{"total":22,"rows":[{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"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":"2106.15318","title":"Analysing Affective Behavior in the second ABAW2 Competition","created":"2021-06-14","cited_by_count":163,"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":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17,"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":"2309.06745","title":"VEATIC: Video-based Emotion and Affect Tracking in Context Dataset","created":"2023-09-13","cited_by_count":12,"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":"2207.05577","title":"Learning from Label Relationships in Human Affect","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2212.06972","title":"Disentangling Prosody Representations with Unsupervised Speech Reconstruction","created":"2022-12-14","cited_by_count":8,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"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":"2206.07593","title":"HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2105.08146","title":"MUSER: MUltimodal Stress Detection using Emotion Recognition as an Auxiliary Task","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2205.00129","title":"Gaze-enhanced Crossmodal Embeddings for Emotion Recognition","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2208.07221","title":"CIAO! A Contrastive Adaptation Mechanism for Non-Universal Facial Expression Recognition","created":"2022-08-10","cited_by_count":4,"area":null},{"id":"2403.04798","title":"JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2407.06115","title":"Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2102.09150","title":"An Enhanced Adversarial Network with Combined Latent Features for Spatio-Temporal Facial Affect Estimation in the Wild","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2103.03700","title":"Analyzing the Influence of Dataset Composition for Emotion Recognition","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2406.06401","title":"INTERSPEECH 2009 Emotion Challenge Revisited: Benchmarking 15 Years of Progress in Speech Emotion Recognition","created":"2024-06-10","cited_by_count":0,"area":null}],"next_cursor":null}