{"total":172,"rows":[{"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":"2106.15318","title":"Analysing Affective Behavior in the second ABAW2 Competition","created":"2021-06-14","cited_by_count":163,"area":null},{"id":"2202.10659","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges","created":"2022-02-22","cited_by_count":156,"area":null},{"id":"2207.01138","title":"ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges","created":"2022-07-03","cited_by_count":110,"area":null},{"id":"2303.01498","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges","created":"2023-03-02","cited_by_count":110,"area":null},{"id":"2402.19344","title":"The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition","created":"2024-02-29","cited_by_count":78,"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":"2407.03835","title":"7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition","created":"2024-07-04","cited_by_count":53,"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":"2303.00175","title":"A Deep Neural Architecture for Harmonizing 3-D Input Data Analysis and Decision Making in Medical Imaging","created":"2023-03-01","cited_by_count":39,"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":"2304.08981","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","created":"2023-04-18","cited_by_count":33,"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":"2403.02192","title":"Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans","created":"2024-03-04","cited_by_count":30,"area":null},{"id":"2112.00585","title":"Neural Emotion Director: Speech-preserving semantic control of facial expressions in \"in-the-wild\" videos","created":"2021-12-01","cited_by_count":28,"area":null},{"id":"2104.07123","title":"The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stress","created":"2021-04-14","cited_by_count":27,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2107.04187","title":"A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition","created":"2021-07-09","cited_by_count":24,"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":"2403.06242","title":"COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System","created":"2024-03-10","cited_by_count":23,"area":null},{"id":"2101.06053","title":"The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements","created":"2021-01-15","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":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21,"area":null},{"id":"2203.13031","title":"Continuous Emotion Recognition using Visual-audio-linguistic information: A Technical Report for ABAW3","created":"2022-03-24","cited_by_count":20,"area":null},{"id":"2206.04732","title":"AI-MIA: COVID-19 Detection & Severity Analysis through Medical Imaging","created":"2022-06-09","cited_by_count":20,"area":null},{"id":"2303.08356","title":"Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition","created":"2023-03-15","cited_by_count":20,"area":null},{"id":"2310.03485","title":"BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classification","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2107.04225","title":"A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis","created":"2021-07-09","cited_by_count":19,"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":"2209.09068","title":"Audio-Visual Fusion for Emotion Recognition in the Valence-Arousal Space Using Joint Cross-Attention","created":"2022-09-19","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":"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":"2103.13372","title":"Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition","created":"2021-03-24","cited_by_count":16,"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":"2303.00180","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":"2403.09915","title":"Robust Light-Weight Facial Affective Behavior Recognition with CLIP","created":"2024-03-14","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":"2107.01175","title":"Continuous Emotion Recognition with Audio-visual Leader-follower Attentive Fusion","created":"2021-07-02","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":"2403.13659","title":"Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition","created":"2024-03-20","cited_by_count":15,"area":null},{"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":"2103.15599","title":"Graph-based Facial Affect Analysis: A Review","created":"2021-03-29","cited_by_count":14,"area":null},{"id":"2403.10488","title":"Joint Multimodal Transformer for Emotion Recognition in the Wild","created":"2024-03-15","cited_by_count":14,"area":null},{"id":"2407.15728","title":"SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2506.05372","title":"DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarios","created":"2025-05-29","cited_by_count":13,"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":"2405.06749","title":"Ensuring UAV Safety: A Vision-only and Real-time Framework for Collision Avoidance Through Object Detection, Tracking, and Distance Estimation","created":"2024-05-10","cited_by_count":11,"area":null},{"id":"2107.04192","title":"Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Technique","created":"2021-07-09","cited_by_count":10,"area":null},{"id":"2203.13046","title":"Facial Action Unit Recognition With Multi-models Ensembling","created":"2022-03-24","cited_by_count":10,"area":null},{"id":"2203.13301","title":"Multi-modal Multi-label Facial Action Unit Detection with Transformer","created":"2022-03-24","cited_by_count":10,"area":null},{"id":"2207.09748","title":"Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2203.12531","title":"Multi-label Transformer for Action Unit Detection","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2203.12845","title":"Multiple Emotion Descriptors Estimation at the ABAW3 Challenge","created":"2022-03-24","cited_by_count":9,"area":null},{"id":"2203.12891","title":"An Ensemble Approach for Facial Expression Analysis in Video","created":"2022-03-24","cited_by_count":9,"area":null},{"id":"2203.13472","title":"Facial