{"total":13,"rows":[{"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":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15,"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":"2105.04047","title":"Analyzing Online Political Advertisements","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11,"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":"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":"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":"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":"2209.03126","title":"DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention","created":"2022-09-07","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":"2109.00693","title":"AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification","created":"2021-09-02","cited_by_count":0,"area":null}],"next_cursor":null}