Recognition and Localization of Food in Cooking Videos - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Recognition and Localization of Food in Cooking Videos

Résumé

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.
Fichier principal
Vignette du fichier
paper-cea18-hal.pdf (826.38 Ko) Télécharger le fichier
Recognition and localization of food in Cooking Videos.pdf (5.49 Mo) Télécharger le fichier
annotation_json.zip (184.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01815512 , version 1 (14-06-2018)
hal-01815512 , version 2 (14-06-2018)
hal-01815512 , version 3 (06-07-2018)

Identifiants

Citer

Nachwa Aboubakr, Rémi Ronfard, James L. Crowley. Recognition and Localization of Food in Cooking Videos. Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management (CEA-MADiMa 2018), Jul 2018, Stockholm, Sweden. pp.21-24, ⟨10.1145/3230519.3230590⟩. ⟨hal-01815512v3⟩
683 Consultations
846 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More