Mayer, L., Luttner, L., Godau, P., Fritzsche, K., Reinke, A., Boland, L., Brandt, J., Heinecke, J., Nobuhara, C. K., Holzwarth, N., Christodoulou, E., Knopp, M., Michael, D., Piermarco, P., Neyaz, S., Özarslan, K. D., Hennighausen, J., Aumente-Maestro, C., Rädsch, T., Baji, D., Full, P. M., Aichholz, F., Erpenbeck, J. V., Schott, L. F., Winkelhausen, B., de Boer, C., Güttner, B., Hummel, A., Just, G., Kirchner, M., Li, C., Raffaut, R., Rodriguez, A., Venkatesh, D. K., Wang, K., Xu, J., Zeinoddin, M. S., Khan, S., Pausch, T. M., Speidel, S., Stoyanov, D., Hashimoto, D. A., Kolbinger, F. R., Weiser, T. G., & Maier-Hein, L. (2026). HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding. https://omanscience.com/ar/articles/heico-focus-a-clinically-grounded-dataset-for-long-context-video-understanding