Exploring Human-Object Interaction Detection
Year: 2020
Type: dissertation
Abstract: Human-object interaction detection is a relatively new task in the world of computer vision and visual semantic information extraction. The goal of human-object interaction detection is to have machines identifying interactions that humans perform on objects. We provide a basic survey of the developments in the field of human object interaction detection. Many works in this field use multi-stream convolutional neural network architectures, which combine features from multiple sources in the input image. To provide insight to future researchers, we perform a study examining the performance of each component of a multi-stream architecture for human-object interaction detection. We examine the HORCNN architecture as a foundational work in the field. We also provide an in-depth look at the HICO-DET dataset, a popular benchmark in the field of human object interaction detection. Lastly, we begin the construction of a human-object interaction benchmarking platform.
Author: Trevor Bergstrom
Institution: University of Oregon
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: University of Oregon
OpenAlex ID: W3137937148
