NAC-TCN：用于情感理解的具有因果膨胀邻域注意力机制的时间卷积网络
NAC-TCN: Temporal Convolutional Networks with Causal Dilated Neighborhood Attention for Emotion Understanding
AI总结：
提出NAC-TCN模型，通过引入因果膨胀邻域注意力与卷积结合，在降低计算和内存开销的同时，于标准情感识别数据集上以更少参数达到或超越现有主流方法性能。
摘要：
在视频情感识别任务中，一项关键改进是关注随时间变化的情感而非单一帧。已有许多架构解决此任务，如GRUs、LSTMs、Self-Attention、Transformers和时间卷积网络（TCNs）。然而，这些方法存在内存占用高、计算量大或梯度表现差的问题。我们提出了一种名为Neighborhood Attention with Convolutions TCN（NAC-TCN）的方法，它结合了注意力机制和时间卷积网络的优势，同时确保理解因果关系，从而降低了计算和内存开销。我们通过引入因果版本的膨胀邻域注意力机制并将其与卷积相结合来实现这一点。在标准情感识别数据集上，我们的模型在性能上与TCNs、TCAN、LSTMs和GRUs相当、更优或达到最先进水平，且所需参数更少。我们在线发布了代码，以便于复现和用于其他项目。
英文摘要：
In the task of emotion recognition from videos, a key improvement has been to focus on emotions over time rather than a single frame. There are many architectures to address this task such as GRUs, LSTMs, Self-Attention, Transformers, and Temporal Convolutional Networks (TCNs). However, these methods suffer from high memory usage, large amounts of operations, or poor gradients. We propose a method known as Neighborhood Attention with Convolutions TCN (NAC-TCN) which incorporates the benefits of attention and Temporal Convolutional Networks while ensuring that causal relationships are understood which results in a reduction in computation and memory cost. We accomplish this by introducing a causal version of Dilated Neighborhood Attention while incorporating it with convolutions. Our model achieves comparable, better, or state-of-the-art performance over TCNs, TCAN, LSTMs, and GRUs while requiring fewer parameters on standard emotion recognition datasets. We publish our code online for easy reproducibility and use in other projects.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
