Papers › Probabilistic framework for solving Visual Dialog

Probabilistic framework for solving Visual Dialog

11 Sep 2019arXiv:1909.04800archive 2025-07-28

Badri N. Patro, Anupriy, Vinay P. Namboodiri

In this paper, we propose a probabilistic framework for solving the task of `Visual Dialog'. Solving this task requires reasoning and understanding of visual modality, language modality, and common sense knowledge to answer. Various architectures have been proposed to solve this task by variants of multi-modal deep learning techniques that combine visual and language representations. However, we believe that it is crucial to understand and analyze the sources of uncertainty for solving this task. Our approach allows for estimating uncertainty and also aids a diverse generation of answers. The proposed approach is obtained through a probabilistic representation module that provides us with representations for image, question and conversation history, a module that ensures that diverse latent representations for candidate answers are obtained given the probabilistic representations and an uncertainty representation module that chooses the appropriate answer that minimizes uncertainty. We thoroughly evaluate the model with a detailed ablation analysis, comparison with state of the art and visualization of the uncertainty that aids in the understanding of the method. Using the proposed probabilistic framework, we thus obtain an improved visual dialog system that is also more explainable.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Common Sense ReasoningVisual Dialog

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning Visual Dialog v0.9 PDUN 1 in 10 R@5 81.0 #1 of 1 Archive leaderboard report
Common Sense Reasoning Visual Dialog v0.9 PDUN Recall@10 90.5 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections