Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders
Not on the map. Why?
Abstract (arXiv)
Automated facial expression quality assessment (FEQA) in neurological disorders is critical for enhancing diagnostic accuracy and improving patient care, yet effectively capturing the subtle motions and nuances of facial muscle movements remains a challenge. We propose to analyse facial landmark trajectories, a compact yet informative representation, that encodes these subtle motions from a high-level structural perspective. Hence, we introduce Trajectory-guided Motion Perception Transformer (TraMP-Former), a novel FEQA framework that fuses landmark trajectory features for fine-grained motion capture with visual semantic cues from RGB frames, ultimately regressing the combined features into a quality score. Extensive experiments demonstrate that TraMP-Former achieves new state-of-the-art performance on benchmark datasets with neurological disorders, including PFED5 (up by 6.51%) and an augmented Toronto NeuroFace (up by 7.62%). Our ablation studies further validate the efficiency and effectiveness of landmark trajectories in FEQA. Our code is available at https://github.com/shuchaoduan/TraMP-Former.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 66 references that are in the map. First posted on arXiv 13 Apr 2025.
Builds on
24 of 66 references.
References · 24
- 2023CoTracker: It is Better to Track Togethercited by 522
- 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 287
- 2020DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wildcited by 128
- 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 120
- 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 89
- 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
- 2020Uncertainty-aware Score Distribution Learning for Action Quality Assessmentcited by 80
- 2018Action Quality Assessment Across Multiple Actionscited by 79
- 2021Group-aware Contrastive Regression for Action Quality Assessmentcited by 75
- 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
- 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 47
- 2022Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wildcited by 41
12 more
- 2023From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videoscited by 39
- 2016Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networkscited by 32
- 2022Action Quality Assessment with Temporal Parsing Transformercited by 31
- 2024CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignmentcited by 17
- 2023TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identificationcited by 14
- 2020Deep Domain Adaptation for Ordinal Regression of Pain Intensity Estimation Using Weakly-Labelled Videoscited by 11
- 2024Interpretable Long-term Action Quality Assessmentcited by 7
- 2020Synthetic Expressions are Better Than Real for Learning to Detect Facial Actionscited by 4
- 2022Facial Expression Analysis Using Decomposed Multiscale Spatiotemporal Networkscited by 4
- 2022Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matricescited by 4
- 2023QAFE-Net: Quality Assessment of Facial Expressions with Landmark Heatmapscited by 2
- 2024Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identificationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.