@inproceedings{yan-etal-2021-control,
title = "Control Image Captioning Spatially and Temporally",
author = "Yan, Kun and
Ji, Lei and
Luo, Huaishao and
Zhou, Ming and
Duan, Nan and
Ma, Shuai",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.157/",
doi = "10.18653/v1/2021.acl-long.157",
pages = "2014--2025",
abstract = "Generating image captions with user intention is an emerging need. The recently published Localized Narratives dataset takes mouse traces as another input to the image captioning task, which is an intuitive and efficient way for a user to control what to describe in the image. However, how to effectively employ traces to improve generation quality and controllability is still under exploration. This paper aims to solve this problem by proposing a novel model called LoopCAG, which connects Contrastive constraints and Attention Guidance in a Loop manner, engaged explicit spatial and temporal constraints to the generating process. Precisely, each generated sentence is temporally aligned to the corresponding trace sequence through a contrastive learning strategy. Besides, each generated text token is supervised to attend to the correct visual objects under heuristic spatial attention guidance. Comprehensive experimental results demonstrate that our LoopCAG model learns better correspondence among the three modalities (vision, language, and traces) and achieves SOTA performance on trace-controlled image captioning task. Moreover, the controllability and explainability of LoopCAG are validated by analyzing spatial and temporal sensitivity during the generation process."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2021-control">
<titleInfo>
<title>Control Image Captioning Spatially and Temporally</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaishao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating image captions with user intention is an emerging need. The recently published Localized Narratives dataset takes mouse traces as another input to the image captioning task, which is an intuitive and efficient way for a user to control what to describe in the image. However, how to effectively employ traces to improve generation quality and controllability is still under exploration. This paper aims to solve this problem by proposing a novel model called LoopCAG, which connects Contrastive constraints and Attention Guidance in a Loop manner, engaged explicit spatial and temporal constraints to the generating process. Precisely, each generated sentence is temporally aligned to the corresponding trace sequence through a contrastive learning strategy. Besides, each generated text token is supervised to attend to the correct visual objects under heuristic spatial attention guidance. Comprehensive experimental results demonstrate that our LoopCAG model learns better correspondence among the three modalities (vision, language, and traces) and achieves SOTA performance on trace-controlled image captioning task. Moreover, the controllability and explainability of LoopCAG are validated by analyzing spatial and temporal sensitivity during the generation process.</abstract>
<identifier type="citekey">yan-etal-2021-control</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.157</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.157/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2014</start>
<end>2025</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Control Image Captioning Spatially and Temporally
%A Yan, Kun
%A Ji, Lei
%A Luo, Huaishao
%A Zhou, Ming
%A Duan, Nan
%A Ma, Shuai
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F yan-etal-2021-control
%X Generating image captions with user intention is an emerging need. The recently published Localized Narratives dataset takes mouse traces as another input to the image captioning task, which is an intuitive and efficient way for a user to control what to describe in the image. However, how to effectively employ traces to improve generation quality and controllability is still under exploration. This paper aims to solve this problem by proposing a novel model called LoopCAG, which connects Contrastive constraints and Attention Guidance in a Loop manner, engaged explicit spatial and temporal constraints to the generating process. Precisely, each generated sentence is temporally aligned to the corresponding trace sequence through a contrastive learning strategy. Besides, each generated text token is supervised to attend to the correct visual objects under heuristic spatial attention guidance. Comprehensive experimental results demonstrate that our LoopCAG model learns better correspondence among the three modalities (vision, language, and traces) and achieves SOTA performance on trace-controlled image captioning task. Moreover, the controllability and explainability of LoopCAG are validated by analyzing spatial and temporal sensitivity during the generation process.
%R 10.18653/v1/2021.acl-long.157
%U https://aclanthology.org/2021.acl-long.157/
%U https://doi.org/10.18653/v1/2021.acl-long.157
%P 2014-2025
Markdown (Informal)
[Control Image Captioning Spatially and Temporally](https://aclanthology.org/2021.acl-long.157/) (Yan et al., ACL-IJCNLP 2021)
ACL
- Kun Yan, Lei Ji, Huaishao Luo, Ming Zhou, Nan Duan, and Shuai Ma. 2021. Control Image Captioning Spatially and Temporally. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2014–2025, Online. Association for Computational Linguistics.