HULU视频内容相关性推荐大赛启动，丰厚奖励等你来拿

HULU视频内容相关性推荐大赛启动，丰厚奖励等你来拿

竞赛简介

       视频相关性预测是在线流媒体服务中最重要的任务之一。根据用户观看或搜索视频的记录，推荐系统能够提供个性化推荐以帮助用户发现更多感兴趣的视频内容。目前大多数在线服务中的视频相关性预测都是基于用户行为，这将不可避免的带来”冷启动”问题，即系统因无法获取新视频的用户行为记录而难以给出相关推荐；而另一方面，视频本身所包含的图像，声音，文本等源内容可以被有效利用起来，通过智能化的分析理解，作为视频相关性预测的可靠依据。

       基于上述背景，HULU与计算机多媒体领域国际顶级会议ACM Multimedia (MM) 2018 (http://www.acmmm.org/2018/) 联合推出了基于内容的视频相关性预测大赛 (详见会议官方主页http://www.acmmm.org/2018/multimedia-grand-challenge/)

  

我们通过开放部分 HULU自身平台的影视剧集视频数据，让参赛者在真实场景下进行视频内容分析算法的开发与测试，并根据公司多年来积累的隐式用户反馈记录给出相关视频列表，作为选手们验证所得结果的真实参考。更多相关信息请点击我们的竞赛主页：https://github.com/mengyi-liu/cbvrp-acmmm-2018.

竞赛日程

·       4月02日: 竞赛开放注册，参赛者完成在线申请表格并提交

·       4月20日: 竞赛数据开放，供已注册成功参赛者下载进行实验

·       7月01日: 数据实验结果提交截止

·       7月08日: 竞赛论文提交截止（可选项）

·       8月05日: 论文接收结果公布

·       8月31日: 获胜选手提交技术报告及算法核心代码

竞赛奖励

我们将为获胜选手提供总额为2000美金（包含税款）的奖励（具体人数及奖金分配方式将根据竞赛实际结果确定）。获胜选手需向组织方提交技术报告及算法核心代码供组织方验证可重现性。

参赛方式

报名参赛可直接通过填写在线申请表格。

报名成功后主办方将通过邮件通知竞赛数据的下载方式以及其他相关事宜。如有任何疑问，欢迎随时联系cbvrp-acmmm-2018@hulu.com.

Introduction

Video relevance computation is one of the most important tasks for personalized online streaming service. Given the relevance of videos and viewer feedbacks, the system can provide personalized recommendations, which will help the viewer discover more content of interest. In most online service, the computation of video relevance table is based on the viewers' implicit feedback, e.g. watch and search history. The system analyzes the viewer-to-video preference and computes the video-to-video relevance scores using collaborative filtering based methods. However, this kind of method performs poorly for “cold-start” problems - when a new video is added to the library, the recommendation system needs to bootstrap the video relevance score with very little historical viewer feedbacks. One promising approach to solve “cold-start” is analyzing video content itself to predict the relevance score, i.e. predicting the video-to-video relevance by analyzing the key-frames, audio, subtitles and metadata. With the relevance score, we can provide better recommendations for our viewers.

Generally, content-based methods focus on recommending items which have similar content characteristics to the items the user liked in the past. One of the key issues is how to extract the most relevant content features of each item. For most existing systems, the content features are associated with the items as structured metadata, e.g. movie/show genre, director/actors, description; Or other unstructured information from external sources, such as tags, and textual reviews. In contrast to these kinds of “explicit” features, there are also “implicit” content characteristics which can be exploited from the original movie/show video. Such characteristics could be visual features encoding low-level information like lighting, color, shape, motion, or high-level semantics like plot, mood, and artistic style.

To drive the study on this open problem, Hulu organized the 2nd Content-Based Video Relevance Prediction (CBVRP) Challenge (http://www.acmmm.org/2018/multimedia-grand-challenge/) joined with the ACM International Conference on Multimedia (MM 2018) (http://www.acmmm.org/2018/). We release real-world content data along with ground-truth from implicit viewer feedbacks to provide a common platform for algorithm development. For more details, please visit our CBVRP grand challenge website: https://github.com/mengyi-liu/cbvrp-acmmm-2018.

Registration

To register for the challenge and get access to the dataset, please complete the Online Agreement Form. We will send you the download instructions by email after the challenge data available date (Apr. 20th, 2018).

Schedule

April 2nd: Registration open.
April 20th: Challenge data available.
July 1st: Deadline for results submission.
July 8th: Deadline for paper submission (Optional, for more details, please refer to “Submissions” on http://www.acmmm.org/2018/multimedia-grand-challenge/).
August 5th: Notification of winners and paper acceptance.
August 31st: Winners submit the tech report and source code.

Prizes

The total reward is $2,000 USD including the taxable amount, which will be fully sponsored by Hulu LLC. The number of winners will depend on the number of participants and the quality of the results. The organizers reserve the complete right in the final judgement and decision.

The winners of the challenge are required to provide a technique report describing the details of the winning algorithms, and provide the source code to the organizers. The organizers will also run the released the code to test the reproducibility of the winner algorithms. The winners will give a presentation during the conference.

Contact

If you have any question, please send email to cbvrp-acmmm-2018@hulu.com.