A System for Large-Scale Image and Video Retrieval on Everyday Scenes
Published in University of Missouri-Columbia, 2022
Recommended citation: Arun George Zachariah - "A System for Large-Scale Image and Video Retrieval on Everyday Scenes." Doctoral dissertation, University of Missouri-Columbia, 2022. /files/Arun_George_Zachariah_Dissertation.pdf
There has been a growing amount of multimedia data generated on the web today in terms of size and diversity. This has made accurate retrieval from these large and complex collections of data a challenging problem. Motivated by the need for systems that can enable scalable and efficient search, this dissertation proposes QIK (Querying Images Using Contextual Knowledge), a system that leverages deep learning and natural language processing for large-scale image and video retrieval of everyday scenes with common objects.