Skip to content

Taskboard

Jump to bottom Edit New page
Satwik Kottur edited this page Jun 5, 2015 · 17 revisions

Taskboard for VisualWord2Vec!

Code

  • Understand the source code figuring out what each piece does with respect to the ICCV paper (8 June)
  • Comment, clean out irrelevant parts for the current work (12 June)
  • Install and setup Caffe framework (12 June)
  • Cluster the visual vectors, refine trained CNN to classify into one of the clusters, get new word2vec features (15 June)

Ideas

How to incorporate visual features in word2vec?

  1. Group the visual features obtained for 213 verbs into N clusters. Refine the trained CNN to predict the cluster id. Obtain the features from this modified CNN.
  2. ?

Resources

Add a custom footer
Add a custom sidebar
Clone this wiki locally