# 3M: Multi-modal Multi-task Multi-teacher Learning for Game Event Detection

arXiv: https://arxiv.org/abs/2406.09076 · HTML: https://mlsanity.com/paper/2406.09076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers](https://mlsanity.com/paper/2106.01023/) (2021)
- [Information Overload in Group Communication: From Conversation to Cacophony in the Twitch Chat](https://mlsanity.com/paper/1610.06497/) (2016)

## Abstract (arXiv)

Esports has rapidly emerged as a global phenomenon with an ever-expanding audience via platforms, like YouTube. Due to the inherent complexity nature of the game, it is challenging for newcomers to comprehend what the event entails. The chaotic nature of online chat, the fast-paced speech of the game commentator, and the game-specific user interface further compound the difficulty for users in comprehending the gameplay. To overcome these challenges, it is crucial to integrate the Multi-Modal (MM) information from the platform and understand the event. The paper introduces a new MM multi-teacher-based game event detection framework, with the ultimate goal of constructing a comprehensive framework that enhances the comprehension of the ongoing game situation. While conventional MM models typically prioritise aligning MM data through concurrent training towards a unified objective, our framework leverages multiple teachers trained independently on different tasks to accomplish the Game Event Detection. The experiment clearly shows the effectiveness of the proposed MM multi-teacher framework.