Read, Look or Listen? What's Needed for Solving a Multimodal Dataset

no code implementations • 6 Jul 2023 • Netta Madvil, Yonatan Bitton, Roy Schwartz

We propose a two-step method to analyze multimodal datasets, which leverages a small seed of human annotation to map each multimodal instance to the modalities required to process it.

Question Answering Speaker Identification +1