{"total":109,"rows":[{"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":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60,"area":null},{"id":"2308.13382","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","created":"2023-08-25","cited_by_count":44,"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":"2208.10335","title":"Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-19","cited_by_count":41,"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":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33,"area":null},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","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":"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":"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":"2507.23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention","created":"2025-07-30","cited_by_count":28,"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":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25,"area":null},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2507.15765","title":"Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization","created":"2025-07-21","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":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","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":"2305.03343","title":"LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition","created":"2023-05-05","cited_by_count":15,"area":null},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","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":"2301.00985","title":"DFME: A New Benchmark for Dynamic Facial Micro-expression Recognition","created":"2023-01-03","cited_by_count":13,"area":null},{"id":"2409.07388","title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2307.13463","title":"Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2504.07198","title":"Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2406.11253","title":"Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2409.06154","title":"Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2305.07665","title":"A Comprehensive Survey on Affective Computing; Challenges, Trends, Applications, and Future Directions","created":"2023-05-08","cited_by_count":7,"area":null},{"id":"2504.17224","title":"Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2206.07593","title":"HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2407.15590","title":"All rivers run into the sea: Unified Modality Brain-like Emotional Central Mechanism","created":"2024-07-22","cited_by_count":5,"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":"2505.02331","title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2511.15085","title":"TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2601.16449","title":"Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding","created":"2026-01-23","cited_by_count":5,"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":"2405.18769","title":"OUS: Scene-Guided Dynamic Facial Expression Recognition","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2408.02421","title":"FE-Adapter: Adapting Image-based Emotion Classifiers to Videos","created":"2024-08-05","cited_by_count":4,"area":null},{"id":"2502.16129","title":"Robust Dynamic Facial Expression Recognition","created":"2025-02-22","cited_by_count":4,"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":"2505.17090","title":"EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2303.10033","title":"Multi-modal Expression Recognition with Ensemble Method","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2404.17100","title":"Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2406.16473","title":"D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2409.08598","title":"Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2412.18748","title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2507.07678","title":"Action Unit Enhance Dynamic Facial Expression Recognition","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2111.15361","title":"Seeking Salient Facial Regions for Cross-Database Micro-Expression Recognition","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2303.06904","title":"Contextually-rich human affect perception using multimodal scene information","created":"2023-03-13","cited_by_count":2,"area":null},{"id":"2303.09210","title":"A Dual Branch Network for Emotional Reaction Intensity Estimation","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2312.00856","title":"QAFE-Net: Quality Assessment of Facial Expressions with Landmark Heatmaps","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2504.10351","title":"Multimodal Representation Learning Techniques for Comprehensive Facial State Analysis","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2508.06902","title":"eMotions: A Large-Scale Dataset and Audio-Visual Fusion Network for Emotion Analysis in Short-form Videos","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2404.08433","title":"MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2407.16406","title":"Hi-EF: Benchmarking Emotion Forecasting in Human-interaction","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2411.05879","title":"Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2412.00277","title":"Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2504.09530","title":"Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders","created":"2025-04-13","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":"2507.00586","title":"Context-Aware Academic Emotion Dataset and Benchmark","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2511.11406","title":"Robust Low-Rank Sparse Framework for Video-Based Affective Computing","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2511.22188","title":"ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.16485","title":"Smile on the Face, Sadness in the Eyes: Bridging the Emotion Gap with a Multimodal Dataset of Eye and Facial Behaviors","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2602.05496","title":"XEmoGPT: An Explainable Multimodal Emotion Recognition Framework with Cue-Level Perception and Reasoning","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.04128","title":"Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.29697","title":"FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.08847","title":"EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2209.08445","title":"SDFE-LV: A Large-Scale, Multi-Source, and Unconstrained Database for Spotting Dynamic Facial Expressions in Long Videos","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2304.12470","title":"Vision-based Estimation of Fatigue and Engagement in Cognitive Training Sessions","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2405.16451","title":"From Macro to Micro: Boosting micro-expression recognition via pre-training on macro-expression videos","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2407.09913","title":"Emotion Detection through Body Gesture and Face","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2408.10500","title":"SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2411.08472","title":"A survey on Graph Deep Representation Learning for Facial Expression Recognition","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2502.21004","title":"Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2504.21248","title":"Multi-modal Transfer Learning for Dynamic Facial Emotion Recognition in the Wild","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.05043","title":"xTrace: A Facial Expressive Behaviour Analysis Tool for Continuous Affect Recognition","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2507.09248","title":"AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2507.10755","title":"Auditing Facial Emotion Recognition Datasets for Posed Expressions and Racial Bias","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.11892","title":"From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2507.21015","title":"Learning Transferable Facial Emotion Representations from Large-Scale Semantically Rich Captions","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.04344","title":"MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.15221","title":"WELD: The First Naturalistic Long-Period Small-Team Workplace Emotion Dataset for Ubiquitous Affective Computing","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.10958","title":"Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.09276","title":"Dynamic Facial Expressions Analysis Based Parkinson's Disease Auxiliary Diagnosis","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.00311","title":"ReMA: A Training-Free Plug-and-Play Mixing Augmentation for Video Behavior Recognition","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2603.21387","title":"Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.02397","title":"Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.03050","title":"MECO: A Multimodal Dataset for Emotion and Cognitive Understanding in Older Adults","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.10541","title":"Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.12255","title":"ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.12777","title":"Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.15823","title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","created":"2026-04-17","cited_by_count":0,"area":null}],"next_cursor":"100"}