Computer Vision for Science
Organizers: David Fouhey (NYU), Katie Bouman (Caltech), Subhransu Maji (UMass Amherst)
Updated Date: June 17, 2024 at CVPR 2024, All Day
Motivation
Our workshop aims to bring together people working at the intersection of computer vision and the sciences. While many computer vision researchers are working at the intersection of computer vision and a science discipline, these efforts are often not highlighted at CVPR. As a result researchers remain disconnected, unaware of each others’ work, and miss opportunities to learn from each other. Early career researchers walking the poster floor of CVPR can get the mistaken impression that computer vision researchers do not work on or care about these problems.
On the other hand, there has been a recent surge in interest in the community in these topics, with a CVPR 2023 keynote and ICCV 2023 keynote covering AI For Science. These have been large-scale affairs that preclude focused discussions between practitioners. Given the need and considerable interest, we believe that now is the time to start having a workshop on computer vision for science.
We aim to highlight work in this space and are interested in any topic that covers both computer vision and the sciences:
Computer vision topics in this area often include (but are not limited to): reconstruction, recognition, segmentation and counting, human-in-the loop efforts, low-shot learning, domain adaptation and sim2real, video analysis, joint design of hardware and software.
Science topics include (but are not limited to): astrophysics via a variety of instrument types (radio, light, spectropolarimetry), chemistry, biology, neuroscience, and ecology.
Schedule
8:50 AM David Fouhey: Welcoming Remarks
9:00 AM Mike Walmsley: Astronomy Foundation Models
9:30 AM Tali Treibitz: Computer Vision for Coral Science
10:00 AM Coffee Break
10:45 AM Ellen Zhong: Work at Intersection of AI and Structural Biology
11:15 AM Poster Spotlights
11:45AM Lunch
12:45 - 12:25 Lunch Poster Session (Arch 4E)
1:30PM Jacob Berv: 15K Skeletons, or How I Learned to Stop Worrying and Love the Phenotype
2:00PM Yoav Schechner: Spaceborne Tomography of Cloud Microphysics for Climate Research
2:30PM Poster Spotlights
3:00PM Poster Session (Arch 4E)
3:45PM Mark Cheung: Computer Vision for Heliophysics & Astrophysics
4:15PM Sara Beery: Interactive query systems for scientific discovery in natural world data
4:45PM Aviad Levis: Physics-constrained neural fields for 3D imaging in astronomy
Confirmed Speakers
Mike Walmsley
Dunlap Fellow
University of Toronto
Tali Treibitz
Head of Marine Imaging Lab
University of Haifa
Ellen Zhong
Assistant Professor of CS
Princeton University
Mark Cheung
Science & Deputy Director
Space & Astronomy, CSIRO
Sara Beery
Assistant Professor
AI + Decision Making & CSAIL, MIT
Aviad Levis
Assistant Professor (2024)
University of Toronto
Yoav Schechner
Professor
Technion
Jacob Berv
Schmidt AI in Science Postdoc
University of Michigan
Poster List
Put a box on it: Sound Detection with CV Detectors (Aaron Sun)
LeAF: Leveraging Deep Learning for Plant Anomaly Detection and Classification for Farmers with Large Language Models for Natural Language Interaction & BRANCH Robot-Based Deployment (Aditya Sengupta)
Preliminary Report on Mantis Shrimp: a Multi-Survey Computer Vision Photometric Redshift Model (Andrew Engel)
Analysis of 3D Pathology Samples using Weakly Supervised AI (Andrew H. Song)
Towards Pan-Cancer Slide Representation Learning in Computational Pathology (Anurag Vaidya)
Illuminating Astronomy Surveys with Mask Image Modelling (Ashley Ferreira)
Exoplanet Detection via Differentiable Simulation (Brandon Y. Feng)
Single View Refractive Index Tomography with Neural Fields (Brandon Zhao)
Vectorized Coordinate Descent (VCD) (Charles Bouman)
Computational Echocardiography for Universal Screening and Myocardial Motion Tracking (Chengkang Shen)
ModelMine - A large scale 3D model housing database for Architecture design (Danish Syed)
Low-power, Continuous Remote Behavioral Localization with Event Cameras (Friedhelm Hamann)
Simulation and Modeling of Rare Binary Images under the Ising Model (Jiaxuan Xu)
CASPI: Collaborative Photon Processing for Active Single-Photon Imaging (Jongho Lee)
The DECIMER.ai Project (Kohulan Rajan)
Disambiguation of surface normals using single-view Mueller shape-from-polarization (Lily McKenna)
A vision-language foundation model for human pathology (Ming Yang (Max) Lu)
Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions (Oindrila Saha)
Estimating Sediment Concentrations in Global Surface Waters from Satellite Imagery (Rangel Daroya)
Towards a General-Purpose Foundation Model for Computational Pathology (Richard Chen)
SuperSynthIA: Physics-Ready Full-Disk Vector Magnetograms from HMI, Hinode, and Machine Learning (Ruoyu Wang)
FACL-CLIP: Fourier Augmentation Based Consistency Loss Focused CLIP Adaptation for Plant Disease Detection (Sarthak Srivastava)
VolRAFT: Volumetric Optical Flow Network for Digital Volume Correlation of Synchrotron Radiation-based Micro-CT Images of Bone-Implant Interfaces (Tak Ming Wong)
Multi-Stage Graph Learning for fMRI Analysis to Diagnose Neuro-Developmental Disorders (Xinhan Di)
Audio-visual integration in neural network and human brain (Yijun Liu)
Format
CV4Science will be a full day workshop incorporating:
Talks from a set of senior researchers at the interface betwen computer vision and science, including both computer vision researchers and domain experts
Posters from junior researchers that are selected on the basis of an extended abstract. These posters will be given a short spotlight plus a poster.
We will not have long-form workshop papers.
Poster Submission (Due by April 15th)
Based on the submissions received on April 15, we have reached our poster capacity and so cannot accept any late submissions.
Please submit information for your poster here: https://forms.gle/tpUddYyUPzEc8Grm6
In addition to authors, you will need: (a) a title, (b) brief abstract, and (c) an example figure + caption.