Jethro's Braindump

Cross-modal Hashing

Cross-modal hashing is the compression of high dimensional data into compact binary codes with similar binary codes for similar objects. The key ideas is to create codes for cross-modal retrieval. The constraints are :

  1. It has to be an N-dimensional hamming space – a binary representation with a controllable number of bits.
  2. The same object from different modalities has to have a similar hash code
  3. The space has to be similarity-preserving

(Baltrušaitis, Ahuja, and Morency, n.d.) has some good reference papers.


Baltrušaitis, Tadas, Chaitanya Ahuja, and Louis-Philippe Morency. n.d. “Multimodal Machine Learning: A Survey and Taxonomy.”

Links to this note