UR-FUNNY: A Multimodal Language Dataset for Understanding Humor
Not on the map. Why?
Abstract (arXiv)
Humor is a unique and creative communicative behavior displayed during social interactions. It is produced in a multimodal manner, through the usage of words (text), gestures (vision) and prosodic cues (acoustic). Understanding humor from these three modalities falls within boundaries of multimodal language; a recent research trend in natural language processing that models natural language as it happens in face-to-face communication. Although humor detection is an established research area in NLP, in a multimodal context it is an understudied area. This paper presents a diverse multimodal dataset, called UR-FUNNY, to open the door to understanding multimodal language used in expressing humor. The dataset and accompanying studies, present a framework in multimodal humor detection for the natural language processing community. UR-FUNNY is publicly available for research.
Key facts. Cited by 132 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Apr 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 15; 2023: 18; 2024: 26; 2025: 30; 2026: 32.
132 papers.
Sort:
By area:
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 146
- 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
- 2022Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contestcited by 98
- 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Frameworkcited by 83
- 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 75
- 2023Boosting Multi-modal Model Performance with Adaptive Gradient Modulationcited by 73
- 2023SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalizationcited by 48
- 2024What to align in multimodal contrastive learning?cited by 47
- 2021Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysiscited by 45
- 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
- 2024Distilling an End-to-End Voice Assistant Without Instruction Training Datacited by 39
- 2021Multimodal Learning using Optimal Transport for Sarcasm and Humor Detectioncited by 37
38 more
- 2023FunQA: Towards Surprising Video Comprehensioncited by 35
- 2021Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversationscited by 33
- 2025EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Modelscited by 32
- 2022High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learningcited by 31
- 2025Understanding the Emergence of Multimodal Representation Alignmentcited by 31
- 2023A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognitioncited by 29
- 2023SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Modelscited by 28
- 2022i-Code: An Integrative and Composable Multimodal Learning Frameworkcited by 24
- 2022The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stresscited by 23
- 2021The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvementscited by 22
- 2022ExPUNations: Augmenting Puns with Keywords and Explanationscited by 21
- 2023Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applicationscited by 21
- 2023MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Expertscited by 21
- 2024Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Surveycited by 16
- 2024Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?cited by 14
- 2024XMeCap: Meme Caption Generation with Sub-Image Adaptabilitycited by 14
- 2024Can Pre-trained Language Models Understand Chinese Humor?cited by 13
- 2023The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisationcited by 12
- 2021"So You Think You're Funny?": Rating the Humour Quotient in Standup Comedycited by 11
- 2023Can Language Models Laugh at YouTube Short-form Videos?cited by 11
- 2024Debiased Multimodal Understanding for Human Language Sequencescited by 10
- 2022Hybrid Multimodal Fusion for Humor Detectioncited by 9
- 2023Multimodal Fusion Interactions: A Study of Human and Automatic Quantificationcited by 9
- 2024FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wildcited by 9
- 2024YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Modelscited by 9
- 2025Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmarkcited by 9
- 2025StandUp4AI: A New Multilingual Dataset for Humor Detection in Stand-up Comedy Videoscited by 9
- 2021TEASEL: A Transformer-Based Speech-Prefixed Language Modelcited by 8
- 2025Mind the Gap! Static and Interactive Evaluations of Large Audio Modelscited by 8
- 2026Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoningcited by 8
- 2021M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversationscited by 7
- 2024Creativity in AI: Progresses and Challengescited by 7
- 2025MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeXcited by 7
- 2025InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactionscited by 7
- 2025The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignmentcited by 7
- 2023TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Modelscited by 6
- 2024Systematic Literature Review: Computational Approaches for Humour Style Classificationcited by 6
- 2024HumorDB: Can AI understand graphical humor?cited by 6
50 most cited of 132 All 132 (JSON)
- 2026Reinforcement Learning with Comparative Evidence for Social Intelligence2 Oct 2026
- 2026SynCo: Learning Cross-Modal Synergy by Contrasting Interaction Residuals26 Sep 2026
- 2026Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis24 Sep 2026
- 2026MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions10 Sep 2026
- 2026Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion27 Aug 2026
- 2026CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery24 Aug 2026
- 2026Fusion Anything: A Generalized Multimodal Foundation Model16 Aug 2026
- 2026Conformal Fusion Under Missing Modalities7 Aug 2026
