Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
7-2017
Abstract
The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one or more of 4,716 classes. In this Kaggle competition, we placed in the top 3% out of 650 participants using released video and audio features. Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text. The newly introduced text data is termed as YouTube-8M-Text. We present a classification framework for the joint use of text, visual and audio features, and conduct an extensive set of experiments to quantify the benefit that this additional mode brings. The inclusion of text yields state-of-the-art results, e.g. 86.7% GAP on the YouTube-8M-Text validation dataset.
Discipline
Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
Workshop on YouTube-8M Large-Scale Video Understanding, co-located with IEEE Conference on Computer Vision and Pattern Recognition CVPR 2017, July 21-26: Proceedings
First Page
4321
Last Page
4329
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
WANG, Zhe; KUAN, Kingsley; RAVANT, Mathieu; MANEK, Gaurav; SONG, Sibo; FANG, Yuan; and et al.
Truly multi-modal YouTube-8M video classification with video, audio, and text. (2017). Workshop on YouTube-8M Large-Scale Video Understanding, co-located with IEEE Conference on Computer Vision and Pattern Recognition CVPR 2017, July 21-26: Proceedings. 4321-4329.
Available at: https://ink.library.smu.edu.sg/sis_research/4059
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.