{"total":33,"rows":[{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2107.04313","title":"Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset","created":"2021-07-09","cited_by_count":13,"area":null},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2209.06416","title":"ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining","created":"2022-09-14","cited_by_count":12,"area":null},{"id":"2109.00602","title":"Point-of-Interest Type Prediction using Text and Images","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2109.05281","title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","created":"2021-09-11","cited_by_count":9,"area":null},{"id":"2306.04125","title":"Multimodal Fusion Interactions: A Study of Human and Automatic Quantification","created":"2023-06-07","cited_by_count":9,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2503.13834","title":"See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias","created":"2025-03-18","cited_by_count":9,"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":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","cited_by_count":8,"area":null},{"id":"2401.00424","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","created":"2023-12-31","cited_by_count":7,"area":null},{"id":"2508.16122","title":"Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2302.13311","title":"Understanding Social Media Cross-Modality Discourse in Linguistic Space","created":"2023-02-26","cited_by_count":6,"area":null},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2507.22934","title":"Deep Learning Approaches for Multimodal Intent Recognition: A Survey","created":"2025-07-24","cited_by_count":6,"area":null},{"id":"2304.01961","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2310.12172","title":"Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2603.14525","title":"MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2309.07794","title":"Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2409.09504","title":"Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2202.07427","title":"On the Complementarity of Images and Text for the Expression of Emotions in Social Media","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2402.03607","title":"Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2102.04568","title":"Tracking e-cigarette warning label compliance on Instagram with deep learning","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2109.00693","title":"AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification","created":"2021-09-02","cited_by_count":0,"area":null},{"id":"2511.23287","title":"Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla","created":"2025-11-28","cited_by_count":0,"area":null}],"next_cursor":null}