ResearchDatasetsVQA, ImageNet, Flickr, OCRVQA, RefCOCO, HQEditVQA, ImageNet, Flickr, OCRVQA, RefCOCO, HQEditFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-modal Continual LearningVQAv2, ImageNet, Flickr30k, OCRVQA, RefCOCO, HQEdit sequence62.72VQAv2 Accuracy10
Multi-modal Continual LearningVQAv2, ImageNet, Flickr30k, OCRVQA, RefCOCO, HQEdit sequence62.72VQAv2 Accuracy10