让记忆门随输入动态调整，提升人类行为预测准确性
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation
- 用专家混合机制动态选择记忆门矩阵
- 在3个数据集上均超越现有最先进方法
- 适合需要长期行为预判的智能系统研究者
我们提出MixANT，一种用于人类活动随机长期密集预测的新架构。尽管近期状态空间模型（如Mamba）通过输入依赖的选择性在三个关键参数上表现优异，但控制时间记忆的核心遗忘门（$ extbf{A}$矩阵）仍保持静态。为此，我们引入专家混合方法，根据输入特征动态选择上下文相关的$ extbf{A}$矩阵，提升表征能力的同时不牺牲计算效率。在50Salads、Breakfast和Assembly101数据集上的大量实验表明，MixANT在所有评估设置中持续优于现有最先进方法。结果凸显了输入依赖遗忘门机制在多样化真实场景中可靠预测人类行为的重要性。
原文摘要 · Abstract (English)
We present MixANT, a novel architecture for stochastic long-term dense anticipation of human activities. While recent State Space Models (SSMs) like Mamba have shown promise through input-dependent selectivity on three key parameters, the critical forget-gate ($\textbf{A}$ matrix) controlling temporal memory remains static. We address this limitation by introducing a mixture of experts approach that dynamically selects contextually relevant $\textbf{A}$ matrices based on input features, enhancing representational capacity without sacrificing computational efficiency. Extensive experiments on the 50Salads, Breakfast, and Assembly101 datasets demonstrate that MixANT consistently outperforms state-of-the-art methods across all evaluation settings. Our results highlight the importance of input-dependent forget-gate mechanisms for reliable prediction of human behavior in diverse real-world scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。