Expression Recognition with Swin Transformer","created":"2022-03-25","cited_by_count":9,"area":null},{"id":"2407.12927","title":"Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild","created":"2024-07-17","cited_by_count":9,"area":null},{"id":"2105.01502","title":"Technical Report for Valence-Arousal Estimation on Affwild2 Dataset","created":"2021-05-04","cited_by_count":8,"area":null},{"id":"2107.03886","title":"Causal affect prediction model using a facial image sequence","created":"2021-07-08","cited_by_count":8,"area":null},{"id":"2203.13235","title":"Facial Expression Recognition based on Multi-head Cross Attention Network","created":"2022-03-24","cited_by_count":8,"area":null},{"id":"2303.09293","title":"A transformer-based approach to video frame-level prediction in Affective Behaviour Analysis In-the-wild","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2303.10590","title":"Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wild","created":"2023-03-19","cited_by_count":8,"area":null},{"id":"2403.11942","title":"Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modeling","created":"2024-03-18","cited_by_count":8,"area":null},{"id":"2407.11663","title":"Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2407.12390","title":"Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks: Application to 7th ABAW Challenge","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2503.12623","title":"MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2203.13285","title":"Continuous-Time Audiovisual Fusion with Recurrence vs. Attention for In-The-Wild Affect Recognition","created":"2022-03-24","cited_by_count":7,"area":null},{"id":"2303.09162","title":"EmotiEffNet Facial Features in Uni-task Emotion Recognition in Video at ABAW-5 competition","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2303.10644","title":"Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection","created":"2023-03-19","cited_by_count":7,"area":null},{"id":"2407.16945","title":"Affective Behaviour Analysis via Progressive Learning","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2408.02164","title":"Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency","created":"2024-08-04","cited_by_count":7,"area":null},{"id":"2107.03143","title":"Action Units Recognition Using Improved Pairwise Deep Architecture","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2107.03891","title":"Technical Report for Valence-Arousal Estimation in ABAW2 Challenge","created":"2021-07-08","cited_by_count":6,"area":null},{"id":"2109.08061","title":"Invertible Frowns: Video-to-Video Facial Emotion Translation","created":"2021-09-16","cited_by_count":6,"area":null},{"id":"2303.09145","title":"Facial Affective Behavior Analysis Method for 5th ABAW Competition","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2303.09158","title":"Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challenge","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2304.07958","title":"Recursive Joint Attention for Audio-Visual Fusion in Regression based Emotion Recognition","created":"2023-04-17","cited_by_count":6,"area":null},{"id":"2403.11440","title":"Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2403.11757","title":"Efficient Feature Extraction and Late Fusion Strategy for Audiovisual Emotional Mimicry Intensity Estimation","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2403.11879","title":"Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Prediction","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2404.14975","title":"CAGE: Circumplex Affect Guided Expression Inference","created":"2024-04-23","cited_by_count":6,"area":null},{"id":"2407.13184","title":"HSEmotion Team at the 7th ABAW Challenge: Multi-Task Learning and Compound Facial Expression Recognition","created":"2024-07-18","cited_by_count":6,"area":null},{"id":"2408.16907","title":"Ig3D: Integrating 3D Face Representations in Facial Expression Inference","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2410.03848","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2503.09929","title":"Emotion Recognition with CLIP and Sequential Learning","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2107.05160","title":"Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2203.12899","title":"Facial Expression Classification using Fusion of Deep Neural Network in Video for the 3rd ABAW3 Competition","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2207.09012","title":"SS-MFAR : Semi-supervised Multi-task Facial Affect Recognition","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2303.08545","title":"Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2303.09164","title":"Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2303.10536","title":"TempT: Temporal consistency for Test-time adaptation","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2403.12425","title":"Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation","created":"2024-03-19","cited_by_count":5,"area":null},{"id":"2504.11460","title":"Semantic Matters: Multimodal Features for Affective Analysis","created":"2025-03-16","cited_by_count":5,"area":null},{"id":"2107.03009","title":"Multi-modal Affect Analysis using standardized data within subjects in the Wild","created":"2021-07-07","cited_by_count":4,"area":null},{"id":"2203.12428","title":"An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2203.14466","title":"Multi-model Ensemble Learning Method for Human Expression Recognition","created":"2022-03-28","cited_by_count":4,"area":null},{"id":"2203.14694","title":"Facial Action Unit Recognition Based on Transfer Learning","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2207.01113","title":"Are 3D Face Shapes Expressive Enough for Recognising Continuous Emotions and Action Unit Intensities?","created":"2022-07-03","cited_by_count":4,"area":null},{"id":"2303.08617","title":"Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognition","created":"2023-03-15","cited_by_count":4,"area":null}],"next_cursor":"100"}