Concept
VQA
VQA stands for Visual Question Answering: a model takes an image plus a natural-language question and produces a text answer. Think of it like image captioning, except the output is conditioned on a specific query rather than a generic description, so the model has to…
The rest of “VQA” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→