Research map / Video / Action recognition
Revisiting the Volumetric Data of 4DME: Compression, Extension and Benchmarking for Micro-Expression Analysis
Samuel Boccara, Amar Tious, Guoying Zhao, Yante Li, Toinon Vigier, Vincent Ricordel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add depth flow stream to RGB-only stream (ablation) | VoluME-SSSNet · Extended 4DME LOSO | F1: 0.405 -> 0.485 | Improved |
| add RGB flow stream to depth-only stream (ablation) | VoluME-SSSNet · Extended 4DME LOSO | F1: 0.364 -> 0.485 | Improved |
| add depth flow stream to RGB-only stream (ablation) | VoluME-SSSNet · 4DME/CASME3 LODO | F1: 0.300 -> 0.389 | Improved |
| add RGB flow stream to depth-only stream (ablation) | VoluME-SSSNet · 4DME/CASME3 LODO | F1: 0.312 -> 0.389 | Improved |
| use feature-level fusion instead of input-level fusion (ablation) | VoluME-SSSNet · Extended 4DME LOSO | F1: 0.396 -> 0.485 | Improved |
| use feature-level fusion instead of input-level fusion (ablation) | VoluME-SSSNet · 4DME/CASME3 LODO | F1: 0.217 -> 0.389 | Improved |
| add optical strain to dual-stream flow features (ablation) | VoluME-SSSNet · Extended 4DME LOSO | F1: 0.364 -> 0.485 | Improved |
| add optical strain to dual-stream flow features (ablation) | VoluME-SSSNet · 4DME/CASME3 LODO | F1: 0.175 -> 0.389 | Improved |
| compress input with V-PCC R3 (1575x total ratio) | VoluME-SSSNet · Extended 4DME LOSO | macro-F1: 0.386 -> 0.384 | No clear effect |
| compress input with V-PCC R1 (5780x total ratio) | VoluME-SSSNet · Extended 4DME LOSO | macro-F1: 0.386 -> 0.314 | Hurt |
| compress input with Draco QP6 (16.0x geometry ratio) | VoluME-SSSNet · Extended 4DME LOSO | macro-F1: 0.386 -> 0.330 | Hurt |
| compress input with Draco QP9 | VoluME-SSSNet · Extended 4DME LOSO | macro-F1: 0.386 -> 0.376 | No clear effect |
Closest papers by meaning
- From Pixels to Semantics: Unified Facial Action Representation Learning for Micro-Expression Analysis (ICLR 2026 · similarity 0.90)
- Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (TPAMI 2021 · similarity 0.90)
- CAS(ME)3: A Third Generation Facial Spontaneous Micro-Expression Database with Depth Information and High Ecological Validity (TPAMI 2022 · similarity 0.90)
- FED-PsyAU: Privacy-Preserving Micro-Expression Recognition via Psychological AU Coordination and Dynamic Facial Motion Modeling (ICCV 2025 · similarity 0.89)
- MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution (TPAMI 2025 · similarity 0.88)
- MA-Bench: Towards Fine-grained Micro-Action Understanding (CVPR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
