Multi-View Attention Networks for Visual Dialog

By Sungjin Park, Taesun Whang, Y. Yoon, Hueiseok Lim. 2020

25 citations recorded by the source corpus.

Visual dialog is a challenging vision-language task in which a series of questions visually grounded by a given image are answered. To resolve the visual dialog task, a high-level understanding of various multimodal inputs (e.g., question, dialog history, and image) is required. Specifically, it is necessary for an agent to (1) determine the semantic intent of question and (2) align question-relevant textual and visual contents among heterogeneous modality inputs. In this paper, we propose Multi-View Attention Network (MVAN), which leverages multiple views about heterogeneous inputs based on attention mechanisms. MVAN effectively captures the question-relevant information from the dialog history with two complementary modules (i.e., Topic Aggregation and Context Matching), and builds multimodal representations through sequential alignment processes (i.e., Modality Alignment). Experimental results on VisDial v1.0 dataset show the effectiveness of our proposed model, which outperforms previous state-of-the-art methods under both single model and ensemble settings.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

Multi-Modal Open-Domain Dialogue (2020, background): “Other recent architectures have explored text generation (Wang et al., 2020; Park et al., 2020) in the context of the Visual Dialog (Das et al., 2017b) task; however, this task is primarily used to measure a model’s ability to answer questions about an image in the ﬂow of a natural conversation,…”