@inproceedings{liu-etal-2021-progressively,
title = "Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding",
author = "Liu, Daizong and
Qu, Xiaoye and
Zhou, Pan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.733",
doi = "10.18653/v1/2021.emnlp-main.733",
pages = "9302--9311",
abstract = "A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft attention to perform the alignment in a single-step process. However, such single-step attention is insufficient in practice, since complicated relations between inter- and intra-modality are usually obtained through multi-step reasoning. In this paper, we propose an Iterative Alignment Network (IA-Net) for TSG task, which iteratively interacts inter- and intra-modal features within multiple steps for more accurate grounding. Specifically, during the iterative reasoning process, we pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs, and enhance the basic co-attention mechanism in a parallel manner. To further calibrate the misaligned attention caused by each reasoning step, we also devise a calibration module following each attention module to refine the alignment knowledge. With such iterative alignment scheme, our IA-Net can robustly capture the fine-grained relations between vision and language domains step-by-step for progressively reasoning the temporal boundaries. Extensive experiments conducted on three challenging benchmarks demonstrate that our proposed model performs better than the state-of-the-arts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-progressively">
<titleInfo>
<title>Progressively Guide to Attend: An Iterative Alignment Framework 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">Xiaoye</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft attention to perform the alignment in a single-step process. However, such single-step attention is insufficient in practice, since complicated relations between inter- and intra-modality are usually obtained through multi-step reasoning. In this paper, we propose an Iterative Alignment Network (IA-Net) for TSG task, which iteratively interacts inter- and intra-modal features within multiple steps for more accurate grounding. Specifically, during the iterative reasoning process, we pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs, and enhance the basic co-attention mechanism in a parallel manner. To further calibrate the misaligned attention caused by each reasoning step, we also devise a calibration module following each attention module to refine the alignment knowledge. With such iterative alignment scheme, our IA-Net can robustly capture the fine-grained relations between vision and language domains step-by-step for progressively reasoning the temporal boundaries. Extensive experiments conducted on three challenging benchmarks demonstrate that our proposed model performs better than the state-of-the-arts.</abstract>
<identifier type="citekey">liu-etal-2021-progressively</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.733</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.733</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9302</start>
<end>9311</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding
%A Liu, Daizong
%A Qu, Xiaoye
%A Zhou, Pan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F liu-etal-2021-progressively
%X A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft attention to perform the alignment in a single-step process. However, such single-step attention is insufficient in practice, since complicated relations between inter- and intra-modality are usually obtained through multi-step reasoning. In this paper, we propose an Iterative Alignment Network (IA-Net) for TSG task, which iteratively interacts inter- and intra-modal features within multiple steps for more accurate grounding. Specifically, during the iterative reasoning process, we pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs, and enhance the basic co-attention mechanism in a parallel manner. To further calibrate the misaligned attention caused by each reasoning step, we also devise a calibration module following each attention module to refine the alignment knowledge. With such iterative alignment scheme, our IA-Net can robustly capture the fine-grained relations between vision and language domains step-by-step for progressively reasoning the temporal boundaries. Extensive experiments conducted on three challenging benchmarks demonstrate that our proposed model performs better than the state-of-the-arts.
%R 10.18653/v1/2021.emnlp-main.733
%U https://aclanthology.org/2021.emnlp-main.733
%U https://doi.org/10.18653/v1/2021.emnlp-main.733
%P 9302-9311
Markdown (Informal)
[Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding](https://aclanthology.org/2021.emnlp-main.733) (Liu et al., EMNLP 2021)
ACL