{"total":99,"rows":[{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"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":"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":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48,"area":null},{"id":"2206.02187","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","created":"2022-06-05","cited_by_count":47,"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":"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":"2303.11921","title":"Context De-confounded Emotion Recognition","created":"2023-03-21","cited_by_count":34,"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":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"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":"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":"2301.12149","title":"POSTER++: A simpler and stronger facial expression recognition network","created":"2023-01-28","cited_by_count":25,"area":null},{"id":"2403.05963","title":"Robust Emotion Recognition in Context Debiasing","created":"2024-03-09","cited_by_count":24,"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":"2111.04129","title":"Global-Local Attention for Emotion Recognition","created":"2021-11-07","cited_by_count":20,"area":null},{"id":"2502.05660","title":"Evaluating Vision-Language Models for Emotion Recognition","created":"2025-02-08","cited_by_count":19,"area":"lr"},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"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":"2508.09210","title":"MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models","created":"2025-08-11","cited_by_count":17,"area":"mllm"},{"id":"2404.07078","title":"VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning","created":"2024-04-10","cited_by_count":16,"area":"lr"},{"id":"2203.13032","title":"Multi-modal Emotion Estimation for in-the-wild Videos","created":"2022-03-24","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":"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":"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":"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":"2309.06745","title":"VEATIC: Video-based Emotion and Affect Tracking in Context Dataset","created":"2023-09-13","cited_by_count":12,"area":null},{"id":"2312.16778","title":"Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2407.11300","title":"Large Vision-Language Models as Emotion Recognizers in Context Awareness","created":"2024-07-16","cited_by_count":12,"area":"mllm"},{"id":"2107.12096","title":"Towards Unbiased Visual Emotion Recognition via Causal Intervention","created":"2021-07-26","cited_by_count":11,"area":null},{"id":"2407.04963","title":"Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training","created":"2024-07-06","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":"2405.08992","title":"Contextual Emotion Recognition using Large Vision Language Models","created":"2024-05-14","cited_by_count":9,"area":"mllm"},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8,"area":"lr"},{"id":"2305.03500","title":"High-Level Context Representation for Emotion Recognition in Images","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2202.10453","title":"Predicting emotion from music videos: exploring the relative contribution of visual and auditory information to affective responses","created":"2022-02-19","cited_by_count":6,"area":null},{"id":"2304.05634","title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2410.09865","title":"SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data","created":"2024-10-13","cited_by_count":6,"area":"synth"},{"id":"2212.07055","title":"Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition","created":"2022-12-14","cited_by_count":5,"area":null},{"id":"2309.07085","title":"Mitigating Group Bias in Federated Learning for Heterogeneous Devices","created":"2023-09-13","cited_by_count":5,"area":null},{"id":"2312.14626","title":"DSAP: Analyzing Bias Through Demographic Comparison of Datasets","created":"2023-12-22","cited_by_count":5,"area":null},{"id":"2404.17205","title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","created":"2024-04-26","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":"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":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2204.06562","title":"Estimating Structural Disparities for Face Models","created":"2022-04-13","cited_by_count":4,"area":null},{"id":"2310.04043","title":"In the Blink of an Eye: Event-based Emotion Recognition","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2404.10904","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","created":"2024-04-16","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":"2210.10130","title":"PERI: Part Aware Emotion Recognition In The Wild","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2306.08657","title":"EMERSK -- Explainable Multimodal Emotion Recognition with Situational Knowledge","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2310.19995","title":"Emotional Theory of Mind: Bridging Fast Visual Processing with Slow Linguistic Reasoning","created":"2023-10-30","cited_by_count":3,"area":"lr"},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2409.18877","title":"UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception","created":"2024-09-27","cited_by_count":3,"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":"2307.02773","title":"SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2405.00942","title":"Teaching Human Behavior Improves Content Understanding Abilities Of LLMs","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2504.09221","title":"CMCRD: Cross-Modal Contrastive Representation Distillation for Emotion Recognition","created":"2025-04-12","cited_by_count":2,"area":null},{"id":"2505.14270","title":"RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2507.14608","title":"Exp-Graph: How Connections Learn Facial Attributes in Graph-based Expression Recognition","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2508.06093","title":"E-React: Towards Emotionally Controlled Synthesis of Human Reactions","created":"2025-08-08","cited_by_count":2,"area":"diffusion"},{"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":"2208.02991","title":"Analyzing the Impact of Shape & Context on the Face Recognition Performance of Deep Networks","created":"2022-08-05","cited_by_count":1,"area":null},{"id":"2308.00228","title":"Using Scene and Semantic Features for Multi-modal Emotion Recognition","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2311.00923","title":"A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2311.03551","title":"Context Unlocks Emotions: Text-based Emotion Classification Dataset Auditing with Large Language Models","created":"2023-11-06","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":"2505.24342","title":"VAEER: Visual Attention-Inspired Emotion Elicitation Reasoning","created":"2025-05-30","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":"2603.02123","title":"Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy","created":"2026-03-02","cited_by_count":1,"area":"mllm"},{"id":"2608.10796","title":"E$^3$mo-Bench: A Scalable Benchmark for Multimodal Evoked and Expressed Emotion Understanding via Bayesian Pairwise Alignment","created":"2026-08-11","cited_by_count":1,"area":"mllm"},{"id":"2109.13016","title":"Semi-Supervised Adversarial Discriminative Domain Adaptation","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2110.01758","title":"Quantified Facial Expressiveness for Affective Behavior Analytics","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2110.04042","title":"Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition","created":"2021-10-08","cited_by_count":0,"area":null},{"id":"2111.02273","title":"Multi-Cue Adaptive Emotion Recognition Network","created":"2021-11-03","cited_by_count":0,"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":"2306.09372","title":"SAFER: Situation Aware Facial Emotion Recognition","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2306.13076","title":"A Comparison of Time-based Models for Multimodal Emotion Recognition","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2311.11980","title":"Leveraging Previous Facial Action Units Knowledge for Emotion Recognition on Faces","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2401.08221","title":"Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasets","created":"2024-01-16","cited_by_count":0,"area":null},{"id":"2409.02566","title":"How Do You Perceive My Face? Recognizing Facial Expressions in Multi-Modal Context by Modeling Mental Representations","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2504.21309","title":"An Evaluation of a Visual Question Answering Strategy for Zero-shot Facial Expression Recognition in Still Images","created":"2025-04-30","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":"2507.15878","title":"Salience Adjustment for Context-Based Emotion Recognition","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2507.19137","title":"Assessment of Personality Dimensions Across Situations in Dyadic Role-Play Scenarios","created":"2025-07-25","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":"2511.10958","title":"Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.00123","title":"Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models","created":"2026-01-27","cited_by_count":0,"area":"mllm"},{"id":"2604.26519","title":"GIFGuard: Proactive Forensics against Deepfakes in Facial GIFs via Spatiotemporal Watermarking","created":"2026-04-29","cited_by_count":0,"area":"safety"},{"id":"2605.04439","title":"A cross-modal network for facial expression recognition","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.03837","title":"Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.14096","title":"A New Multi-Domain Benchmark for Micro-Action Recognition and Detection","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.21657","title":"Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.22072","title":"A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.18109","title":"SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.36563","title":"AffectReveal: Event-Grounded Emotion Recognition Beyond Visual Appearances","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}