|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i. e., masked language/region modeling is conditioned on full observation of image/text).
Ranked #1 on Visual Reasoning on NLVR2 Test
We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning.
We evaluate various existing VQA baselines and build a model called Explainable Visual Entailment (EVE) system to address the VE task.
Ranked #1 on Visual Entailment on SNLI-VE val
We introduce a new inference task - Visual Entailment (VE) - which differs from traditional Textual Entailment (TE) tasks whereby a premise is defined by an image, rather than a natural language sentence as in TE tasks.