Approach for Video Classification with Multi-Label on YouTube-8m Dataset

Kwangsoo Shin, Junhyeong Jeon, Seungbin Lee, Boyoung Lim, Minsoo Jeong, Jongho Nang

ECCVW 2018 pp. 317-324

doi:10.1007/978-3-030-11018-5_29 /eccvw/2018/shin2018eccvw-approach/

Abstract

Video traffic is increasing at a considerable rate due to the spread of personal media and advancements in media technology. Accordingly, there is a growing need for techniques to automatically classify moving images. This paper use NetVLAD and NetFV models and the Huber loss function for video classification problem and YouTube-8M dataset to verify the experiment. We tried various attempts according to the dataset and optimize hyperparameters, ultimately obtain a GAP score of 0.8668.

PDF ECCVW Semantic Scholar

Cite

Text

Shin et al. "Approach for Video Classification with Multi-Label on YouTube-8m Dataset." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11018-5_29

Markdown

[Shin et al. "Approach for Video Classification with Multi-Label on YouTube-8m Dataset." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/shin2018eccvw-approach/) doi:10.1007/978-3-030-11018-5_29

BibTeX

@inproceedings{shin2018eccvw-approach,
  title     = {{Approach for Video Classification with Multi-Label on YouTube-8m Dataset}},
  author    = {Shin, Kwangsoo and Jeon, Junhyeong and Lee, Seungbin and Lim, Boyoung and Jeong, Minsoo and Nang, Jongho},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {317-324},
  doi       = {10.1007/978-3-030-11018-5_29},
  url       = {https://mlanthology.org/eccvw/2018/shin2018eccvw-approach/}
}