A lighter network (like FlowNet) that estimates the motion between frames.
A heavy network (like ResNet) extracts "deep features" only from select frames. 5faafede261a08fdaba46_source.mp4
Labeling every pixel in the video (e.g., distinguishing "road" from "sidewalk"). A lighter network (like FlowNet) that estimates the
Following a specific target through various lighting and occlusion changes. 5faafede261a08fdaba46_source.mp4