{"total":117,"rows":[{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"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":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98,"area":null},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83,"area":null},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"area":null},{"id":"2308.07686","title":"Boosting Multi-modal Model Performance with Adaptive Gradient Modulation","created":"2023-08-15","cited_by_count":73,"area":null},{"id":"2310.19795","title":"SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization","created":"2023-10-30","cited_by_count":48,"area":null},{"id":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"area":null},{"id":"2107.13669","title":"Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis","created":"2021-07-28","cited_by_count":45,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"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":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2105.09984","title":"Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations","created":"2021-05-20","cited_by_count":33,"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":"2502.16282","title":"Understanding the Emergence of Multimodal Representation Alignment","created":"2025-02-22","cited_by_count":31,"area":null},{"id":"2306.17799","title":"A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition","created":"2023-06-16","cited_by_count":29,"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":"2205.01818","title":"i-Code: An Integrative and Composable Multimodal Learning Framework","created":"2022-05-03","cited_by_count":24,"area":null},{"id":"2207.05691","title":"The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress","created":"2022-06-23","cited_by_count":23,"area":null},{"id":"2101.06053","title":"The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements","created":"2021-01-15","cited_by_count":22,"area":null},{"id":"2210.13513","title":"ExPUNations: Augmenting Puns with Keywords and Explanations","created":"2022-10-24","cited_by_count":21,"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":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2406.08068","title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey","created":"2024-06-12","cited_by_count":16,"area":null},{"id":"2407.17152","title":"XMeCap: Meme Caption Generation with Sub-Image Adaptability","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2407.04105","title":"Can Pre-trained Language Models Understand Chinese Humor?","created":"2024-07-04","cited_by_count":13,"area":null},{"id":"2305.03369","title":"The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation","created":"2023-05-05","cited_by_count":12,"area":null},{"id":"2110.12765","title":"\"So You Think You're Funny?\": Rating the Humour Quotient in Standup Comedy","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2403.05025","title":"Debiased Multimodal Understanding for Human Language Sequences","created":"2024-03-08","cited_by_count":10,"area":null},{"id":"2209.11949","title":"Hybrid Multimodal Fusion for Humor Detection","created":"2022-09-24","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":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","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":"2505.18903","title":"StandUp4AI: A New Multilingual Dataset for Humor Detection in Stand-up Comedy Videos","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2109.05522","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","created":"2021-09-12","cited_by_count":8,"area":null},{"id":"2502.15919","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2108.01260","title":"M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversations","created":"2021-08-03","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2509.25270","title":"InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions","created":"2025-09-28","cited_by_count":7,"area":null},{"id":"2511.21331","title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","created":"2025-11-26","cited_by_count":7,"area":null},{"id":"2303.15430","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models","created":"2023-03-27","cited_by_count":6,"area":null},{"id":"2402.01759","title":"Systematic Literature Review: Computational Approaches for Humour Style Classification","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2507.13335","title":"Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2510.00567","title":"Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.04899","title":"Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding","created":"2025-10-06","cited_by_count":6,"area":null},{"id":"2107.08356","title":"DeHumor: Visual Analytics for Decomposing Humor","created":"2021-07-18","cited_by_count":5,"area":null},{"id":"2210.13522","title":"Context-Situated Pun Generation","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2506.21514","title":"G$^{2}$D: Boosting Multimodal Learning with Gradient-Guided Distillation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2510.04417","title":"Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2205.00001","title":"Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness","created":"2022-04-14","cited_by_count":4,"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":"2306.16413","title":"MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2401.16119","title":"Triple Disentangled Representation Learning for Multimodal Affective Analysis","created":"2024-01-29","cited_by_count":4,"area":null},{"id":"2402.09055","title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","created":"2024-02-14","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":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2206.13969","title":"MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2211.16509","title":"Multimodal Learning for Multi-Omics: A Survey","created":"2022-11-29","cited_by_count":3,"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":"2406.12754","title":"Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba","created":"2024-06-18","cited_by_count":3,"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":"2602.06423","title":"On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2305.12311","title":"i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2405.04671","title":"Interpretable Tensor Fusion","created":"2024-05-07","cited_by_count":2,"area":null},{"id":"2412.12761","title":"Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2504.09049","title":"From Punchlines to Predictions: A Metric to Assess LLM Performance in Identifying Humor in Stand-Up Comedy","created":"2025-04-12","cited_by_count":2,"area":null},{"id":"2509.21584","title":"IndiSeek learns information-guided disentangled representations","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.21805","title":"Towards Minimal Causal Representations for Human Multimodal Language Understanding","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.24919","title":"Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2602.14983","title":"Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2605.04097","title":"CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2605.25409","title":"MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2108.09934","title":"Modeling Dynamics of Facial Behavior for Mental Health Assessment","created":"2021-08-23","cited_by_count":1,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2209.02066","title":"Trust in Language Grounding: a new AI challenge for human-robot teams","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2409.00143","title":"Invariant Representation Guided Multimodal Sentiment Decoding with Sequential Variation Regularization","created":"2024-08-30","cited_by_count":1,"area":null},{"id":"2505.16953","title":"ICYM2I: The illusion of multimodal informativeness under missingness","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2509.25773","title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2601.21670","title":"Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.04260","title":"Decoupled Hierarchical Distillation for Multimodal Emotion Recognition","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.02695","title":"Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.17759","title":"Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.18460","title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2607.16789","title":"MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning","created":"2026-07-18","cited_by_count":1,"area":null},{"id":"2106.00451","title":"Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis","created":"2021-05-28","cited_by_count":0,"area":null},{"id":"2304.11093","title":"Hi Sheldon! Creating Deep Personalized Characters from TV Shows","created":"2023-04-09","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":"2406.17667","title":"This Paper Had the Smartest Reviewers -- Flattery Detection Utilising an Audio-Textual Transformer-Based Approach","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2408.02568","title":"Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2411.02430","title":"Generative Emotion Cause Explanation in Multimodal Conversations","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2508.11180","title":"No Data Wasted: A Semi-supervised Generative Model for Incomplete Multi-view Data Integration with Missing Labels","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.04779","title":"Decoders Laugh as Loud as Encoders","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.18014","title":"ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.06686","title":"Balancing Multi-modal Sensor Learning via Multi-objective Optimization","created":"2025-11-10","cited_by_count":0,"area":null}],"next_cursor":"100"}