Facial Expression Analysis under Partial Occlusion: A Survey

Abstract

Automatic machine-based Facial Expression Analysis (FEA) has made substantial progress in the past few decades driven by its importance for applications in psychology, security, health, entertainment and human computer interaction. The vast majority of completed FEA studies are based on non-occluded faces collected in a controlled laboratory environment. Automatic expression recognition tolerant to partial occlusion remains less understood, particularly in real-world scenarios. In recent years, efforts investigating techniques to handle partial occlusion for FEA have seen an increase. The context is right for a comprehensive perspective of these developments and the state of the art from this perspective. This survey provides such a comprehensive review of recent advances in dataset creation, algorithm development, and investigations of the effects of occlusion critical for robust performance in FEA systems. It outlines existing challenges in overcoming partial occlusion and discusses possible opportunities in advancing the technology. To the best of our knowledge, it is the first FEA survey dedicated to occlusion and aimed at promoting better informed and benchmarked future work.

Authors pre-print of the article accepted for publication in ACM Computing Surveys (accepted on 02-Nov-2017)

Cited by in corpus (37)

• Social physics
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• Filter-enhanced MLP is All You Need for Sequential Recommendation
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Bootstrap Latent Representations for Multi-modal Recommendation
• Medical Deep Learning -- A systematic Meta-Review
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Towards Natural Language Interfaces for Data Visualization: A Survey
• Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis
• Neural Collaborative Reasoning
• Dynamic Facial Expression Recognition under Partial Occlusion with Optical Flow Reconstruction
• Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
• How to Index Item IDs for Recommendation Foundation Models
• Multi-Task Recommendations with Reinforcement Learning
• Causal Collaborative Filtering
• Network representation learning systematic review: ancestors and current development state
• Image Amodal Completion: A Survey
• Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention
• "Centralized or Decentralized?": Concerns and Value Judgments of Stakeholders in the Non-Fungible Tokens (NFTs) Market
• Economic Recommender Systems -- A Systematic Review
• Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
• A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• Recommending on graphs: a comprehensive review from a data perspective
• Exploring Lottery Ticket Hypothesis in Media Recommender Systems
• Adversarial learning for product recommendation
• Deep Learning Approach for Matrix Completion Using Manifold Learning
• Mostra: A Flexible Balancing Framework to Trade-off User, Artist and Platform Objectives for Music Sequencing
• Regulating Group Exposure for Item Providers in Recommendation
• OSP: Boosting Distributed Model Training with 2-stage Synchronization
• A Systematic Literature Review on Process-Aware Recommender Systems
• Data-Driven Forecasting of Non-Equilibrium Solid-State Dynamics
• Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?
• Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion
• Towards Two-Stage Counterfactual Learning to Rank