@inproceedings{tang-etal-2021-decembert,
title = "{D}e{CEMBERT}: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization",
author = "Tang, Zineng and
Lei, Jie and
Bansal, Mohit",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.193",
doi = "10.18653/v1/2021.naacl-main.193",
pages = "2415--2426",
abstract = "Leveraging large-scale unlabeled web videos such as instructional videos for pre-training followed by task-specific finetuning has become the de facto approach for many video-and-language tasks. However, these instructional videos are very noisy, the accompanying ASR narrations are often incomplete, and can be irrelevant to or temporally misaligned with the visual content, limiting the performance of the models trained on such data. To address these issues, we propose an improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input, to provide informative visual cues for learning better video and language associations. Second, to alleviate the temporal misalignment issue, our method incorporates an entropy minimization-based constrained attention loss, to encourage the model to automatically focus on the correct caption from a pool of candidate ASR captions. Our overall approach is named DeCEMBERT (Dense Captions and Entropy Minimization). Comprehensive experiments on three video-and-language tasks (text-to-video retrieval, video captioning, and video question answering) across five datasets demonstrate that our approach outperforms previous state-of-the-art methods. Ablation studies on pre-training and downstream tasks show that adding dense captions and constrained attention loss help improve the model performance. Lastly, we also provide attention visualization to show the effect of applying the proposed constrained attention loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2021-decembert">
<titleInfo>
<title>DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zineng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Leveraging large-scale unlabeled web videos such as instructional videos for pre-training followed by task-specific finetuning has become the de facto approach for many video-and-language tasks. However, these instructional videos are very noisy, the accompanying ASR narrations are often incomplete, and can be irrelevant to or temporally misaligned with the visual content, limiting the performance of the models trained on such data. To address these issues, we propose an improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input, to provide informative visual cues for learning better video and language associations. Second, to alleviate the temporal misalignment issue, our method incorporates an entropy minimization-based constrained attention loss, to encourage the model to automatically focus on the correct caption from a pool of candidate ASR captions. Our overall approach is named DeCEMBERT (Dense Captions and Entropy Minimization). Comprehensive experiments on three video-and-language tasks (text-to-video retrieval, video captioning, and video question answering) across five datasets demonstrate that our approach outperforms previous state-of-the-art methods. Ablation studies on pre-training and downstream tasks show that adding dense captions and constrained attention loss help improve the model performance. Lastly, we also provide attention visualization to show the effect of applying the proposed constrained attention loss.</abstract>
<identifier type="citekey">tang-etal-2021-decembert</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.193</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.193</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2415</start>
<end>2426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization
%A Tang, Zineng
%A Lei, Jie
%A Bansal, Mohit
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F tang-etal-2021-decembert
%X Leveraging large-scale unlabeled web videos such as instructional videos for pre-training followed by task-specific finetuning has become the de facto approach for many video-and-language tasks. However, these instructional videos are very noisy, the accompanying ASR narrations are often incomplete, and can be irrelevant to or temporally misaligned with the visual content, limiting the performance of the models trained on such data. To address these issues, we propose an improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input, to provide informative visual cues for learning better video and language associations. Second, to alleviate the temporal misalignment issue, our method incorporates an entropy minimization-based constrained attention loss, to encourage the model to automatically focus on the correct caption from a pool of candidate ASR captions. Our overall approach is named DeCEMBERT (Dense Captions and Entropy Minimization). Comprehensive experiments on three video-and-language tasks (text-to-video retrieval, video captioning, and video question answering) across five datasets demonstrate that our approach outperforms previous state-of-the-art methods. Ablation studies on pre-training and downstream tasks show that adding dense captions and constrained attention loss help improve the model performance. Lastly, we also provide attention visualization to show the effect of applying the proposed constrained attention loss.
%R 10.18653/v1/2021.naacl-main.193
%U https://aclanthology.org/2021.naacl-main.193
%U https://doi.org/10.18653/v1/2021.naacl-main.193
%P 2415-2426
Markdown (Informal)
[DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization](https://aclanthology.org/2021.naacl-main.193) (Tang et al., NAACL 2021)
ACL