{"total":44,"rows":[{"id":"2303.11921","title":"Context De-confounded Emotion Recognition","created":"2023-03-21","cited_by_count":34,"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":"2403.05963","title":"Robust Emotion Recognition in Context Debiasing","created":"2024-03-09","cited_by_count":24,"area":null},{"id":"2201.05834","title":"Tailor Versatile Multi-modal Learning for Multi-label Emotion Recognition","created":"2022-01-15","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":"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":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","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":"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":"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":"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":"2102.03513","title":"Privacy-Preserving Video Classification with Convolutional Neural Networks","created":"2021-02-06","cited_by_count":10,"area":null},{"id":"2305.03500","title":"High-Level Context Representation for Emotion Recognition in Images","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2207.13064","title":"Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis","created":"2022-07-26","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":"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":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3,"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":"2309.13136","title":"Contextual Emotion Estimation from Image Captions","created":"2023-09-22","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":"2210.04935","title":"Deep Insights of Learning based Micro Expression Recognition: A Perspective on Promises, Challenges and Research Needs","created":"2022-10-10","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":"2307.02773","title":"SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images","created":"2023-07-06","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":"2111.15271","title":"Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2305.02760","title":"Multi-Modality Deep Network for JPEG Artifacts Reduction","created":"2023-05-04","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":"2311.03551","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":"2405.16701","title":"Detail-Enhanced Intra- and Inter-modal Interaction for Audio-Visual Emotion Recognition","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2501.07746","title":"A Heterogeneous Multimodal Graph Learning Framework for Recognizing User Emotions in Social Networks","created":"2025-01-13","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":"2110.01758","title":"Quantified Facial Expressiveness for Affective Behavior Analytics","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2312.07500","title":"Multi-Branch Network for Imagery Emotion Prediction","created":"2023-12-12","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":"2503.06405","title":"Heterogeneous bimodal attention fusion for speech emotion recognition","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2511.19785","title":"Gender Bias in Emotion Recognition by Large Language Models","created":"2025-11-24","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":"2607.25148","title":"Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.13255","title":"A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources","created":"2026-09-06","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}