Pursuing Mid-level Perception from Casual Videos

This thesis aims to summarize a series of explorations around a central theme: How can we learn mid-level perception from collections of casually shot videos? To avoid reader’s disappointment, I would like to be frank at the start: contents within are only starting steps towards solving the problem....

Full description

Bibliographic Details
Main Author: Zhang, Zhoutong
Other Authors: Freeman, William T.
Format: Thesis
Published: Massachusetts Institute of Technology 2023
Online Access:https://hdl.handle.net/1721.1/147336