Rethinking Optical Flow Methods for Micro-Expression Spotting

Micro-expressions (MEs) spotting is popular in some fields, for example, criminal investigation and business communication. But it is still a challenging task to spot the onset and offset of MEs accurately in long videos. This paper refines every step of the workflow before feature extraction, which can reduce error propagation. The workflow takes the advantage of high-quality alignment method, more accurate landmark detector, and also more robust optical flow estimation. Besides, Bayesian optimization hybrid with Nash equilibrium is constructed to search for the optimal parameters. It uses two players to optimize two types of parameters, one player is used to control the ME peak spotting, and another for optical flow field extraction. The algorithm can reduce the search space for each player with better generalization. Finally, our spotting method is evaluated on MEGC2022 spotting task, and achieves F-1-score 0.3564 on CAS(ME)(3)-UNSEEN and F-1-score 0.3265 on SAMM-UNSEEN.