The YouTube-8M Kaggle Competition: Challenges and Methods

June 28, 2017 · Entered Twilight · 🏛 arXiv.org

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CONTRIBUTING.md, LICENSE, README.md, __init__.py, average_precision_calculator.py, cloudml-4gpu.yaml, cloudml-gpu-distributed.yaml, cloudml-gpu.yaml, convert_prediction_from_json_to_csv.py, eval.py, eval_util.py, export_model.py, frame_level_models.py, inference.py, losses.py, mean_average_precision_calculator.py, model_utils.py, models.py, readers.py, run_frame.sh, run_video.sh, train.py, utils.py, video_level_models.py

Authors Haosheng Zou, Kun Xu, Jialian Li, Jun Zhu arXiv ID 1706.09274 Category cs.CV: Computer Vision Citations 13 Venue arXiv.org Repository https://github.com/taufikxu/youtube ⭐ 3 Last Checked 1 month ago

Abstract

We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time. In this paper, we present an extensive analysis and solution to the underlying machine-learning problem based on frame-level data, where major challenges are identified and corresponding preliminary methods are proposed. It's noteworthy that, with merely the proposed strategies and uniformly-averaging multi-crop ensemble was it sufficient for us to reach our ranking. We also report the methods we believe to be promising but didn't have enough time to train to convergence. We hope this paper could serve, to some extent, as a review and guideline of the YouTube-8M multi-label video classification benchmark, inspiring future attempts and research.