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.

该研究提出了一种新型的多模信息游戏事件检测框架，旨在构建一个综合框架，增强对进行中游戏情况的理解。实验证明了所提出的多模信息多教师框架的有效性。

3M：多模态多任务多教师学习用于游戏事件检测

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

This paper focuses on an important type of black-box attacks, i.e.,
transfer-based adversarial attacks, where the adversary generates adversarial
examples by a substitute (source) model and utilize them to attack an unseen
target model, without knowing its information. Existing methods tend to give
unsatisfactory adversarial transferability when the source and target models
are from different types of DNN architectures (e.g. ResNet-18 and Swin
Transformer). In this paper, we observe that the above phenomenon is induced by
the output inconsistency problem. To alleviate this problem while effectively
utilizing the existing DNN models, we propose a common knowledge learning (CKL)
framework to learn better network weights to generate adversarial examples with
better transferability, under fixed network architectures. Specifically, to
reduce the model-specific features and obtain better output distributions, we
construct a multi-teacher framework, where the knowledge is distilled from
different teacher architectures into one student network. By considering that
the gradient of input is usually utilized to generated adversarial examples, we
impose constraints on the gradients between the student and teacher models, to
further alleviate the output inconsistency problem and enhance the adversarial
transferability. Extensive experiments demonstrate that our proposed work can
significantly improve the adversarial transferability.

本文研究黑盒攻击的一种重要类型 —— 基于转移的对抗攻击，并提出了一种通用知识学习框架，通过构建多教师框架来减少模型特定特征，获得更好的输出分布，加强对抗转移性能，同时通过对学生和教师模型之间的梯度施加约束来进一步缓解输出不一致问题和增强对抗转移性能。实验表明，所提出的方法可以显著提高对抗转移性能。

生成可传递对抗样本的常识学习

Common Knowledge Learning for Generating Transferable Adversarial  Examples

Open compound domain adaptation (OCDA) considers the target domain as the
compound of multiple unknown homogeneous subdomains. The goal of OCDA is to
minimize the domain gap between the labeled source domain and the unlabeled
compound target domain, which benefits the model generalization to the unseen
domains. Current OCDA for semantic segmentation methods adopt manual domain
separation and employ a single model to simultaneously adapt to all the target
subdomains. However, adapting to a target subdomain might hinder the model from
adapting to other dissimilar target subdomains, which leads to limited
performance. In this work, we introduce a multi-teacher framework with
bidirectional photometric mixing to separately adapt to every target subdomain.
First, we present an automatic domain separation to find the optimal number of
subdomains. On this basis, we propose a multi-teacher framework in which each
teacher model uses bidirectional photometric mixing to adapt to one target
subdomain. Furthermore, we conduct an adaptive distillation to learn a student
model and apply consistency regularization to improve the student
generalization. Experimental results on benchmark datasets show the efficacy of
the proposed approach for both the compound domain and the open domains against
existing state-of-the-art approaches.

本文提出了一种基于多教师框架的光度混合自适应分割方法，用于解决开放式复合领域自适应问题，比现有方法效果更好。