Despite the superior performance brought by vision-and-language pretrain...
Visual Question Answering (VQA) models often perform poorly on
out-of-di...
Our commonsense knowledge about objects includes their typical visual
at...
While Visual Question Answering (VQA) has progressed rapidly, previous w...
While neural symbolic methods demonstrate impressive performance in visu...
While image captioning has progressed rapidly, existing works focus main...
Person re-identification (reID) is an important task that requires to
re...