimulation in Probable Mild Alzheimer's Dementia Patients: Results of a Preliminary Clinical Trial
Diane Chan, Ho-Jun Suk, Brennan Jackson, Noah Pollak Milman, Danielle Stark,
Elizabeth B. Klerman, Erin Kitchener, Vanesa S. Fernandez Avalos, Arit Banerjee, Sara D. Beach,
Joel Blanchard, Colton Stearns, Aaron Boes, Brandt Uitermarkt, Phillip Gander, Matthew Howard III,
Eliezer J. Sternberg, Alfonso Nieto-Castanon, Sheeba Anteraper, Susan Whitfield-Gabrieli,
Emery N. Brown, Edward S. Boyden, Bradford Dickerson, and Li-Huei Tsai. Neuron 2021.
Abstract:
Non-invasive Gamma ENtrainment Using Sensory stimuli (GENUS) at 40Hz reduced Alzheimer’s disease (AD) pathology,
prevented cerebral atrophy and improved performance during behavioral testing in mouse models of AD.
We report data from a safety study (NCT04042922) and a randomized, placebo-controlled trial in
participants with probable mild AD dementia after 3 months of one-hour daily 40Hz light and sound GENUS (NCT04055376)
to assess safety, compliance, entrainment and possible effects on brain structure, function, sleep and cognitive function.
GENUS was well-tolerated and compliance was high in both groups. Electroencephalography recordings show that
our GENUS device safely and effectively induced 40Hz entrainment in cognitively normal subjects and participants
with mild AD. After 3 months of daily stimulation, participants with mild AD in the 40Hz GENUS group showed
less ventricular enlargement and stabilization of the hippocampal size compared to the control group. Functional
connectivity increased in both the default mode network and the medial visual network after 3 months of stimulation.
Circadian rhythmicity also improved with GENUS. Compared to controls, the active group performed better on the
face-name association delayed recall test. These results suggest that 40Hz GENUS can be used safely at home daily
and shows favorable outcomes on cognitive function, daily rhythms, and structural and functional MRI biomarkers of
AD-related degeneration. These results support further evaluation of GENUS in larger and longer clinical trials to
evaluate its potential as a disease modifying therapeutic for Alzheimer’s disease..