Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy
Year: 2026
Type: preprint
Abstract: The classification of microscopy videos capturing complex cellular behaviors is crucial for understanding and quantifying the dynamics of biological processes over time. However, it remains a frontier in computer vision, requiring approaches that effectively model the shape and motion of objects without rigid boundaries, extract hierarchical spatiotemporal features from entire image sequences rather than static frames, and account for multiple objects within the field of view. To this end, we organized the Cell Behavior Video Classification Challenge (CBVCC), benchmarking 35 methods based on three approaches: classification of tracking-derived features, end-to-end deep learning architectures to directly learn spatiotemporal features from the entire video sequence without explicit cell tracking, or ensembling tracking-derived with image-derived features. We discuss the results achieved by the participants and compare the potential and limitations of each approach, serving as a basis to foster the development of computer vision methods for studying cellular dynamics.
Source: arXiv (Cornell University)
Authors: Cabini, Raffaella Fiamma, Barkauskas, Deborah, Chen, Guangyu, Cheng, Zhi-Qi, Cicchetti, David E, Drazba, Judith, Fernandez-Gonzalez, Rodrigo, Hawkins, Raymond, Hu, Yujia, Kini, Jyoti, LeWarne, Charles, Lin, Xufeng, Nakkina, Sai Preethi, Peterson, John W, Schreurs, Koert, Singh, Ayushi, Viswanathan, Kumaran Bala Kandan, Wortel, Inge MN, Zhang, Sanjian, Krause, Rolf, Gonzalez, Santiago Fernandez, Pizzagalli, Diego Ulisse
Institutions: University of Pavia, Istituto Universitario di Studi Superiori di Pavia, Università della Svizzera italiana, Garvan Institute of Medical Research, University of Washington Tacoma, Radboud University Nijmegen, Cleveland Clinic Lerner College of Medicine, University of Toronto, University of Central Florida, UNSW Sydney, SUNY Upstate Medical University
Subfield: Biophysics
Domain: Life Sciences
Open Access status: green
Awards: G1652972601, AI and Simulations for Decoding the Spatiotemporal Dynamics of Immune Responses, EXTRAVOLT - Modulating extravasation of inflammatory cells in the blood-brain barrier via electric stimulation, Identification of alkaloids from medicinal plants of Cameroon, G7771916705, G7819825814
OpenAlex ID: W7124425340
Cites:
Cited by:
Related to: