Counterfactual visual dialog: Robust commonsense knowledge learning from unbiased training
Visual Dialog (VD) requires an agent to answer the current question by engaging in a
conversation with humans referring to an image. Despite the recent progress, it is beneficial …
conversation with humans referring to an image. Despite the recent progress, it is beneficial …
Knowledge-aware causal inference network for visual dialog
Z Zhang, Y Ji, C Liu - Proceedings of the 2023 ACM International …, 2023 - dl.acm.org
The effective knowledge and interaction within multi-modalities are key to Visual Dialog.
Classic graph-based framework with the direct connection between history dialog and …
Classic graph-based framework with the direct connection between history dialog and …
[HTML][HTML] A fine-grained deconfounding study for knowledge-based visual dialog
AA Liu, Q Wu, C Huang, C Xue, X Liu, N Xu - Visual Informatics, 2024 - Elsevier
Abstract Knowledge-based Visual Dialog is a challenging vision-language task, where an
agent engages in dialog to answer questions with humans based on the input image and …
agent engages in dialog to answer questions with humans based on the input image and …