Overview of Tencent Multi-modal Ads Video Understanding Challenge

Bibliographic Details
Title:	Overview of Tencent Multi-modal Ads Video Understanding Challenge
Authors:	Wang, Zhenzhi, Wu, Liyu, Li, Zhimin, Xiong, Jiangfeng, Lu, Qinglin
Publication Year:	2021
Collection:	Computer Science
Subject Terms:	Computer Science - Computer Vision and Pattern Recognition
More Details:	Multi-modal Ads Video Understanding Challenge is the first grand challenge aiming to comprehensively understand ads videos. Our challenge includes two tasks: video structuring in the temporal dimension and multi-modal video classification. It asks the participants to accurately predict both the scene boundaries and the multi-label categories of each scene based on a fine-grained and ads-related category hierarchy. Therefore, our task has four distinguishing features from previous ones: ads domain, multi-modal information, temporal segmentation, and multi-label classification. It will advance the foundation of ads video understanding and have a significant impact on many ads applications like video recommendation. This paper presents an overview of our challenge, including the background of ads videos, an elaborate description of task and dataset, evaluation protocol, and our proposed baseline. By ablating the key components of our baseline, we would like to reveal the main challenges of this task and provide useful guidance for future research of this area. In this paper, we give an extended version of our challenge overview. The dataset will be publicly available at https://algo.qq.com/. Comment: 8-page extended version of our challenge paper in ACM MM 2021. It presents the overview of grand challenge "Multi-modal Ads Video Understanding" in ACM MM 2021. Our grand challenge is also the Tencent Advertising Algorithm Competition (TAAC) 2021
Document Type:	Working Paper
Access URL:	http://arxiv.org/abs/2109.07951
Accession Number:	edsarx.2109.07951
Database:	arXiv

FullText	Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2109.07951 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20210916&spage=&pages=&title=Overview of Tencent Multi-modal Ads Video Understanding Challenge&atitle=Overview%20of%20Tencent%20Multi-modal%20Ads%20Video%20Understanding%20Challenge&aulast=Wang%2C%20Zhenzhi&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries
Header	DbId: edsarx DbLabel: arXiv An: edsarx.2109.07951 RelevancyScore: 1017 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1016.9287109375
IllustrationInfo
Items	– Name: Title Label: Title Group: Ti Data: Overview of Tencent Multi-modal Ads Video Understanding Challenge – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Zhenzhi%22">Wang, Zhenzhi</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+Liyu%22">Wu, Liyu</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Zhimin%22">Li, Zhimin</searchLink><br /><searchLink fieldCode="AR" term="%22Xiong%2C+Jiangfeng%22">Xiong, Jiangfeng</searchLink><br /><searchLink fieldCode="AR" term="%22Lu%2C+Qinglin%22">Lu, Qinglin</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2021 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink> – Name: Abstract Label: Description Group: Ab Data: Multi-modal Ads Video Understanding Challenge is the first grand challenge aiming to comprehensively understand ads videos. Our challenge includes two tasks: video structuring in the temporal dimension and multi-modal video classification. It asks the participants to accurately predict both the scene boundaries and the multi-label categories of each scene based on a fine-grained and ads-related category hierarchy. Therefore, our task has four distinguishing features from previous ones: ads domain, multi-modal information, temporal segmentation, and multi-label classification. It will advance the foundation of ads video understanding and have a significant impact on many ads applications like video recommendation. This paper presents an overview of our challenge, including the background of ads videos, an elaborate description of task and dataset, evaluation protocol, and our proposed baseline. By ablating the key components of our baseline, we would like to reveal the main challenges of this task and provide useful guidance for future research of this area. In this paper, we give an extended version of our challenge overview. The dataset will be publicly available at https://algo.qq.com/.<br />Comment: 8-page extended version of our challenge paper in ACM MM 2021. It presents the overview of grand challenge "Multi-modal Ads Video Understanding" in ACM MM 2021. Our grand challenge is also the Tencent Advertising Algorithm Competition (TAAC) 2021 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2109.07951" linkWindow="_blank">http://arxiv.org/abs/2109.07951</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2109.07951
PLink	https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2109.07951
RecordInfo	BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general Titles: – TitleFull: Overview of Tencent Multi-modal Ads Video Understanding Challenge Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Zhenzhi – PersonEntity: Name: NameFull: Wu, Liyu – PersonEntity: Name: NameFull: Li, Zhimin – PersonEntity: Name: NameFull: Xiong, Jiangfeng – PersonEntity: Name: NameFull: Lu, Qinglin IsPartOfRelationships: – BibEntity: Dates: – D: 16 M: 09 Type: published Y: 2021
ResultId	1