@inproceedings{lian-etal-2021-sketchy,
title = "Sketchy Scene Captioning: Learning Multi-Level Semantic Information from Sparse Visual Scene Cues",
author = "Lian, Zhou and
Yangdong, Chen and
Yuejie, Zhang",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.104",
pages = "1167--1177",
abstract = "To enrich the research about sketch modality a new task termed Sketchy Scene Captioning isproposed in this paper. This task aims to generate sentence-level and paragraph-level descrip-tions for a sketchy scene. The sentence-level description provides the salient semantics of asketchy scene while the paragraph-level description gives more details about the sketchy scene. Sketchy Scene Captioning can be viewed as an extension of sketch classification which can onlyprovide one class label for a sketch. To generate multi-level descriptions for a sketchy scene ischallenging because of the visual sparsity and ambiguity of the sketch modality. To achieve ourgoal we first contribute a sketchy scene captioning dataset to lay the foundation of this new task. The popular sequence learning scheme e.g. Long Short-Term Memory neural network with vi-sual attention mechanism is then adopted to recognize the objects in a sketchy scene and inferthe relations among the objects. In the experiments promising results have been achieved on the proposed dataset. We believe that this work will motivate further researches on the understanding of sketch modality and the numerous sketch-based applications in our daily life. The collected dataset is released at \url{https://github.com/SketchysceneCaption/Dataset}.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lian-etal-2021-sketchy">
<titleInfo>
<title>Sketchy Scene Captioning: Learning Multi-Level Semantic Information from Sparse Visual Scene Cues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Yangdong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Yuejie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To enrich the research about sketch modality a new task termed Sketchy Scene Captioning isproposed in this paper. This task aims to generate sentence-level and paragraph-level descrip-tions for a sketchy scene. The sentence-level description provides the salient semantics of asketchy scene while the paragraph-level description gives more details about the sketchy scene. Sketchy Scene Captioning can be viewed as an extension of sketch classification which can onlyprovide one class label for a sketch. To generate multi-level descriptions for a sketchy scene ischallenging because of the visual sparsity and ambiguity of the sketch modality. To achieve ourgoal we first contribute a sketchy scene captioning dataset to lay the foundation of this new task. The popular sequence learning scheme e.g. Long Short-Term Memory neural network with vi-sual attention mechanism is then adopted to recognize the objects in a sketchy scene and inferthe relations among the objects. In the experiments promising results have been achieved on the proposed dataset. We believe that this work will motivate further researches on the understanding of sketch modality and the numerous sketch-based applications in our daily life. The collected dataset is released at https://github.com/SketchysceneCaption/Dataset.</abstract>
<identifier type="citekey">lian-etal-2021-sketchy</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.104</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1167</start>
<end>1177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sketchy Scene Captioning: Learning Multi-Level Semantic Information from Sparse Visual Scene Cues
%A Lian, Zhou
%A Yangdong, Chen
%A Yuejie, Zhang
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G English
%F lian-etal-2021-sketchy
%X To enrich the research about sketch modality a new task termed Sketchy Scene Captioning isproposed in this paper. This task aims to generate sentence-level and paragraph-level descrip-tions for a sketchy scene. The sentence-level description provides the salient semantics of asketchy scene while the paragraph-level description gives more details about the sketchy scene. Sketchy Scene Captioning can be viewed as an extension of sketch classification which can onlyprovide one class label for a sketch. To generate multi-level descriptions for a sketchy scene ischallenging because of the visual sparsity and ambiguity of the sketch modality. To achieve ourgoal we first contribute a sketchy scene captioning dataset to lay the foundation of this new task. The popular sequence learning scheme e.g. Long Short-Term Memory neural network with vi-sual attention mechanism is then adopted to recognize the objects in a sketchy scene and inferthe relations among the objects. In the experiments promising results have been achieved on the proposed dataset. We believe that this work will motivate further researches on the understanding of sketch modality and the numerous sketch-based applications in our daily life. The collected dataset is released at https://github.com/SketchysceneCaption/Dataset.
%U https://aclanthology.org/2021.ccl-1.104
%P 1167-1177
Markdown (Informal)
[Sketchy Scene Captioning: Learning Multi-Level Semantic Information from Sparse Visual Scene Cues](https://aclanthology.org/2021.ccl-1.104) (Lian et al., CCL 2021)
ACL