Recommending Videos in Cold Start With Automatic Visual Tags. Elahi, M., Bakhshandegan Moghaddam, F., Hosseini, R., Rimaz, M. H., El Ioini, N., Tkalčič, M., Trattner, C., & Tillo, T. In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization, pages 54–60, Utrecht Netherlands, June, 2021. ACM. ![Recommending Videos in Cold Start With Automatic Visual Tags [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.
@inproceedings{elahi_recommending_2021,
address = {Utrecht Netherlands},
title = {Recommending {Videos} in {Cold} {Start} {With} {Automatic} {Visual} {Tags}},
copyright = {All rights reserved},
isbn = {978-1-4503-8367-7},
url = {https://dl.acm.org/doi/10.1145/3450614.3461687},
doi = {10.1145/3450614.3461687},
abstract = {This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.},
language = {en},
urldate = {2022-10-04},
booktitle = {Adjunct {Proceedings} of the 29th {ACM} {Conference} on {User} {Modeling}, {Adaptation} and {Personalization}},
publisher = {ACM},
author = {Elahi, Mehdi and Bakhshandegan Moghaddam, Farshad and Hosseini, Reza and Rimaz, Mohammad Hossein and El Ioini, Nabil and Tkalčič, Marko and Trattner, Christoph and Tillo, Tammam},
month = jun,
year = {2021},
pages = {54--60},
}
Downloads: 0
{"_id":"3EqHLFsjzvpxu4zcd","bibbaseid":"elahi-bakhshandeganmoghaddam-hosseini-rimaz-elioini-tkali-trattner-tillo-recommendingvideosincoldstartwithautomaticvisualtags-2021","author_short":["Elahi, M.","Bakhshandegan Moghaddam, F.","Hosseini, R.","Rimaz, M. H.","El Ioini, N.","Tkalčič, M.","Trattner, C.","Tillo, T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Utrecht Netherlands","title":"Recommending Videos in Cold Start With Automatic Visual Tags","copyright":"All rights reserved","isbn":"978-1-4503-8367-7","url":"https://dl.acm.org/doi/10.1145/3450614.3461687","doi":"10.1145/3450614.3461687","abstract":"This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.","language":"en","urldate":"2022-10-04","booktitle":"Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization","publisher":"ACM","author":[{"propositions":[],"lastnames":["Elahi"],"firstnames":["Mehdi"],"suffixes":[]},{"propositions":[],"lastnames":["Bakhshandegan","Moghaddam"],"firstnames":["Farshad"],"suffixes":[]},{"propositions":[],"lastnames":["Hosseini"],"firstnames":["Reza"],"suffixes":[]},{"propositions":[],"lastnames":["Rimaz"],"firstnames":["Mohammad","Hossein"],"suffixes":[]},{"propositions":[],"lastnames":["El","Ioini"],"firstnames":["Nabil"],"suffixes":[]},{"propositions":[],"lastnames":["Tkalčič"],"firstnames":["Marko"],"suffixes":[]},{"propositions":[],"lastnames":["Trattner"],"firstnames":["Christoph"],"suffixes":[]},{"propositions":[],"lastnames":["Tillo"],"firstnames":["Tammam"],"suffixes":[]}],"month":"June","year":"2021","pages":"54–60","bibtex":"@inproceedings{elahi_recommending_2021,\n\taddress = {Utrecht Netherlands},\n\ttitle = {Recommending {Videos} in {Cold} {Start} {With} {Automatic} {Visual} {Tags}},\n\tcopyright = {All rights reserved},\n\tisbn = {978-1-4503-8367-7},\n\turl = {https://dl.acm.org/doi/10.1145/3450614.3461687},\n\tdoi = {10.1145/3450614.3461687},\n\tabstract = {This paper addresses the so-called New Item problem in video Recommender Systems, as part of Cold Start. New item problem occurs when a new item is added to the system catalog, and the recommender system has no or little data describing that item. This could cause the system to fail to meaningfully recommend the new item to the users. We propose a novel technique that can generate cold start recommendation by utilizing automatic visual tags, i.e., tags that are automatically annotated by deeply analyzing the content of the videos and detecting faces, objects, and even celebrities within the videos. The automatic visual tags do not need any human involvement and have been shown to be very effective in representing the video content. In order to evaluate our proposed technique, we have performed a set of experiments using a large dataset of videos. The results have shown that the automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.},\n\tlanguage = {en},\n\turldate = {2022-10-04},\n\tbooktitle = {Adjunct {Proceedings} of the 29th {ACM} {Conference} on {User} {Modeling}, {Adaptation} and {Personalization}},\n\tpublisher = {ACM},\n\tauthor = {Elahi, Mehdi and Bakhshandegan Moghaddam, Farshad and Hosseini, Reza and Rimaz, Mohammad Hossein and El Ioini, Nabil and Tkalčič, Marko and Trattner, Christoph and Tillo, Tammam},\n\tmonth = jun,\n\tyear = {2021},\n\tpages = {54--60},\n}\n\n","author_short":["Elahi, M.","Bakhshandegan Moghaddam, F.","Hosseini, R.","Rimaz, M. H.","El Ioini, N.","Tkalčič, M.","Trattner, C.","Tillo, T."],"key":"elahi_recommending_2021","id":"elahi_recommending_2021","bibbaseid":"elahi-bakhshandeganmoghaddam-hosseini-rimaz-elioini-tkali-trattner-tillo-recommendingvideosincoldstartwithautomaticvisualtags-2021","role":"author","urls":{"Paper":"https://dl.acm.org/doi/10.1145/3450614.3461687"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero-mypublications/markotka75","dataSources":["vM5p4dhf8dDtXLnWN"],"keywords":[],"search_terms":["recommending","videos","cold","start","automatic","visual","tags","elahi","bakhshandegan moghaddam","hosseini","rimaz","el ioini","tkalčič","trattner","tillo"],"title":"Recommending Videos in Cold Start With Automatic Visual Tags","year":2021}