Choosing Basic-Level Concept Names Using Visual and Language Context

Abstract

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 thou-sands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong improvement over re-cent work by Ordonez et al, by modeling of both visual and language context. Our study suggests that a model for nam-ing visual concepts is an important part of any automatic image/video captioning and visual story-telling system. 1.

Cite

Text

Mathews et al. "Choosing Basic-Level Concept Names Using Visual and Language Context." IEEE/CVF Winter Conference on Applications of Computer Vision, 2015. doi:10.1109/WACV.2015.85

Markdown

[Mathews et al. "Choosing Basic-Level Concept Names Using Visual and Language Context." IEEE/CVF Winter Conference on Applications of Computer Vision, 2015.](https://mlanthology.org/wacv/2015/mathews2015wacv-choosing/) doi:10.1109/WACV.2015.85

BibTeX

@inproceedings{mathews2015wacv-choosing,
  title     = {{Choosing Basic-Level Concept Names Using Visual and Language Context}},
  author    = {Mathews, Alexander Patrick and Xie, Lexing and He, Xuming},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2015},
  pages     = {595-602},
  doi       = {10.1109/WACV.2015.85},
  url       = {https://mlanthology.org/wacv/2015/mathews2015wacv-choosing/}
}