Automatic Understanding of Image and Video Advertisements
There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action. We propose the novel problem of automatic advertisement understanding. To enable research on this problem, we create two datasets: an image dataset of...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Hussain, Zaeem Zhang, Mingda Zhang, Xiaozhong Ye, Keren Thomas, Christopher Agha, Zuha Ong, Nathan Kovashka, Adriana |
| description | There is more to images than their objective physical content: for example,
advertisements are created to persuade a viewer to take a certain action. We
propose the novel problem of automatic advertisement understanding. To enable
research on this problem, we create two datasets: an image dataset of 64,832
image ads, and a video dataset of 3,477 ads. Our data contains rich annotations
encompassing the topic and sentiment of the ads, questions and answers
describing what actions the viewer is prompted to take and the reasoning that
the ad presents to persuade the viewer ("What should I do according to this ad,
and why should I do it?"), and symbolic references ads make (e.g. a dove
symbolizes peace). We also analyze the most common persuasive strategies ads
use, and the capabilities that computer vision systems should have to
understand these strategies. We present baseline classification results for
several prediction tasks, including automatically answering questions about the
messages of the ads. |
| doi_str_mv | 10.48550/arxiv.1707.03067 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1707_03067</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1707_03067</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-5fef935659699378c7f22e5d25d7675515a8c5cddd2078c74aa9195641702253</originalsourceid><addsrcrecordid>eNotj8tqwzAQRbXpoqT5gK6qH7AjSx7JWprQtIFAF31szeAZBUFtF1kJ6d_n0a4ulwuXc4R4rFRZNwBqhekUj2XllCuVUdbdC98e8jRgjr38HInTnHGkOO7lFOR2wD3LS5dfkXiSLR055TjzwGOeH8RdwO-Zl_-5EO-b54_1a7F7e9mu212B1rkCAgdvwIK33hvX9C5ozUAayFkHUAE2PfREpNV1rRF95cHWF0itwSzE09_rDb37SXHA9NtdFbqbgjkDaf0_1Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Automatic Understanding of Image and Video Advertisements</title><source>arXiv.org</source><creator>Hussain, Zaeem ; Zhang, Mingda ; Zhang, Xiaozhong ; Ye, Keren ; Thomas, Christopher ; Agha, Zuha ; Ong, Nathan ; Kovashka, Adriana</creator><creatorcontrib>Hussain, Zaeem ; Zhang, Mingda ; Zhang, Xiaozhong ; Ye, Keren ; Thomas, Christopher ; Agha, Zuha ; Ong, Nathan ; Kovashka, Adriana</creatorcontrib><description>There is more to images than their objective physical content: for example,
advertisements are created to persuade a viewer to take a certain action. We
propose the novel problem of automatic advertisement understanding. To enable
research on this problem, we create two datasets: an image dataset of 64,832
image ads, and a video dataset of 3,477 ads. Our data contains rich annotations
encompassing the topic and sentiment of the ads, questions and answers
describing what actions the viewer is prompted to take and the reasoning that
the ad presents to persuade the viewer ("What should I do according to this ad,
and why should I do it?"), and symbolic references ads make (e.g. a dove
symbolizes peace). We also analyze the most common persuasive strategies ads
use, and the capabilities that computer vision systems should have to
understand these strategies. We present baseline classification results for
several prediction tasks, including automatically answering questions about the
messages of the ads.</description><identifier>DOI: 10.48550/arxiv.1707.03067</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2017-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1707.03067$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1707.03067$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hussain, Zaeem</creatorcontrib><creatorcontrib>Zhang, Mingda</creatorcontrib><creatorcontrib>Zhang, Xiaozhong</creatorcontrib><creatorcontrib>Ye, Keren</creatorcontrib><creatorcontrib>Thomas, Christopher</creatorcontrib><creatorcontrib>Agha, Zuha</creatorcontrib><creatorcontrib>Ong, Nathan</creatorcontrib><creatorcontrib>Kovashka, Adriana</creatorcontrib><title>Automatic Understanding of Image and Video Advertisements</title><description>There is more to images than their objective physical content: for example,
