Choosing Basic-Level Concept Names using Visual and Language Context
We study basic-level categories for describing visual concepts, and empirically observe context-dependant basic level names across thousands of concepts. We propose methods for predicting basic-level names using a series of classification and ranking tasks, producing the first large scale catalogue of basic-level names for hundreds of thousands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong...[Show more]
|Collections||ANU Research Publications|
|Source:||Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015|
|01_Mathews_Choosing_Basic-Level_Concept_2015.pdf||1.34 MB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.