paper-with-me

홈 › Papers

History for Visual Dialog: Do we really need it?

2020-05-08 · ACL 2020 6 · Shubham Agarwal, Trung Bui, Joon-Young Lee, Ioannis Konstas, Verena Rieser

Visual Dialog involves "understanding" the dialog history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to generate the correct response. In this paper, we show that co-attention models which explicitly encode dialog history outperform models that don't, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowd-sourcing dataset collection procedure by showing that history is indeed only required for a small amount of the data and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisDialConv) of the VisDial val set and provide a benchmark of 63% NDCG.

📄 PDF Abstract BibTeX arXiv:2005.07493

Code (2)

shubhamagarwal92/visdial_conv 공식 구현 pytorch
shubhamagarwal92/visdialconv-amt 공식 구현

Tasks

Visual Dialog

Similar Papers 제목 키워드 기반

Region under Discussion for visual dialog

2021-11-01 · EMNLP 2021 11 · Mauricio Mazuecos, Franco M. Luque, Jorge Sánchez, Hernán Maina 외

Visual Dialog is assumed to require the dialog history to generate correct responses during a dialog. However, it is not clear from previous work how dialog history is needed for visual dialog. In this paper we define wh…

Visual Dialog

Recursive Visual Attention in Visual Dialog

2018-12-06 · CVPR 2019 6 · Yulei Niu, Hanwang Zhang, Manli Zhang, Jianhong Zhang 외

Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded question…

Question AnsweringVisual DialogVisual Question AnsweringVisual Question Answering (VQA)

Modality-Balanced Models for Visual Dialogue

2020-01-17 · Hyounghun Kim, Hao Tan, Mohit Bansal

The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we find that a large number of conversatio…

Visual Dialog

GoG: Relation-aware Graph-over-Graph Network for Visual Dialog

2021-09-17 · Findings (ACL) 2021 8 · Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li 외

Visual dialog, which aims to hold a meaningful conversation with humans about a given image, is a challenging task that requires models to reason the complex dependencies among visual content, dialog history, and current…

coreference-resolutionCoreference ResolutionImplicit RelationsRelation+1

VD-BERT: A Unified Vision and Dialog Transformer with BERT

2020-04-28 · EMNLP 2020 11 · Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King 외

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attentio…

Answer GenerationVisual Dialog