Predicting video popularity based on video covers and titles using a multimodal large-scale model and pipeline parallelism

Research Article
Open access

Predicting video popularity based on video covers and titles using a multimodal large-scale model and pipeline parallelism

Jie Qin 1* , Bei'an Wang 2 , Tianyu Zhu 3
  • 1 Xi'an Jiaotong University    
  • 2 Wuhan University    
  • 3 South China University of Technology    
  • *corresponding author 1503490056@stu.xjtu.edu.cn
Published on 22 February 2024 | https://doi.org/10.54254/2755-2721/41/20230741
ACE Vol.41
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-83558-307-4
ISBN (Online): 978-1-83558-308-1

Abstract

In the era of traffic, controlling traffic is equivalent to mastering influence and economic benefits. At the video level, under the premise of the same video content, it is very important to study what kind of cover and title can be more attractive to people. Unlike most previous studies that focused on YouTube videos, our data came from Bilibili’s videos. This paper tried to use two neural network models, ViT and Bert, combined with GPipe and backend fusion multimodal data fusion methods, to predict the possible click-through rate and popularity of a specific video based on its existing video cover and title. In the process, we switched to different visual and language models to complete the same training task, with the goal of comparing the impact of different models on the results. By adjusting the weight of two models, we finally achieved a good result of up to 62% accuracy.

Keywords:

ViT, Bert, Gpipe, Pipeline Parallelism, Covers on Video Views

Qin,J.;Wang,B.;Zhu,T. (2024). Predicting video popularity based on video covers and titles using a multimodal large-scale model and pipeline parallelism. Applied and Computational Engineering,41,182-189.
Export citation

References

[1]. Millionz.Co Offers Multi-Tiered Service To Help Influencers, Businesses, and creatives gain massive increases in followers, likes, video views, music plays, and shares. Influence is power! [J] M2 Presswire. Volume , Issue . 2021

[2]. Kati Dlaske. Music video covers, minoritised languages, and affective investments in the space of YouTube [J] Language in Society. Volume 46 , Issue 4 . 2017. PP 451-475

[3]. Wondwesen Tafesse. YouTube marketing: how marketers video optimization practices influence video views [J] Internet Research. Volume ahead-of-print , Issue ahead-of-print . 2020. PP 1689-1707

[4]. Ya L I , University A A .Research on Development Status and Optimization Measures of Agricultural Products Cross-border E-commerce Logistics in Anhui Province[J].Journal of Anhui Agricultural Sciences, 2019.

[5]. Dai X, Wang J. Effect of online video infotainment on audience attention[J]. Humanities and Social Sciences Communications, 2023, P3.

[6]. Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.

[7]. Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.

[8]. Huang Y, Cheng Y, Bapna A, et al. Gpipe: Efficient training of giant neural networks using pipeline parallelism[J]. Advances in neural information processing systems, 2019, 32.

[9]. Shazeer N, Stern M. Adafactor: Adaptive learning rates with sublinear memory cost[C]//International Conference on Machine Learning. PMLR, 2018: 4596-4604.

[10]. Dai, Z., Liu, H., Le, Q. V., & Tan, M. CoAtNet: Marrying Convolution and Attention for All Data Sizes. arXiv preprint arXiv:2106.04803, 2021.

Cite this article

Qin,J.;Wang,B.;Zhu,T. (2024). Predicting video popularity based on video covers and titles using a multimodal large-scale model and pipeline parallelism. Applied and Computational Engineering,41,182-189.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 2023 International Conference on Machine Learning and Automation

ISBN：978-1-83558-307-4(Print) / 978-1-83558-308-1(Online)
Editor：Mustafa İSTANBULLU
Conference website: https://2023.confmla.org/
Conference date: 18 October 2023
Series: Applied and Computational Engineering
Volume number: Vol.41
ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Millionz.Co Offers Multi-Tiered Service To Help Influencers, Businesses, and creatives gain massive increases in followers, likes, video views, music plays, and shares. Influence is power! [J] M2 Presswire. Volume , Issue . 2021

[2]. Kati Dlaske. Music video covers, minoritised languages, and affective investments in the space of YouTube [J] Language in Society. Volume 46 , Issue 4 . 2017. PP 451-475

[3]. Wondwesen Tafesse. YouTube marketing: how marketers video optimization practices influence video views [J] Internet Research. Volume ahead-of-print , Issue ahead-of-print . 2020. PP 1689-1707

[4]. Ya L I , University A A .Research on Development Status and Optimization Measures of Agricultural Products Cross-border E-commerce Logistics in Anhui Province[J].Journal of Anhui Agricultural Sciences, 2019.

[5]. Dai X, Wang J. Effect of online video infotainment on audience attention[J]. Humanities and Social Sciences Communications, 2023, P3.

[6]. Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.

[7]. Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.

[8]. Huang Y, Cheng Y, Bapna A, et al. Gpipe: Efficient training of giant neural networks using pipeline parallelism[J]. Advances in neural information processing systems, 2019, 32.

[9]. Shazeer N, Stern M. Adafactor: Adaptive learning rates with sublinear memory cost[C]//International Conference on Machine Learning. PMLR, 2018: 4596-4604.

[10]. Dai, Z., Liu, H., Le, Q. V., & Tan, M. CoAtNet: Marrying Convolution and Attention for All Data Sizes. arXiv preprint arXiv:2106.04803, 2021.

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.