Learning to represent scenes with geometry and semantics
<p>Scene representation is the process of converting sensory observations of an environment into compact descriptions. Such intelligent behavior is a cornerstone of artificial intelligence. Scientists have long sought to reproduce the extraordinary ability of humans for understanding the physi...
Main Author: | Wang, B |
---|---|
Other Authors: | Trigoni, A |
Format: | Thesis |
Language: | English |
Published: |
2022
|
Subjects: |
Similar Items
-
Pixel-level scene understanding with deep structured models
by: Arnab, A
Published: (2019) -
Holistic, instance-level scene parsing with deep neural networks
by: Li, Q
Published: (2020) -
Unifying motion segmentation, estimation, and tracking for complex dynamic scenes
by: Judd, K
Published: (2019) -
Effective representations for road scene understanding with scalable learning
by: Bruls, TAH
Published: (2020) -
Learning distributional uncertainty estimation for semantic segmentation
by: Williams, D
Published: (2024)