<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/bfb330c56d66456695c7c1e25401d12e&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/bfb330c56d66456695c7c1e25401d12e-85feaf4ccd146196.gif</thumbnail_url><duration>73.203</duration><title>DeepSight Part 2</title><description>This Loom checks the output of a video emotion analysis after processing is complete. The video took about 7 minutes to process, which the author says is typical for a model of this size. The output includes a video editor style timeline showing emotion values at each timestamp, starting with labels like afraid, depressed, excited, and delighted, with exaggerated numbers for display. It also shows corresponding FMRI output alongside the emotion timeline.</description></oembed>