paper-with-me

홈 › Papers

VU-BERT: A Unified framework for Visual Dialog

2022-02-22 · Tong Ye, Shijing Si, Jianzong Wang, Rui Wang, Ning Cheng, Jing Xiao

The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog history. Existing researches tend to employ the modality-specific modules to model the interactions, which might be troublesome to use. To fill in this gap, we propose a unified framework for image-text joint embedding, named VU-BERT, and apply patch projection to obtain vision embedding firstly in visual dialog tasks to simplify the model. The model is trained over two tasks: masked language modeling and next utterance retrieval. These tasks help in learning visual concepts, utterances dependence, and the relationships between these two modalities. Finally, our VU-BERT achieves competitive performance (0.7287 NDCG scores) on VisDial v1.0 Datasets.

📄 PDF Abstract BibTeX arXiv:2202.10787

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMasked Language ModelingRetrievalVisual Dialog

Similar Papers 제목 키워드 기반

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

Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation

2021-05-24 · CVPR 2021 1 · Tao Tu, Qing Ping, Govind Thattai, Gokhan Tur 외

GuessWhat?! is a two-player visual dialog guessing game where player A asks a sequence of yes/no questions (Questioner) and makes a final guess (Guesser) about a target object in an image, based on answers from player B …

Referring ExpressionReferring Expression ComprehensionVisual DialogVisual Grounding

GRAVL-BERT: Graphical Visual-Linguistic Representations for Multimodal Coreference Resolution

2022-10-01 · COLING 2022 10 · Danfeng Guo, Arpit Gupta, Sanchit Agarwal, Jiun-Yu Kao 외

Learning from multimodal data has become a popular research topic in recent years. Multimodal coreference resolution (MCR) is an important task in this area. MCR involves resolving the references across different modalit…

coreference-resolutionCoreference ResolutionVisual Grounding

Unified Multimodal Model with Unlikelihood Training for Visual Dialog

2022-11-23 · ZiHao Wang, Junli Wang, Changjun Jiang

The task of visual dialog requires a multimodal chatbot to answer sequential questions from humans about image content. Prior work performs the standard likelihood training for answer generation on the positive instances…

Answer GenerationChatbotLanguage ModelingLanguage Modelling+3

Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning

2022-04-15 · Feilong Chen, Xiuyi Chen, Shuang Xu, Bo Xu

Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though existing methods try to deal …

Contrastive LearningQuestion AnsweringVisual DialogVisual Question Answering+1