@inproceedings{guo-etal-2021-multi,
title = "Multi-Scale Progressive Attention Network for Video Question Answering",
author = "Guo, Zhicheng and
Zhao, Jiaxuan and
Jiao, Licheng and
Liu, Xu and
Li, Lingling",
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 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.122",
doi = "10.18653/v1/2021.acl-short.122",
pages = "973--978",
abstract = "Understanding the multi-scale visual information in a video is essential for Video Question Answering (VideoQA). Therefore, we propose a novel Multi-Scale Progressive Attention Network (MSPAN) to achieve relational reasoning between cross-scale video information. We construct clips of different lengths to represent different scales of the video. Then, the clip-level features are aggregated into node features by using max-pool, and a graph is generated for each scale of clips. For cross-scale feature interaction, we design a message passing strategy between adjacent scale graphs, i.e., top-down scale interaction and bottom-up scale interaction. Under the question{'}s guidance of progressive attention, we realize the fusion of all-scale video features. Experimental evaluations on three benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA show our method has achieved state-of-the-art performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2021-multi">
<titleInfo>
<title>Multi-Scale Progressive Attention Network for Video Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxuan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Licheng</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingling</namePart>
<namePart type="family">Li</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 2: Short 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>Understanding the multi-scale visual information in a video is essential for Video Question Answering (VideoQA). Therefore, we propose a novel Multi-Scale Progressive Attention Network (MSPAN) to achieve relational reasoning between cross-scale video information. We construct clips of different lengths to represent different scales of the video. Then, the clip-level features are aggregated into node features by using max-pool, and a graph is generated for each scale of clips. For cross-scale feature interaction, we design a message passing strategy between adjacent scale graphs, i.e., top-down scale interaction and bottom-up scale interaction. Under the question’s guidance of progressive attention, we realize the fusion of all-scale video features. Experimental evaluations on three benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA show our method has achieved state-of-the-art performance.</abstract>
<identifier type="citekey">guo-etal-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.122</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.122</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>973</start>
<end>978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Scale Progressive Attention Network for Video Question Answering
%A Guo, Zhicheng
%A Zhao, Jiaxuan
%A Jiao, Licheng
%A Liu, Xu
%A Li, Lingling
%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 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F guo-etal-2021-multi
%X Understanding the multi-scale visual information in a video is essential for Video Question Answering (VideoQA). Therefore, we propose a novel Multi-Scale Progressive Attention Network (MSPAN) to achieve relational reasoning between cross-scale video information. We construct clips of different lengths to represent different scales of the video. Then, the clip-level features are aggregated into node features by using max-pool, and a graph is generated for each scale of clips. For cross-scale feature interaction, we design a message passing strategy between adjacent scale graphs, i.e., top-down scale interaction and bottom-up scale interaction. Under the question’s guidance of progressive attention, we realize the fusion of all-scale video features. Experimental evaluations on three benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA show our method has achieved state-of-the-art performance.
%R 10.18653/v1/2021.acl-short.122
%U https://aclanthology.org/2021.acl-short.122
%U https://doi.org/10.18653/v1/2021.acl-short.122
%P 973-978
Markdown (Informal)
[Multi-Scale Progressive Attention Network for Video Question Answering](https://aclanthology.org/2021.acl-short.122) (Guo et al., ACL-IJCNLP 2021)
ACL
- Zhicheng Guo, Jiaxuan Zhao, Licheng Jiao, Xu Liu, and Lingling Li. 2021. Multi-Scale Progressive Attention Network for Video Question Answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 973–978, Online. Association for Computational Linguistics.