SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.10250 · 2026

Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy

Zhi-Qi Cheng, Jyoti Kini, Yujia Hu, Rolf Krause, Diego Pizzagalli, Raffaella Fiamma Cabini, Deborah Barkauskas, Guangyu Chen, David Cicchetti, Judith Drazba, Rodrigo Fernandez-Gonzalez, Raymond Hawkins, and 11 more

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
rcabini/CBVCC canonical 0 of 9
FunctionStatusWhere it lives
clean_model_name Not yet run rcabini/CBVCC/metrics/roc_curves.py
code served (permissive licence) · get_code("a84537303b1cb3ce")
compute_score_by_snr Not yet run rcabini/CBVCC/metrics/snr_curves.py
code served (permissive licence) · get_code("0f0b42b010a85e6c")
compute_score_per_cell_count Not yet run rcabini/CBVCC/metrics/ncell_curves.py
code served (permissive licence) · get_code("1c5a3555364fe2f2")
evaluate_models Not yet run rcabini/CBVCC/metrics/overall_metrics.py
code served (permissive licence) · get_code("518fd11990fae12d")
load_gt Not yet run rcabini/CBVCC/metrics/upload_files.py
code served (permissive licence) · get_code("d377a59a3235b985")
load_paths Not yet run rcabini/CBVCC/metrics/compute_quality_metrics.py
code served (permissive licence) · get_code("bfc3eb5075c265eb")
load_track_counts Not yet run rcabini/CBVCC/metrics/upload_files.py
code served (permissive licence) · get_code("9bc7b3e836770ca1")
plot_roc_curves Not yet run rcabini/CBVCC/metrics/roc_curves.py
code served (permissive licence) · get_code("4f07a51467646c98")
preprocess_submission Not yet run rcabini/CBVCC/metrics/upload_files.py
code served (permissive licence) · get_code("f86acc357e1aa5bf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.10250")
get_code_for_paper("2601.10250")
have("2601.10250")

Connect an agent — have() is free.