Efficient Lightweight 3D-CNN using Frame Skipping and Contrast Enhancement for Facial Macro- and Micro-expression Spotting

• URL: http://arxiv.org/abs/2105.06340v1
• Date: Thu, 13 May 2021 14:55:06 GMT
• Title: Efficient Lightweight 3D-CNN using Frame Skipping and Contrast Enhancement for Facial Macro- and Micro-expression Spotting
• Authors: Chuin Hong Yap, Moi Hoon Yap, Adrian K. Davison, Ryan Cunningham
• Abstract summary: We construct an efficient lightweight 3D-Convolutional Network using Frame Skipping and Contrast Enhancement (EL-FACE) for the micro-expression spotting task. Our model achieves state-of-the-art performance in SAMM Long Videos and remained competitive in the CAS(ME)2 dataset.
• Score: 8.249165772349127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Micro-expression spotting is the preliminary step for any micro-expression related analysis to avoid excessive false positives. We propose an efficient lightweight macro- and micro-expression spotting method which takes advantage of the duration differences of macro- and micro-expressions. Using effective frame skips, local contrast normalisation, depthwise separable convolutions and residual connections, we construct Efficient Lightweight 3D-Convolutional Network using Frame Skipping and Contrast Enhancement (EL-FACE) for the micro-expression spotting task. Our model achieves state-of-the-art performance in SAMM Long Videos and remained competitive in the CAS(ME)2 dataset.

Related papers

• Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS [52.3215552448623]
  Novel View Synthesis (NVS) without Structure-from-Motion (SfM) pre-processed camera poses are crucial for promoting rapid response capabilities and enhancing robustness against variable operating conditions. Recent SfM-free methods have integrated pose optimization, designing end-to-end frameworks for joint camera pose estimation and NVS. Most existing works rely on per-pixel image loss functions, such as L2 loss. In this study, we propose a correspondence-guided SfM-free 3D Gaussian splatting for NVS.
  arXiv  Detail & Related papers  (2024-08-16T13:11:22Z)
• SpotFormer: Multi-Scale Spatio-Temporal Transformer for Facial Expression Spotting [11.978551396144532]
  In this paper, we propose an efficient framework for facial expression spotting. First, we propose a Sliding Window-based Multi-Resolution Optical flow (SW-MRO) feature, which calculates multi-resolution optical flow of the input sequence within compact sliding windows. Second, we propose SpotFormer, a multi-scale-temporal Transformer that simultaneously encodes facial-temporal relationships of the SW-MRO features for accurate frame-level probability estimation. Third, we introduce supervised contrastive learning into SpotFormer to enhance the discriminability between different types of expressions.
  arXiv  Detail & Related papers  (2024-07-30T13:02:08Z)
• Adaptive Temporal Motion Guided Graph Convolution Network for Micro-expression Recognition [48.21696443824074]
  We propose a novel framework for micro-expression recognition, named the Adaptive Temporal Motion Guided Graph Convolution Network (ATM-GCN) Our framework excels at capturing temporal dependencies between frames across the entire clip, thereby enhancing micro-expression recognition at the clip level.
  arXiv  Detail & Related papers  (2024-06-13T10:57:24Z)
• From Macro to Micro: Boosting micro-expression recognition via pre-training on macro-expression videos [9.472210792839023]
  Micro-expression recognition (MER) has drawn increasing attention in recent years due to its potential applications in intelligent medical and lie detection. We propose a generalized transfer learning paradigm, called textbfMAcro-expression textbfTO textbfMIcro-expression (MA2MI) Under our paradigm, networks can learns the ability to represent subtle facial movement by reconstructing future frames.
  arXiv  Detail & Related papers  (2024-05-26T06:42:06Z)
• DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models [85.4852517178828]
  We present DualFocus, a framework for integrating macro and micro perspectives within multi-modal large language models (MLLMs) We demonstrate DualFocus's superiority in balancing detailed examination with holistic insight, significantly reducing hallucination instances in MLLMs.
  arXiv  Detail & Related papers  (2024-02-22T18:26:02Z)
• Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition [24.75382410411772]
  This paper focuses on the research of micro-expression recognition (MER) It proposes a flexible and reliable deep learning method called learning to rank onset--offset representations (LTR3O)
  arXiv  Detail & Related papers  (2023-10-07T03:09:53Z)
• Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction [65.5397271106534]
  A single neural network is difficult to handle all exposure problems. In particular, convolutions hinder the ability to restore faithful color or details on extremely over-/under- exposed regions. We propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction.
  arXiv  Detail & Related papers  (2023-09-02T09:07:36Z)
• Short and Long Range Relation Based Spatio-Temporal Transformer for Micro-Expression Recognition [61.374467942519374]
  We propose a novel a-temporal transformer architecture -- to the best of our knowledge, the first purely transformer based approach for micro-expression recognition. The architecture comprises a spatial encoder which learns spatial patterns, a temporal dimension classification for temporal analysis, and a head. A comprehensive evaluation on three widely used spontaneous micro-expression data sets, shows that the proposed approach consistently outperforms the state of the art.
  arXiv  Detail & Related papers  (2021-12-10T22:10:31Z)
• Shallow Optical Flow Three-Stream CNN for Macro- and Micro-Expression Spotting from Long Videos [15.322908569777551]
  We propose a model to predict a score that captures the likelihood of a frame being in an expression interval. We demonstrate the efficacy and efficiency of the proposed approach on the recent MEGC 2020 benchmark.
  arXiv  Detail & Related papers  (2021-06-11T16:19:48Z)
• Self-Supervised Multi-Frame Monocular Scene Flow [61.588808225321735]
  We introduce a multi-frame monocular scene flow network based on self-supervised learning. We observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.
  arXiv  Detail & Related papers  (2021-05-05T17:49:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.