{"total":492,"rows":[{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2103.15792","title":"Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework","created":"2021-03-29","cited_by_count":174,"area":null},{"id":"2105.03790","title":"Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study","created":"2021-05-08","cited_by_count":168,"area":null},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93,"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":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85,"area":null},{"id":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","cited_by_count":84,"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":"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":"2207.10299","title":"Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition","created":"2022-07-21","cited_by_count":67,"area":null},{"id":"2401.01219","title":"Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond","created":"2024-01-02","cited_by_count":60,"area":null},{"id":"2108.08504","title":"Understanding and Mitigating Annotation Bias in Facial Expression Recognition","created":"2021-08-19","cited_by_count":50,"area":null},{"id":"2205.10237","title":"M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database","created":"2022-05-09","cited_by_count":50,"area":null},{"id":"2103.16854","title":"Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion","created":"2021-03-31","cited_by_count":49,"area":null},{"id":"2203.12367","title":"Transformer-based Multimodal Information Fusion for Facial Expression Analysis","created":"2022-03-23","cited_by_count":49,"area":null},{"id":"2204.04083","title":"POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition","created":"2022-04-08","cited_by_count":49,"area":null},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44,"area":"mllm"},{"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":"2308.11509","title":"SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation","created":"2023-08-22","cited_by_count":39,"area":null},{"id":"2312.05447","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos","created":"2023-12-09","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":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35,"area":null},{"id":"2203.14779","title":"A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition","created":"2022-03-28","cited_by_count":34,"area":null},{"id":"2403.12960","title":"FaceXFormer: A Unified Transformer for Facial Analysis","created":"2024-03-19","cited_by_count":34,"area":null},{"id":"2104.03509","title":"Py-Feat: Python Facial Expression Analysis Toolbox","created":"2021-04-08","cited_by_count":33,"area":null},{"id":"2203.12341","title":"Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin","created":"2022-03-23","cited_by_count":32,"area":null},{"id":"2205.04442","title":"MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition","created":"2022-05-09","cited_by_count":31,"area":null},{"id":"2103.09154","title":"Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition","created":"2021-03-16","cited_by_count":30,"area":null},{"id":"2209.10448","title":"Uncertainty-aware Label Distribution Learning for Facial Expression Recognition","created":"2022-09-21","cited_by_count":30,"area":null},{"id":"2407.02157","title":"FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs","created":"2024-07-02","cited_by_count":30,"area":null},{"id":"2403.04697","title":"AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors","created":"2024-03-07","cited_by_count":29,"area":null},{"id":"2303.00193","title":"CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition","created":"2023-03-01","cited_by_count":28,"area":null},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"area":null},{"id":"2101.04215","title":"Multimodal Engagement Analysis from Facial Videos in the Classroom","created":"2021-01-11","cited_by_count":27,"area":null},{"id":"2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","created":"2021-06-08","cited_by_count":27,"area":null},{"id":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27,"area":null},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26,"area":null},{"id":"2109.01812","title":"Stimuli-Aware Visual Emotion Analysis","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2501.05710","title":"EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model","created":"2025-01-10","cited_by_count":26,"area":null},{"id":"2301.12149","title":"POSTER++: A simpler and stronger facial expression recognition network","created":"2023-01-28","cited_by_count":25,"area":null},{"id":"2303.10849","title":"Multi-modal Facial Affective Analysis based on Masked Autoencoder","created":"2023-03-20","cited_by_count":23,"area":null},{"id":"2103.11436","title":"Responsible AI: Gender bias assessment in emotion recognition","created":"2021-03-21","cited_by_count":22,"area":null},{"id":"2201.11095","title":"Self-attention fusion for audiovisual emotion recognition with incomplete data","created":"2022-01-26","cited_by_count":22,"area":null},{"id":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2303.11225","title":"HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details","created":"2023-03-20","cited_by_count":22,"area":null},{"id":"2402.01355","title":"FindingEmo: An Image Dataset for Emotion Recognition in the Wild","created":"2024-02-02","cited_by_count":22,"area":null},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21,"area":null},{"id":"2111.04129","title":"Global-Local Attention for Emotion Recognition","created":"2021-11-07","cited_by_count":20,"area":null},{"id":"2402.08360","title":"Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks","created":"2024-02-13","cited_by_count":20,"area":"mllm"},{"id":"2103.10189","title":"Learning