clulab / twitter4food

Repository for the health informatics analytics on twitter project
Apache License 2.0
1 stars 4 forks source link

Multi-modal classification: object recognition #13

Open herongrove opened 7 years ago

herongrove commented 7 years ago

Use off-the-shelf (e.g. AlexNet) object recognition on a user's Twitter and Instagram photos to generate features for the SVM classifier. For example, if the user has a picture of a dog catching a frisbee on a lawn, you may generate imgCls:rottweiler, imgCls:grass, imgCls:cloud, etc.