{"total":30,"rows":[{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2204.13861","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","created":"2022-04-29","cited_by_count":58,"area":null},{"id":"2407.00224","title":"Multimodal Prototyping for cancer survival prediction","created":"2024-06-28","cited_by_count":47,"area":null},{"id":"2310.11374","title":"DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations","created":"2023-10-17","cited_by_count":30,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"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":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2410.18882","title":"A Survey of Multimodal Sarcasm Detection","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2504.16427","title":"Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark","created":"2025-04-23","cited_by_count":9,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2403.11311","title":"Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding","created":"2024-03-17","cited_by_count":7,"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":"2305.16406","title":"Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2310.09821","title":"LICO: Explainable Models with Language-Image Consistency","created":"2023-10-15","cited_by_count":5,"area":null},{"id":"2510.23727","title":"MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2209.14272","title":"Towards Multimodal Prediction of Spontaneous Humour: A Novel Dataset and First Results","created":"2022-09-28","cited_by_count":4,"area":null},{"id":"2408.07694","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2509.04605","title":"Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2406.07753","title":"The MuSe 2024 Multimodal Sentiment Analysis Challenge: Social Perception and Humor Recognition","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2408.02595","title":"Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2305.13583","title":"Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2405.08454","title":"Alignment Helps Make the Most of Multimodal Data","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2406.12304","title":"COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2409.01037","title":"NYK-MS: A Well-annotated Multi-modal Metaphor and Sarcasm Understanding Benchmark on Cartoon-Caption Dataset","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2608.04234","title":"Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.26879","title":"Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.30470","title":"Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.17707","title":"Focus on What You Need: Global-to-Local Dynamic Attention for Multimodal Sarcasm Detection","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}