The primary goal of this challenge is to encourage participants to build better algorithms for autonomous remote instruction systems in uncontrolled and austere environments, especially for life saving procedures [1]. Because most battlefield death occurs well before receiving comprehensive medical care, there is an opportunity for a first responder to provide effective initial treatment in order to save lives [2-4]. An AI-based guidance system can not only enhance the capabilities of untrained personnel to deliver diagnosis or resuscitative care in austere environments, but also increase their confidence to undertake psychologically daunting procedures [1,5]. Understanding and predicting actions based on the appearance of a scene (e.g. a patient injured in the field) is a desired treat in AI systems in this context could help the first responder and untrained personnel. For example, if a patient is bleeding due to a blast injury, the action required may be to apply a tourniquet. There are many popular datasets to investigate human actions and intentions from the first-person view for activities of daily living (ADL) [6-9], but only very few are related to the medical domain (refer to [10] for egocentric datasets of medical procedures). To the best of our knowledge, our dataset is the first egocentric view dataset of life-saving intervention (LSI) procedures with detailed annotations by medical professionals. We have collected over 60 procedure videos with environment, simulator, and type variability. Based on this dataset, the challenge we propose involves multiple tasks to encourage participants across the globe to design impactful algorithms with applications to medicine. The envisioned algorithms include action recognition, action anticipation, procedure recognition, and visual question answering. This challenge is proposed to support the future development of innovative solutions for autonomous remote instruction systems including action anticipation, recognition, and procedure recognition algorithms to support medical procedures in austere, emergent, and uncontrolled settings. We also plan to use this dataset to develop automated medical image interpretation and promote its use in low medical resource settings. [1] A. W. Kirkpatrick, J. L. McKee, P. B. McBeth, C. G. Ball, A. LaPorta, T. Broderick, T. Leslie, D. King, H. E. Wright Beatty, J. Keillor, and H. Tien, “The Damage Control Surgery in Austere Environments Research Group (DCSAERG): A dynamic program to facilitate real-time telementoring/telediagnosis to address exsanguination in extreme and austere environments,” Journal of Trauma and Acute Care Surgery, vol. 83, no. 1, 2017. [2] B. J. Eastridge, M. Hardin, J. Cantrell, L. Oetjen-Gerdes, T. Zubko, C. Mallak, C. E. Wade, J. Simmons, J. Mace, R. Mabry, R. Bolenbaucher, and L. H. Blackbourne, “Died of wounds on the battlefield: Causation and implications for improving combat casualty care,” Journal of Trauma: Injury, Infection & Critical Care, vol. 71, no. 1, 2011. [3] B. J. Eastridge, R. L. Mabry, P. Seguin, J. Cantrell, T. Tops, P. Uribe, O. Mallett, T. Zubko, L. Oetjen-Gerdes, T. E. Rasmussen, F. K. Butler, R. S. Kotwal, J. B. Holcomb, C. Wade, H. Champion, M. Lawnick, L. Moores, and L. H. Blackbourne, “Death on the battlefield (2001–2011),” Journal of Trauma and Acute Care Surgery, vol. 73, no. 6, 2012. [4] B. J. Eastridge, J. B. Holcomb, and S. Shackelford, “Outcomes of traumatic hemorrhagic shock and the epidemiology of preventable death from injury,” Transfusion, vol. 59, no. S2, pp. 1423–1428, 2019. [5] A. W. Kirkpatrick, H. Tien, A. T. LaPorta, K. Lavell, J. Keillor, H. E. Wright Beatty, J. L. McKee, S. Brien, D. J. Roberts, J. Wong, C. G. Ball, and A. Beckett, “The marriage of surgical simulation and telementoring for damage-control surgical training of operational first responders,” Journal of Trauma and Acute Care Surgery, vol. 79, no. 5, pp. 741–747, 2015.