跨被试脑电到视频重建及超越
Cross-Subject EEG-to-Video Reconstruction and Beyond
SAM-Net 的跨被试对齐思路（中心渐进式对抗 + New2Source 映射）可迁移到其他需要跨域泛化的视觉生成任务，如跨摄像头行人重识别或跨模态视频生成；其 HRT 编码器对多通道时序信号的区域引导交互设计，对处理多传感器时序数据有参考价值。
原文依据 we propose a Subject Adversarial and Mapping Network (SAM-Net)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从脑电图（EEG）重建视频内容是一项具有重要科学意义的研究任务。然而，由于被试间生理状态的差异以及信号采集配置的变化，该任务面临跨被试生成不一致的挑战。为解决此问题，我们提出了被试对抗与映射网络（SAM-Net）。在 SAM-Net 中，我们首先引入混合区域-时序（HRT）编码器，以脑区引导的方式进行通道间语义交互，并聚合不同时间尺度上的时序语义。其次，我们提出中心渐进式被试对抗（C-SA）机制，逐步缩小不同被试间的度量距离，从而获得统一且稳定的语义表示。第三，我们设计了 New2Source 映射器，将新被试的 EEG 分布与多个已知被试的分布对齐。最后，我们采用关键帧引导的连续语义生成范式，驱动连贯高质量视频的生成。大量实验验证了我们的 SAM-Net 在跨被试 EEG 到视频生成任务中的竞争性性能，以及在涉及新被试的生成任务中的优异表现。
英文原文摘要 1268 字符
Reconstructing video content from EEG (electroencephalogram) is a research task of significant scientific importance. However, due to inter-subject differences in physiological states and variations in signal acquisition configurations, this task faces the challenge of inconsistent cross-subject generation.To address this, we propose a Subject Adversarial and Mapping Network (SAM-Net). In SAM-Net, we first introduce a Hybrid Region-Temporal (HRT) Encoder to conduct inter-channel semantic interactions guided by brain regions and aggregate temporal semantics across different time scales. Secondly, we propose a Centered-progressive Subject Adversarial (C-SA) Mechanism to gradually narrow the metric distance between different subjects, thereby obtaining a unified and stable semantic representation. Thirdly, we design a New2Source Mapper to align the EEG distribution of new subjects with that of multiple known subjects. Finally, we adopt a keyframe-guided continuous semantic generation paradigm to drive the production of coherent and high-quality videos. Extensive experiments validate the competitive performance of our SAM-Net in cross-subject EEG-to-Video generation tasks, as well as its excellent performance in generation tasks involving new subjects.