'Fitness that Fits': - A Prototype Model for Workout Video Recommendation

Ercan Ezin; Eunchong Kim; Ivan Palomares Carrascosa

'Fitness that Fits': - A Prototype Model for Workout Video Recommendation

Ercan Ezin, Eunchong Kim, Ivan Palomares Carrascosa

Research output: Contribution to conference › Conference Paper › peer-review

292 Downloads (Pure)

Abstract

Personalization services enable Internet users to benefit from tailored recommended content at their finger tips. Our interest in
this contribution lies in video recommendation within the fitness
domain to support an active lifestyle. We present ’Fitness that Fits’, a preliminary platform for workout video recommendation, which benefits from the Youtube-8M labeled dataset and its rich variety of categorized video labels, thereby enabling fitness workout video recommendations predicated on the users’ preferences and their recent viewing behavior. The proposed model also incorporates an approach to produce diversified recommendations and foster the practice of distinct fitness activities based on like-minded users’ information. An initial experimental study shows the trade-offs of the hybrid approach considered.

Original language	English
Number of pages	6
Publication status	Published - 2 Oct 2018
Event	12th ACM Conference on Recommender Systems - Vancouver, Canada Duration: 2 Oct 2018 → 7 Oct 2018 https://recsys.acm.org/recsys18/

Conference

Conference	12th ACM Conference on Recommender Systems
Abbreviated title	RECSYS 2018
Country/Territory	Canada
City	Vancouver
Period	2/10/18 → 7/10/18
Internet address	https://recsys.acm.org/recsys18/

Structured keywords

Jean Golding

Keywords

Personalized Wellbeing
Preference Modeling
Diversity

Access to Document

Full-text PDF (accepted author manuscript)Accepted author manuscript, 862 KB

Cite this

@conference{977aeba1c70f4d8598c779693ce0605c,

title = "'Fitness that Fits': - A Prototype Model for Workout Video Recommendation",

abstract = "Personalization services enable Internet users to benefit from tailored recommended content at their finger tips. Our interest inthis contribution lies in video recommendation within the fitnessdomain to support an active lifestyle. We present {\textquoteright}Fitness that Fits{\textquoteright}, a preliminary platform for workout video recommendation, which benefits from the Youtube-8M labeled dataset and its rich variety of categorized video labels, thereby enabling fitness workout video recommendations predicated on the users{\textquoteright} preferences and their recent viewing behavior. The proposed model also incorporates an approach to produce diversified recommendations and foster the practice of distinct fitness activities based on like-minded users{\textquoteright} information. An initial experimental study shows the trade-offs of the hybrid approach considered.",

keywords = "Personalized Wellbeing, Preference Modeling, Diversity",

author = "Ercan Ezin and Eunchong Kim and {Palomares Carrascosa}, Ivan",

year = "2018",

month = oct,

day = "2",

language = "English",

note = "12th ACM Conference on Recommender Systems, RECSYS 2018 ; Conference date: 02-10-2018 Through 07-10-2018",

url = "https://recsys.acm.org/recsys18/",

}

TY - CONF

T1 - 'Fitness that Fits'

T2 - 12th ACM Conference on Recommender Systems

AU - Ezin, Ercan

AU - Kim, Eunchong

AU - Palomares Carrascosa, Ivan

PY - 2018/10/2

Y1 - 2018/10/2

N2 - Personalization services enable Internet users to benefit from tailored recommended content at their finger tips. Our interest inthis contribution lies in video recommendation within the fitnessdomain to support an active lifestyle. We present ’Fitness that Fits’, a preliminary platform for workout video recommendation, which benefits from the Youtube-8M labeled dataset and its rich variety of categorized video labels, thereby enabling fitness workout video recommendations predicated on the users’ preferences and their recent viewing behavior. The proposed model also incorporates an approach to produce diversified recommendations and foster the practice of distinct fitness activities based on like-minded users’ information. An initial experimental study shows the trade-offs of the hybrid approach considered.

AB - Personalization services enable Internet users to benefit from tailored recommended content at their finger tips. Our interest inthis contribution lies in video recommendation within the fitnessdomain to support an active lifestyle. We present ’Fitness that Fits’, a preliminary platform for workout video recommendation, which benefits from the Youtube-8M labeled dataset and its rich variety of categorized video labels, thereby enabling fitness workout video recommendations predicated on the users’ preferences and their recent viewing behavior. The proposed model also incorporates an approach to produce diversified recommendations and foster the practice of distinct fitness activities based on like-minded users’ information. An initial experimental study shows the trade-offs of the hybrid approach considered.

KW - Personalized Wellbeing

KW - Preference Modeling

KW - Diversity

UR - https://recsys.acm.org/recsys18/program/

M3 - Conference Paper

Y2 - 2 October 2018 through 7 October 2018

ER -

'Fitness that Fits': - A Prototype Model for Workout Video Recommendation

Abstract

Conference

Structured keywords

Keywords

Access to Document

Other files and links

Fingerprint

Cite this