@inproceedings{lin-etal-2020-semi,
title = "Semi-Supervised Learning for Video Captioning",
author = "Lin, Ke and
Gan, Zhuoxin and
Wang, Liwei",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.98",
doi = "10.18653/v1/2020.findings-emnlp.98",
pages = "1096--1106",
abstract = "Deep neural networks have made great success on video captioning in supervised learning setting. However, annotating videos with descriptions is very expensive and time-consuming. If the video captioning algorithm can benefit from a large number of unlabeled videos, the cost of annotation can be reduced. In the proposed study, we make the first attempt to train the video captioning model on labeled data and unlabeled data jointly, in a semi-supervised learning manner. For labeled data, we train them with the traditional cross-entropy loss. For unlabeled data, we leverage a self-critical policy gradient method with the difference between the scores obtained by Monte-Carlo sampling and greedy decoding as the reward function, while the scores are the negative K-L divergence between output distributions of original video data and augmented video data. The final loss is the weighted sum of losses obtained by labeled data and unlabeled data. Experiments conducted on VATEX, MSR-VTT and MSVD dataset demonstrate that the introduction of unlabeled data can improve the performance of the video captioning model. The proposed semi-supervised learning algorithm also outperforms several state-of-the-art semi-supervised learning approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2020-semi">
<titleInfo>
<title>Semi-Supervised Learning for Video Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoxin</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liwei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep neural networks have made great success on video captioning in supervised learning setting. However, annotating videos with descriptions is very expensive and time-consuming. If the video captioning algorithm can benefit from a large number of unlabeled videos, the cost of annotation can be reduced. In the proposed study, we make the first attempt to train the video captioning model on labeled data and unlabeled data jointly, in a semi-supervised learning manner. For labeled data, we train them with the traditional cross-entropy loss. For unlabeled data, we leverage a self-critical policy gradient method with the difference between the scores obtained by Monte-Carlo sampling and greedy decoding as the reward function, while the scores are the negative K-L divergence between output distributions of original video data and augmented video data. The final loss is the weighted sum of losses obtained by labeled data and unlabeled data. Experiments conducted on VATEX, MSR-VTT and MSVD dataset demonstrate that the introduction of unlabeled data can improve the performance of the video captioning model. The proposed semi-supervised learning algorithm also outperforms several state-of-the-art semi-supervised learning approaches.</abstract>
<identifier type="citekey">lin-etal-2020-semi</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.98</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.98</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1096</start>
<end>1106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-Supervised Learning for Video Captioning
%A Lin, Ke
%A Gan, Zhuoxin
%A Wang, Liwei
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lin-etal-2020-semi
%X Deep neural networks have made great success on video captioning in supervised learning setting. However, annotating videos with descriptions is very expensive and time-consuming. If the video captioning algorithm can benefit from a large number of unlabeled videos, the cost of annotation can be reduced. In the proposed study, we make the first attempt to train the video captioning model on labeled data and unlabeled data jointly, in a semi-supervised learning manner. For labeled data, we train them with the traditional cross-entropy loss. For unlabeled data, we leverage a self-critical policy gradient method with the difference between the scores obtained by Monte-Carlo sampling and greedy decoding as the reward function, while the scores are the negative K-L divergence between output distributions of original video data and augmented video data. The final loss is the weighted sum of losses obtained by labeled data and unlabeled data. Experiments conducted on VATEX, MSR-VTT and MSVD dataset demonstrate that the introduction of unlabeled data can improve the performance of the video captioning model. The proposed semi-supervised learning algorithm also outperforms several state-of-the-art semi-supervised learning approaches.
%R 10.18653/v1/2020.findings-emnlp.98
%U https://aclanthology.org/2020.findings-emnlp.98
%U https://doi.org/10.18653/v1/2020.findings-emnlp.98
%P 1096-1106
Markdown (Informal)
[Semi-Supervised Learning for Video Captioning](https://aclanthology.org/2020.findings-emnlp.98) (Lin et al., Findings 2020)
ACL
- Ke Lin, Zhuoxin Gan, and Liwei Wang. 2020. Semi-Supervised Learning for Video Captioning. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1096–1106, Online. Association for Computational Linguistics.