Drill-down: Interactive retrieval of complex scenes using natural language queriesFuwen TanPaola Cascante-Bonillaet al.2019NeurIPS 2019
SimVQA: Exploring Simulated Environments for Visual Question AnsweringPaola Cascante-BonillaHui Wuet al.2022CVPR 2022
Chat-crowd: A dialog-based platform for visual layout compositionPaola Cascante-BonillaXuwang Yinet al.2019NAACL 2019