Beyond Labels and Captions: Contextualizing Grounded Semantics for Explainable Visual Interpretation
One of the long-standing problems in artificial intelligence is the development of intelligent agents with complete visual understanding. Understanding entails recognition of scene attributes such as actors, objects and actions as well as reasoning about the common semantic structure that combines t...
Main Author: | Aakur, Sathyanarayanan Narasimhan |
---|---|
Format: | Others |
Published: |
Scholar Commons
2019
|
Subjects: | |
Online Access: | https://scholarcommons.usf.edu/etd/7718 https://scholarcommons.usf.edu/cgi/viewcontent.cgi?article=8915&context=etd |
Similar Items
-
Classifying literary genres
by: Abdulfattah Omar
Published: (2020-07-01) -
LAM: Remote Sensing Image Captioning with Label-Attention Mechanism
by: Zhengyuan Zhang, et al.
Published: (2019-10-01) -
Exploring Multi-Level Attention and Semantic Relationship for Remote Sensing Image Captioning
by: Zhenghang Yuan, et al.
Published: (2020-01-01) -
Image Caption Generation Using Multi-Level Semantic Context Information
by: Peng Tian, et al.
Published: (2021-06-01) -
Semantics-Driven Remote Sensing Scene Understanding Framework for Grounded Spatio-Contextual Scene Descriptions
by: Abhishek V. Potnis, et al.
Published: (2021-01-01)