to Amend Facial Expression Representation via De-albino and Affinity","created":"2021-03-18","cited_by_count":19,"area":null},{"id":"2107.03107","title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","created":"2021-07-07","cited_by_count":18,"area":null},{"id":"2107.03708","title":"Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition","created":"2021-07-08","cited_by_count":18,"area":null},{"id":"2201.05297","title":"MMNet: Muscle motion-guided network for micro-expression recognition","created":"2022-01-14","cited_by_count":18,"area":null},{"id":"2308.10713","title":"LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis","created":"2023-08-18","cited_by_count":18,"area":null},{"id":"2403.10825","title":"Affective Behaviour Analysis via Integrating Multi-Modal Knowledge","created":"2024-03-16","cited_by_count":18,"area":null},{"id":"2405.19100","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","created":"2024-05-29","cited_by_count":18,"area":null},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"id":"2103.08310","title":"EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognition","created":"2021-03-10","cited_by_count":17,"area":null},{"id":"2203.13052","title":"Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition","created":"2022-03-24","cited_by_count":17,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2307.09023","title":"LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2310.19636","title":"Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition","created":"2023-10-30","cited_by_count":17,"area":null},{"id":"2403.02138","title":"Self-Supervised Facial Representation Learning with Facial Region Awareness","created":"2024-03-04","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":"2210.15878","title":"Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation","created":"2022-10-28","cited_by_count":16,"area":null},{"id":"2303.00180","title":"MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimation","created":"2023-03-01","cited_by_count":16,"area":null},{"id":"2304.00058","title":"Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding","created":"2023-03-31","cited_by_count":16,"area":null},{"id":"2409.17717","title":"Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkit","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2103.08134","title":"Detection and Localization of Facial Expression Manipulations","created":"2021-03-15","cited_by_count":15,"area":null},{"id":"2203.13032","title":"Multi-modal Emotion Estimation for in-the-wild Videos","created":"2022-03-24","cited_by_count":15,"area":null},{"id":"2409.02828","title":"ExpLLM: Towards Chain of Thought for Facial Expression Recognition","created":"2024-09-04","cited_by_count":15,"area":"lr"},{"id":"2503.10399","title":"HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2504.16405","title":"EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment","created":"2025-04-23","cited_by_count":15,"area":"mllm"},{"id":"2103.15599","title":"Graph-based Facial Affect Analysis: A Review","created":"2021-03-29","cited_by_count":14,"area":null},{"id":"2303.12745","title":"Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2305.17895","title":"ReSup: Reliable Label Noise Suppression for Facial Expression Recognition","created":"2023-05-29","cited_by_count":14,"area":null},{"id":"2404.09010","title":"MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild","created":"2024-04-13","cited_by_count":14,"area":null},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2407.11243","title":"Representation Learning and Identity Adversarial Training for Facial Behavior Understanding","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2407.19809","title":"Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRS","created":"2024-07-29","cited_by_count":14,"area":null},{"id":"2505.19328","title":"BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change","created":"2025-05-25","cited_by_count":14,"area":null},{"id":"2107.14203","title":"Did the Model Change? Efficiently Assessing Machine Learning API Shifts","created":"2021-07-29","cited_by_count":13,"area":null},{"id":"2209.08289","title":"Continuously Controllable Facial Expression Editing in Talking Face Videos","created":"2022-09-17","cited_by_count":13,"area":null},{"id":"2303.15889","title":"Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition","created":"2023-03-28","cited_by_count":13,"area":null},{"id":"2307.11404","title":"Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition","created":"2023-07-21","cited_by_count":13,"area":null},{"id":"2403.09500","title":"Faceptor: A Generalist Model for Face Perception","created":"2024-03-14","cited_by_count":13,"area":null},{"id":"2407.20175","title":"Towards Localized Fine-Grained Control for Facial Expression Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2410.20717","title":"Face-MLLM: A Large Face Perception Model","created":"2024-10-28","cited_by_count":13,"area":"mllm"},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2105.07484","title":"Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild","created":"2021-05-16","cited_by_count":12,"area":null},{"id":"2106.03487","title":"Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2107.03465","title":"An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild","created":"2021-07-07","cited_by_count":12,"area":null},{"id":"2107.04127","title":"Multitask Multi-database Emotion Recognition","created":"2021-07-08","cited_by_count":12,"area":null},{"id":"2205.14361","title":"Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher","created":"2022-05-28","cited_by_count":12,"area":null}],"next_cursor":"100"}