Learning to Enforce and Utilize Temporal Consistency in Video Processing

PhD Thesis Proposal Defence


Title: "Learning to Enforce and Utilize Temporal Consistency in Video 
Processing"

by

Mr. Chenyang LEI


Abstract:

Countless videos exist in the world with diverse contents and styles. However, 
in many cases, the original videos captured or created are not perfect, and 
many algorithms are proposed to process these diverse videos for various 
purposes. Video temporal consis- tency is a common goal for various video 
processing algorithms, while these algorithms are designed for different 
downstream applications. The video temporal consistency de- notes the property 
that correspondences of consecutive frames in a video share the consis- tent 
features (e.g., color). Video temporal consistency in video processing is 
challenging since it is related to several hard problems in computer vision. 
This thesis focuses on studying the video temporal consistency problem with 
machine learning. Since temporal consistency is a common goal for video 
processing algorithms, can deep networks learn the temporal consistency from 
large-scale data or few data? We try to propose several approaches that can 
obtain satisfying performance on various video processing tasks.


Date:			Friday, 29 April 2022

Time:                  	2:00pm - 4:00pm

Zoom Meeting:
https://hkust.zoom.us/j/2788883395?pwd=cnpKL01vZ2t3ZEZyQy9UWnVZM3RWUT09

Committee Members:	Dr. Qifeng Chen (Supervisor)
  			Dr. Dan Xu (Chairperson)
 			Prof. Pedro Sander
 			Prof. Chiew-Lan Tai


**** ALL are Welcome ****