@inproceedings{liu-hu-2022-learning,
title = "Learning to Focus on the Foreground for Temporal Sentence Grounding",
author = "Liu, Daizong and
Hu, Wei",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.490",
pages = "5532--5541",
abstract = "Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Previous works typically model the target activity referred to the sentence query in a video by extracting the appearance information from each whole frame. However, these methods fail to distinguish visually similar background noise and capture subtle details of small objects. Although a few recent works additionally adopt a detection model to filter out the background contents and capture local appearances of foreground objects, they rely on the quality of the detection model and suffer from the time-consuming detection process. To this end, we propose a novel detection-free framework for TSG{---}Grounding with Learnable Foreground (GLF), which efficiently learns to locate the foreground regions related to the query in consecutive frames for better modelling the target activity. Specifically, we first split each video frame into multiple patch candidates of equal size, and reformulate the foreground detection problem as a patch localization task. Then, we develop a self-supervised coarse-to-fine paradigm to learn to locate the most query-relevant patch in each frame and aggregate them among the video for final grounding. Further, we employ a multi-scale patch reasoning strategy to capture more fine-grained foreground information. Extensive experiments on three challenging datasets (Charades-STA, TACoS, ActivityNet) show that the proposed GLF outperforms state-of-the-art methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-hu-2022-learning">
<titleInfo>
<title>Learning to Focus on the Foreground for Temporal Sentence Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daizong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Previous works typically model the target activity referred to the sentence query in a video by extracting the appearance information from each whole frame. However, these methods fail to distinguish visually similar background noise and capture subtle details of small objects. Although a few recent works additionally adopt a detection model to filter out the background contents and capture local appearances of foreground objects, they rely on the quality of the detection model and suffer from the time-consuming detection process. To this end, we propose a novel detection-free framework for TSG—Grounding with Learnable Foreground (GLF), which efficiently learns to locate the foreground regions related to the query in consecutive frames for better modelling the target activity. Specifically, we first split each video frame into multiple patch candidates of equal size, and reformulate the foreground detection problem as a patch localization task. Then, we develop a self-supervised coarse-to-fine paradigm to learn to locate the most query-relevant patch in each frame and aggregate them among the video for final grounding. Further, we employ a multi-scale patch reasoning strategy to capture more fine-grained foreground information. Extensive experiments on three challenging datasets (Charades-STA, TACoS, ActivityNet) show that the proposed GLF outperforms state-of-the-art methods.</abstract>
<identifier type="citekey">liu-hu-2022-learning</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.490</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5532</start>
<end>5541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Focus on the Foreground for Temporal Sentence Grounding
%A Liu, Daizong
%A Hu, Wei
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F liu-hu-2022-learning
%X Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Previous works typically model the target activity referred to the sentence query in a video by extracting the appearance information from each whole frame. However, these methods fail to distinguish visually similar background noise and capture subtle details of small objects. Although a few recent works additionally adopt a detection model to filter out the background contents and capture local appearances of foreground objects, they rely on the quality of the detection model and suffer from the time-consuming detection process. To this end, we propose a novel detection-free framework for TSG—Grounding with Learnable Foreground (GLF), which efficiently learns to locate the foreground regions related to the query in consecutive frames for better modelling the target activity. Specifically, we first split each video frame into multiple patch candidates of equal size, and reformulate the foreground detection problem as a patch localization task. Then, we develop a self-supervised coarse-to-fine paradigm to learn to locate the most query-relevant patch in each frame and aggregate them among the video for final grounding. Further, we employ a multi-scale patch reasoning strategy to capture more fine-grained foreground information. Extensive experiments on three challenging datasets (Charades-STA, TACoS, ActivityNet) show that the proposed GLF outperforms state-of-the-art methods.
%U https://aclanthology.org/2022.coling-1.490
%P 5532-5541
Markdown (Informal)
[Learning to Focus on the Foreground for Temporal Sentence Grounding](https://aclanthology.org/2022.coling-1.490) (Liu & Hu, COLING 2022)
ACL