ME-TST+：基于ROI关系感知与时序状态转换的微表情分析
ME-TST+: Micro-expression Analysis via Temporal State Transition with ROI Relationship Awareness
AI总结：
本文提出基于状态空间模型的ME-TST和ME-TST+架构，通过时序状态转换机制将窗口级分类替换为视频级回归，并结合多粒度ROI建模与slowfast Mamba框架及定位识别协同策略，实现了最先进的微表情分析性能。
摘要：
微表情（MEs）被视为个体内在情绪、偏好和倾向的重要指标。ME分析需要在长视频序列中定位ME区间并识别其对应的情感类别。以往的深度学习方法通常采用滑动窗口分类网络。然而，固定窗口长度和硬分类在实际应用中存在显著局限。此外，这些方法通常将ME定位和识别视为两个独立任务，忽略了它们之间的本质联系。为应对这些挑战，本文提出了两种基于状态空间模型的架构，即ME-TST和ME-TST+，利用时序状态转换机制将传统的窗口级分类替换为视频级回归。这能更精确地刻画ME的时序动态，并支持对不同持续时间的ME进行建模。在ME-TST+中，我们进一步引入多粒度ROI建模和slowfast Mamba框架，以缓解将ME分析视为时间序列任务所带来的信息损失。此外，我们提出了一种在特征和结果层面的定位与识别协同策略，利用其内在联系来增强整体分析性能。大量实验表明，所提方法达到了最先进的性能。代码可在https://github.com/zizheng-guo/ME-TST获取。
英文摘要：
Micro-expressions (MEs) are regarded as important indicators of an individual's intrinsic emotions, preferences, and tendencies. ME analysis requires spotting of ME intervals within long video sequences and recognition of their corresponding emotional categories. Previous deep learning approaches commonly employ sliding-window classification networks. However, the use of fixed window lengths and hard classification presents notable limitations in practice. Furthermore, these methods typically treat ME spotting and recognition as two separate tasks, overlooking the essential relationship between them. To address these challenges, this paper proposes two state space model-based architectures, namely ME-TST and ME-TST+, which utilize temporal state transition mechanisms to replace conventional window-level classification with video-level regression. This enables a more precise characterization of the temporal dynamics of MEs and supports the modeling of MEs with varying durations. In ME-TST+, we further introduce multi-granularity ROI modeling and the slowfast Mamba framework to alleviate information loss associated with treating ME analysis as a time-series task. Additionally, we propose a synergy strategy for spotting and recognition at both the feature and result levels, leveraging their intrinsic connection to enhance overall analysis performance. Extensive experiments demonstrate that the proposed methods achieve state-of-the-art performance. The codes are available at https://github.com/zizheng-guo/ME-TST.
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。
