@inproceedings{wang-etal-2019-youmakeup,
title = "{Y}ou{M}akeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension",
author = "Wang, Weiying and
Wang, Yongcheng and
Chen, Shizhe and
Jin, Qin",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1517",
doi = "10.18653/v1/D19-1517",
pages = "5133--5143",
abstract = "Multimodal semantic comprehension has attracted increasing research interests recently such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension has not been well investigated, which requires to capture semantic details of multimodal contents. In this work, we introduce {``}YouMakeup{''}, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which requires fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models{'} ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering from different aspects. We also establish a baseline of step caption generation for future comparison. The dataset will be publicly available at \url{https://github.com/AIM3-RUC/YouMakeup} to support research investigation in fine-grained semantic comprehension.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2019-youmakeup">
<titleInfo>
<title>YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiying</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongcheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhe</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal semantic comprehension has attracted increasing research interests recently such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension has not been well investigated, which requires to capture semantic details of multimodal contents. In this work, we introduce “YouMakeup”, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which requires fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models’ ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering from different aspects. We also establish a baseline of step caption generation for future comparison. The dataset will be publicly available at https://github.com/AIM3-RUC/YouMakeup to support research investigation in fine-grained semantic comprehension.</abstract>
<identifier type="citekey">wang-etal-2019-youmakeup</identifier>
<identifier type="doi">10.18653/v1/D19-1517</identifier>
<location>
<url>https://aclanthology.org/D19-1517</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>5133</start>
<end>5143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension
%A Wang, Weiying
%A Wang, Yongcheng
%A Chen, Shizhe
%A Jin, Qin
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F wang-etal-2019-youmakeup
%X Multimodal semantic comprehension has attracted increasing research interests recently such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension has not been well investigated, which requires to capture semantic details of multimodal contents. In this work, we introduce “YouMakeup”, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which requires fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models’ ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering from different aspects. We also establish a baseline of step caption generation for future comparison. The dataset will be publicly available at https://github.com/AIM3-RUC/YouMakeup to support research investigation in fine-grained semantic comprehension.
%R 10.18653/v1/D19-1517
%U https://aclanthology.org/D19-1517
%U https://doi.org/10.18653/v1/D19-1517
%P 5133-5143
Markdown (Informal)
[YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension](https://aclanthology.org/D19-1517) (Wang et al., EMNLP-IJCNLP 2019)
ACL