{"total":56,"rows":[{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180,"area":null},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151,"area":null},{"id":"2104.00232","title":"Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition","created":"2021-04-01","cited_by_count":89,"area":null},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81,"area":null},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80,"area":null},{"id":"2203.09463","title":"FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos","created":"2022-03-17","cited_by_count":69,"area":null},{"id":"2208.00847","title":"MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-01","cited_by_count":65,"area":null},{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48,"area":null},{"id":"2307.02227","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","created":"2023-07-05","cited_by_count":43,"area":null},{"id":"2103.17107","title":"Facial expression and attributes recognition based on multi-task learning of lightweight neural networks","created":"2021-03-31","cited_by_count":40,"area":null},{"id":"2403.06375","title":"FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization","created":"2024-03-11","cited_by_count":39,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37,"area":null},{"id":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33,"area":null},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32,"area":null},{"id":"2205.04749","title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2206.04975","title":"NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition","created":"2022-06-10","cited_by_count":27,"area":null},{"id":"2102.11464","title":"FaceController: Controllable Attribute Editing for Face in the Wild","created":"2021-02-23","cited_by_count":22,"area":null},{"id":"2111.04129","title":"Global-Local Attention for Emotion Recognition","created":"2021-11-07","cited_by_count":20,"area":null},{"id":"2403.01901","title":"FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","cited_by_count":18,"area":null},{"id":"2202.12951","title":"Model Attribution of Face-swap Deepfake Videos","created":"2022-02-25","cited_by_count":17,"area":null},{"id":"2203.13436","title":"Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devices","created":"2022-03-25","cited_by_count":16,"area":null},{"id":"2303.15477","title":"Adaptive Log-Euclidean Metrics for SPD Matrix Learning","created":"2023-03-26","cited_by_count":13,"area":null},{"id":"2101.00317","title":"Identity-aware Facial Expression Recognition in Compressed Video","created":"2021-01-01","cited_by_count":9,"area":null},{"id":"2105.06421","title":"Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2503.14295","title":"PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2412.17616","title":"Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2508.13442","title":"EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2503.00202","title":"MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2311.03782","title":"CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videos","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2401.05625","title":"Face-GPS: A Comprehensive Technique for Quantifying Facial Muscle Dynamics in Videos","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2407.19894","title":"CardioSyntax: end-to-end SYNTAX score prediction -- dataset, benchmark and method","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2409.19501","title":"Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2503.19416","title":"EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2201.06868","title":"A Study on the Ambiguity in Human Annotation of German Oral History Interviews for Perceived Emotion Recognition and Sentiment Analysis","created":"2022-01-18","cited_by_count":2,"area":null},{"id":"2208.10221","title":"Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition","created":"2022-08-22","cited_by_count":2,"area":null},{"id":"2407.02361","title":"GCF: Graph Convolutional Networks for Facial Expression Recognition","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2506.11477","title":"FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2601.01847","title":"ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2104.05971","title":"Learning Multi-modal Information for Robust Light Field Depth Estimation","created":"2021-04-13","cited_by_count":1,"area":null},{"id":"2104.08373","title":"Constructing Robust Emotional State-based Feature with a Novel Voting Scheme for Multi-modal Deception Detection in Videos","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2107.04569","title":"Seven Basic Expression Recognition Using ResNet-18","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2110.04481","title":"Comparing Facial Expression Recognition in Humans and Machines: Using CAM, GradCAM, and Extremal Perturbation","created":"2021-10-09","cited_by_count":1,"area":null},{"id":"2209.07629","title":"Self-Relation Attention and Temporal Awareness for Emotion Recognition via Vocal Burst","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2304.12194","title":"Neural Architecture Search Using Genetic Algorithm for Facial Expression Recognition","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2410.05074","title":"xLSTM-FER: Enhancing Student Expression Recognition with Extended Vision Long Short-Term Memory Network","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2506.20867","title":"Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.20615","title":"EmoCAST: Emotional Talking Portrait via Emotive Text Description","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.19749","title":"Talking Head Generation via AU-Guided Landmark Prediction","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2604.07786","title":"Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2110.04476","title":"Label quality in AffectNet: results of crowd-based re-annotation","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2211.00233","title":"Detection of (Hidden) Emotions from Videos using Muscles Movements and Face Manifold Embedding","created":"2022-11-01","cited_by_count":0,"area":null},{"id":"2301.00964","title":"e-Inu: Simulating A Quadruped Robot With Emotional Sentience","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2510.24777","title":"Cross-Enhanced Multimodal Fusion of Eye-Tracking and Facial Features for Alzheimer's Disease Diagnosis","created":"2025-10-25","cited_by_count":0,"area":null}],"next_cursor":null}