advertisements are created to persuade a viewer to take a certain action. We
propose the novel problem of automatic advertisement understanding. To enable
research on this problem, we create two datasets: an image dataset of 64,832
image ads, and a video dataset of 3,477 ads. Our data contains rich annotations
encompassing the topic and sentiment of the ads, questions and answers
describing what actions the viewer is prompted to take and the reasoning that
the ad presents to persuade the viewer ("What should I do according to this ad,
and why should I do it?"), and symbolic references ads make (e.g. a dove
symbolizes peace). We also analyze the most common persuasive strategies ads
use, and the capabilities that computer vision systems should have to
understand these strategies. We present baseline classification results for
several prediction tasks, including automatically answering questions about the
messages of the ads.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAQRbXpoqT5gK6qH7AjSx7JWprQtIFAF31szeAZBUFtF1kJ6d_n0a4ulwuXc4R4rFRZNwBqhekUj2XllCuVUdbdC98e8jRgjr38HInTnHGkOO7lFOR2wD3LS5dfkXiSLR055TjzwGOeH8RdwO-Zl_-5EO-b54_1a7F7e9mu212B1rkCAgdvwIK33hvX9C5ozUAayFkHUAE2PfREpNV1rRF95cHWF0itwSzE09_rDb37SXHA9NtdFbqbgjkDaf0_1Q</recordid><startdate>20170710</startdate><enddate>20170710</enddate><creator>Hussain, Zaeem</creator><creator>Zhang, Mingda</creator><creator>Zhang, Xiaozhong</creator><creator>Ye, Keren</creator><creator>Thomas, Christopher</creator><creator>Agha, Zuha</creator><creator>Ong, Nathan</creator><creator>Kovashka, Adriana</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20170710</creationdate><title>Automatic Understanding of Image and Video Advertisements</title><author>Hussain, Zaeem ; Zhang, Mingda ; Zhang, Xiaozhong ; Ye, Keren ; Thomas, Christopher ; Agha, Zuha ; Ong, Nathan ; Kovashka, Adriana</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-5fef935659699378c7f22e5d25d7675515a8c5cddd2078c74aa9195641702253</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Hussain, Zaeem</creatorcontrib><creatorcontrib>Zhang, Mingda</creatorcontrib><creatorcontrib>Zhang, Xiaozhong</creatorcontrib><creatorcontrib>Ye, Keren</creatorcontrib><creatorcontrib>Thomas, Christopher</creatorcontrib><creatorcontrib>Agha, Zuha</creatorcontrib><creatorcontrib>Ong, Nathan</creatorcontrib><creatorcontrib>Kovashka, Adriana</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hussain, Zaeem</au><au>Zhang, Mingda</au><au>Zhang, Xiaozhong</au><au>Ye, Keren</au><au>Thomas, Christopher</au><au>Agha, Zuha</au><au>Ong, Nathan</au><au>Kovashka, Adriana</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatic Understanding of Image and Video Advertisements</atitle><date>2017-07-10</date><risdate>2017</risdate><abstract>There is more to images than their objective physical content: for example,
advertisements are created to persuade a viewer to take a certain action. We
propose the novel problem of automatic advertisement understanding. To enable
research on this problem, we create two datasets: an image dataset of 64,832
image ads, and a video dataset of 3,477 ads. Our data contains rich annotations
encompassing the topic and sentiment of the ads, questions and answers
describing what actions the viewer is prompted to take and the reasoning that
the ad presents to persuade the viewer ("What should I do according to this ad,
and why should I do it?"), and symbolic references ads make (e.g. a dove
symbolizes peace). We also analyze the most common persuasive strategies ads
use, and the capabilities that computer vision systems should have to
understand these strategies. We present baseline classification results for
several prediction tasks, including automatically answering questions about the
messages of the ads.</abstract><doi>10.48550/arxiv.1707.03067</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1707.03067 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1707_03067 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | Automatic Understanding of Image and Video Advertisements |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T05%3A35%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automatic%20Understanding%20of%20Image%20and%20Video%20Advertisements&rft.au=Hussain,%20Zaeem&rft.date=2017-07-10&rft_id=info:doi/10.48550/arxiv.1707.03067&rft_dat=%3Carxiv_GOX%3E1707_03067%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |