@inproceedings{chen-etal-2019-weakly,
title = "Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video",
author = "Chen, Zhenfang and
Ma, Lin and
Luo, Wenhan and
Wong, Kwan-Yee Kenneth",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1183",
doi = "10.18653/v1/P19-1183",
pages = "1884--1894",
abstract = "In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training. First, a set of spatio-temporal tubes, referred to as instances, are extracted from the video. We then encode these instances and the sentence using our newly proposed attentive interactor which can exploit their fine-grained relationships to characterize their matching behaviors. Besides a ranking loss, a novel diversity loss is introduced to train our attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones. We also contribute a dataset, called VID-sentence, based on the ImageNet video object detection dataset, to serve as a benchmark for our task. Results from extensive experiments demonstrate the superiority of our model over the baseline approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2019-weakly">
<titleInfo>
<title>Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenfang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kwan-Yee</namePart>
<namePart type="given">Kenneth</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training. First, a set of spatio-temporal tubes, referred to as instances, are extracted from the video. We then encode these instances and the sentence using our newly proposed attentive interactor which can exploit their fine-grained relationships to characterize their matching behaviors. Besides a ranking loss, a novel diversity loss is introduced to train our attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones. We also contribute a dataset, called VID-sentence, based on the ImageNet video object detection dataset, to serve as a benchmark for our task. Results from extensive experiments demonstrate the superiority of our model over the baseline approaches.</abstract>
<identifier type="citekey">chen-etal-2019-weakly</identifier>
<identifier type="doi">10.18653/v1/P19-1183</identifier>
<location>
<url>https://aclanthology.org/P19-1183</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>1884</start>
<end>1894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
%A Chen, Zhenfang
%A Ma, Lin
%A Luo, Wenhan
%A Wong, Kwan-Yee Kenneth
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F chen-etal-2019-weakly
%X In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training. First, a set of spatio-temporal tubes, referred to as instances, are extracted from the video. We then encode these instances and the sentence using our newly proposed attentive interactor which can exploit their fine-grained relationships to characterize their matching behaviors. Besides a ranking loss, a novel diversity loss is introduced to train our attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones. We also contribute a dataset, called VID-sentence, based on the ImageNet video object detection dataset, to serve as a benchmark for our task. Results from extensive experiments demonstrate the superiority of our model over the baseline approaches.
%R 10.18653/v1/P19-1183
%U https://aclanthology.org/P19-1183
%U https://doi.org/10.18653/v1/P19-1183
%P 1884-1894
Markdown (Informal)
[Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video](https://aclanthology.org/P19-1183) (Chen et al., ACL 2019)
ACL