{"total":112,"rows":[{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256,"area":null},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186,"area":null},{"id":"2204.11423","title":"Trusted Multi-View Classification with Dynamic Evidential Fusion","created":"2022-04-25","cited_by_count":168,"area":null},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2403.07300","title":"CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning","created":"2024-03-12","cited_by_count":108,"area":null},{"id":"2102.02051","title":"Trusted Multi-View Classification","created":"2021-02-03","cited_by_count":94,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82,"area":null},{"id":"2110.00413","title":"Detecting Harmful Memes and Their Targets","created":"2021-09-24","cited_by_count":78,"area":null},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2210.05916","title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features","created":"2022-10-12","cited_by_count":56,"area":null},{"id":"2105.09284","title":"SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images","created":"2021-04-25","cited_by_count":50,"area":null},{"id":"2103.12541","title":"A Survey on Multimodal Disinformation Detection","created":"2021-03-13","cited_by_count":47,"area":null},{"id":"2109.08013","title":"Detecting Propaganda Techniques in Memes","created":"2021-08-07","cited_by_count":44,"area":null},{"id":"2110.10949","title":"Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection","created":"2021-10-21","cited_by_count":37,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34,"area":null},{"id":"2304.06306","title":"Efficient Multimodal Fusion via Interactive Prompting","created":"2023-04-13","cited_by_count":32,"area":null},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2203.07376","title":"HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing","created":"2022-03-14","cited_by_count":26,"area":null},{"id":"2411.05383","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","created":"2024-11-08","cited_by_count":24,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2205.05738","title":"DISARM: Detecting the Victims Targeted by Harmful Memes","created":"2022-05-11","cited_by_count":20,"area":null},{"id":"2310.11748","title":"BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification","created":"2023-10-18","cited_by_count":18,"area":null},{"id":"2401.13298","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2406.04802","title":"Predictive Dynamic Fusion","created":"2024-06-07","cited_by_count":17,"area":null},{"id":"2112.03562","title":"CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification","created":"2021-12-07","cited_by_count":16,"area":null},{"id":"2301.11219","title":"Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?","created":"2023-01-26","cited_by_count":14,"area":null},{"id":"2305.09299","title":"UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning","created":"2023-05-16","cited_by_count":13,"area":null},{"id":"2105.04047","title":"Analyzing Online Political Advertisements","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2205.00302","title":"SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities","created":"2022-04-30","cited_by_count":11,"area":null},{"id":"2305.15913","title":"MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2412.12164","title":"GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection","created":"2024-12-11","cited_by_count":11,"area":null},{"id":"2104.03435","title":"Multimodal Fusion Refiner Networks","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2108.08920","title":"Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach","created":"2021-08-19","cited_by_count":9,"area":null},{"id":"2403.14652","title":"MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation","created":"2024-02-24","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":"2106.05903","title":"Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2202.06076","title":"Indication as Prior Knowledge for Multimodal Disease Classification in Chest Radiographs with Transformers","created":"2022-02-12","cited_by_count":8,"area":null},{"id":"2411.12174","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","created":"2024-11-19","cited_by_count":8,"area":null},{"id":"2403.10829","title":"Deciphering Hate: Identifying Hateful Memes and Their Targets","created":"2024-03-16","cited_by_count":7,"area":null},{"id":"2409.11624","title":"Multimodal Generalized Category Discovery","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2109.01229","title":"Multimodal Conditionality for Natural Language Generation","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2401.06194","title":"CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classification","created":"2024-01-11","cited_by_count":6,"area":null},{"id":"2112.12792","title":"Understanding and Measuring Robustness of Multimodal Learning","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2203.03441","title":"Multi-Modal Attribute Extraction for E-Commerce","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2302.07315","title":"A dataset for Audio-Visual Sound Event Detection in Movies","created":"2023-02-14","cited_by_count":5,"area":null},{"id":"2310.06383","title":"What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?","created":"2023-10-10","cited_by_count":5,"area":null},{"id":"2403.10568","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2406.03916","title":"ArMeme: Propagandistic Content in Arabic Memes","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2407.14058","title":"Towards the Causal Complete Cause of Multi-Modal Representation Learning","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2602.19605","title":"CLCR: Cross-Level Semantic Collaborative Representation for Multimodal Learning","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2402.09036","title":"Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2408.07445","title":"Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2107.13054","title":"Exceeding the Limits of Visual-Linguistic Multi-Task Learning","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2305.18599","title":"Improving Generalization for Multimodal Fake News Detection","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2310.08032","title":"Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning","created":"2023-10-12","cited_by_count":3,"area":null},{"id":"2403.12481","title":"TT-BLIP: Enhancing Fake News Detection Using BLIP and Tri-Transformer","created":"2024-03-19","cited_by_count":3,"area":null},{"id":"2109.04422","title":"TxT: Crossmodal End-to-End Learning with Transformers","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2209.14667","title":"Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2309.03064","title":"A Multimodal Analysis of Influencer Content on Twitter","created":"2023-09-06","cited_by_count":2,"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":"2407.16243","title":"Chameleon: Images Are What You Need For Multimodal Learning Robust To Missing Modalities","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2409.17777","title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2501.17823","title":"Robust Multimodal Learning via Cross-Modal Proxy Tokens","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2602.01101","title":"Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2105.13132","title":"Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2109.03571","title":"TrollsWithOpinion: A Dataset for Predicting Domain-specific Opinion Manipulation in Troll Memes","created":"2021-09-08","cited_by_count":1,"area":null},{"id":"2110.06486","title":"Understanding of Emotion Perception from Art","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2112.08470","title":"Insta-VAX: A Multimodal Benchmark for Anti-Vaccine and Misinformation Posts Detection on Social Media","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2112.11710","title":"Fusion of medical imaging and electronic health records with attention and multi-head machanisms","created":"2021-12-22","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":"2301.00503","title":"A Concept Knowledge Graph for User Next Intent Prediction at Alipay","created":"2023-01-02","cited_by_count":1,"area":null},{"id":"2306.14182","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2310.05193","title":"Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2401.14856","title":"Memory-Inspired Temporal Prompt Interaction for Text-Image Classification","created":"2024-01-26","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":"2402.14579","title":"Text Role Classification in Scientific Charts Using Multimodal Transformers","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2411.07527","title":"Prompt-enhanced Network for Hateful Meme Classification","created":"2024-11-12","cited_by_count":1,"area":null},{"id":"2412.13794","title":"MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2506.07801","title":"MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2508.11197","title":"E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2601.04567","title":"All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.18231","title":"Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2605.14380","title":"VISHC at PsyDefDetect: Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.22016","title":"EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2107.09909","title":"DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework","created":"2021-07-21","cited_by_count":0,"area":null},{"id":"2112.09253","title":"Logically at Factify 2022: Multimodal Fact Verification","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2202.04266","title":"MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis","created":"2022-02-09","cited_by_count":0,"area":null},{"id":"2206.07190","title":"Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2302.09327","title":"Transformadores: Fundamentos teoricos y Aplicaciones","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2306.06476","title":"Modality Influence in Multimodal Machine Learning","created":"2023-06-10","cited_by_count":0,"area":null},{"id":"2312.03734","title":"Conditional Prompt Tuning for Multimodal Fusion","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2401.04354","title":"Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition","created":"2024-01-09","cited_by_count":0,"area":null},{"id":"2406.06048","title":"Robust Latent Representation Tuning for Image-text Classification","created":"2024-06-10","cited_by_count":0,"area":null}],"next_cursor":"100"}