UTS submission to Google YouTube-8M Challenge 2017
On the map: Mixture-of-experts → Vision mixture-of-experts
Abstract (arXiv)
In this paper, we present our solution to Google YouTube-8M Video Classification Challenge 2017. We leveraged both video-level and frame-level features in the submission. For video-level classification, we simply used a 200-mixture Mixture of Experts (MoE) layer, which achieves GAP 0.802 on the validation set with a single model. For frame-level classification, we utilized several variants of recurrent neural networks, sequence aggregation with attention mechanism and 1D convolutional models. We achieved GAP 0.8408 on the private testing set with the ensemble model. The source code of our models can be found in urlhttps://github.com/ffmpbgrnn/yt8m.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. First posted on arXiv 13 Jul 2017.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2017Large-Scale YouTube-8M Video Understanding with Deep Neural Networks ↗
- 2017Hierarchical Deep Recurrent Architecture for Video Understanding ↗
- 2026MVEB: Massive Video Embedding Benchmark
- 2023DeVAn: Dense Video Annotation for Video-Language Models
- 2026AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
- 2025REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding
- 2024Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning
- 2024Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input