# 3D-CNN for Facial Micro- and Macro-expression Spotting on Long Video Sequences using Temporal Oriented Reference Frame

Source: [3D-CNN for Facial Micro- and Macro-expression Spotting on Long Video Sequences using Temporal Oriented Reference Frame](<https://www.sota2.com/research/paper/68fa6ca51e209131cea35318>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:53.744Z

Authors: Chuin Hong Yap, Moi Hoon Yap, Adrian K. Davison, Connah Kendrick, Jingting Li, Sujing Wang, Ryan Cunningham

Published: 2021-05-13T14:55:06.000Z

## Abstract

Facial expression spotting is the preliminary step for micro- and macro-expression analysis. The task of reliably spotting such expressions in video sequences is currently unsolved. The current best systems depend upon optical flow methods to extract regional motion features, before categorisation of that motion into a specific class of facial movement. Optical flow is susceptible to drift error, which introduces a serious problem for motions with long-term dependencies, such as high frame-rate macro-expression. We propose a purely deep learning solution which, rather than tracking frame differential motion, compares via a convolutional model, each frame with two temporally local reference frames. Reference frames are sampled according to calculated micro- and macro-expression duration. As baseline for MEGC2021 using leave-one-subject-out evaluation method, we show that our solution achieves F1-score of 0.105 in a high frame-rate (200 fps) SAMM long videos dataset (SAMM-LV) and is competitive in a low frame-rate (30 fps) (CAS(ME)2) dataset. On unseen MEGC2022 challenge dataset, the baseline results are 0.1176 on SAMM Challenge dataset, 0.1739 on CAS(ME)3 and overall performance of 0.1531 on both dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Facial Expression Spotting on CAS(ME)2](<https://www.sota2.com/research/sota/facial-expression-spotting-on-cas-me-2.md>): Facial Expression Spotting; CAS(ME)2; Overall F1-score: 16.75.

- [Facial expression spotting on SAMM-LV](<https://www.sota2.com/research/sota/facial-expression-spotting-on-samm-lv.md>): Facial Expression Spotting; SAMM-LV; ME F1-score: 4.66.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.06340>)

[PDF](<https://arxiv.org/pdf/2105.06340.pdf>)