 |
Conference papers
Recognition and Localization of Food in Cooking Videos
Abstract : In this paper, we describe experiments with techniques for locating foods and recognizing food states in cooking videos. We describe production of a new data set that provides annotated images for food types and food states. We compare results with two techniques for detecting food types and food states, and then show that recognizing type and state with separate classifiers improves recognition results. We then use this to provide detection of composite activation maps for food types. The results provide a promising first step towards construction of narratives for cooking actions.
Keywords :
Object localization
Weakly supervised learning
Cited literature [18 references]
https://hal.archives-ouvertes.fr/hal-01815512
Contributor : Nachwa Aboubakr <>
Submitted on : Thursday, June 14, 2018 - 5:17:10 PM
Last modification on : Thursday, November 19, 2020 - 1:02:25 PM
Long-term archiving on: : Wednesday, September 26, 2018 - 5:41:11 PM
Contributor : Nachwa Aboubakr <>
Submitted on : Thursday, June 14, 2018 - 5:17:10 PM
Last modification on : Thursday, November 19, 2020 - 1:02:25 PM
Long-term archiving on: : Wednesday, September 26, 2018 - 5:41:11 PM
File
paper-cea18-hal.pdf
Files produced by the author(s)