MIDL Vision 2020

with Fabio Cuzzolin 19 Fabio adds: “This challenge task was pure single frame detection, whereas here in Brookes we are world leaders in action tube detection. So, not just detecting the bounding boxes frame by frame, but detecting the entire action instance described as a series of bounding boxes linked up in time, which people call action tubes in the literature. The baseline that we used in this challenge is based on the RetinaNet object detector because the task was frame-level detection. It was not about detecting the entire action tubes. For the MICCAI challenge we plan to use our own online action tube detection method, which was published at ICCV 2017 in collaboration with Oxford University. It is the main paper that we have published on this topic and has achieved around 150 citations in just two years, so we are very happy with its impact.” The SARAS endoscopic vision challenge for surgeon action detection (SARAS-ESAD) takes place tomorrow (Thursday) at 09:00-13:00.