- 2026Reading Between the Frames of Multimodal Drivelology5 Aug 2026
- 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning18 Jul 2026
- 2026Information-Theoretic Decomposition for Multimodal Interaction Learning10 Jun 2026
- 2026MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model25 May 2026
38 more
- 2026SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning12 May 2026
- 2026MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method7 May 2026
- 2026Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts5 May 2026
- 2026Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models3 May 2026
- 2026When Jokes Cross the Line: Analyzing Regular Humor and Dark Humor in YouTube Shorts30 Apr 2026
- 2026CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness30 Apr 2026
- 2026Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective20 Apr 2026
- 2026Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor18 Mar 2026
- 2026Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data3 Mar 2026
- 2026CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion22 Feb 2026
- 2026Automatic Funny Scene Extraction from Long-form Cinematic Videos17 Feb 2026
- 2026Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations16 Feb 2026
- 2026OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization11 Feb 2026
- 2026On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation6 Feb 2026
- 2026Decoupled Hierarchical Distillation for Multimodal Emotion Recognition4 Feb 2026
- 2026Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning1 Feb 2026
- 2026Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion29 Jan 2026
- 2026GRCF: Two-Stage Groupwise Ranking and Calibration Framework for Multimodal Sentiment Analysis14 Jan 2026
- 2026Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?10 Jan 2026
- 2026A Vision for Multisensory Intelligence: Sensing, Science, and Synergy8 Jan 2026
- 2025OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition22 Dec 2025
- 2025The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment26 Nov 2025
- 2025Vulnerability-Aware Robust Multimodal Adversarial Training22 Nov 2025
- 2025Balancing Multi-modal Sensor Learning via Multi-objective Optimization10 Nov 2025
- 2025Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning28 Oct 2025
- 2025ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy20 Oct 2025
- 2025Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding6 Oct 2025
- 2025Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions6 Oct 2025
- 2025Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation1 Oct 2025
- 2025v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound30 Sep 2025
- 2025InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions28 Sep 2025
- 2025Towards Minimal Causal Representations for Human Multimodal Language Understanding26 Sep 2025
- 2025IndiSeek learns information-guided disentangled representations25 Sep 2025
- 2025Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics12 Sep 2025
- 2025Decoders Laugh as Loud as Encoders5 Sep 2025
- 2025Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding28 Aug 2025
- 2025No Data Wasted: A Semi-supervised Generative Model for Incomplete Multi-view Data Integration with Missing Labels15 Aug 2025
- 2025Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting4 Aug 2025
50 newest of 132 All 132 (JSON)
- 2025EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Modelscited by 32
- 2024YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Modelscited by 9
- 2025MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeXcited by 7
- 2024HumorDB: Can AI understand graphical humor?cited by 6
- 2025Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comicscited by 5
- 2025Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Promptingcited by 3
- 2023Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddingscited by 1
- 2026Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?cited by 0
- 2026Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Modelscited by 0
- 2026Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models3 May 2026
- 2026Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?10 Jan 2026
- 2025Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics12 Sep 2025
- 2025Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting4 Aug 2025
- 2025MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX27 Mar 2025
- 2025EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models6 Feb 2025
- 2024YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models20 Sep 2024
- 2024HumorDB: Can AI understand graphical humor?19 Jun 2024
- 2023Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings13 Nov 2023
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 146
- 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
- 2022Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contestcited by 98
- 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Frameworkcited by 83
- 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 75
- 2023Boosting Multi-modal Model Performance with Adaptive Gradient Modulationcited by 73
- 2023SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalizationcited by 48
- 2024What to align in multimodal contrastive learning?cited by 47
- 2021Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysiscited by 45
- 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
- 2024Distilling an End-to-End Voice Assistant Without Instruction Training Datacited by 39
- 2021Multimodal Learning using Optimal Transport for Sarcasm and Humor Detectioncited by 37
12 most cited of 117 All 117 (JSON)
- 2026SynCo: Learning Cross-Modal Synergy by Contrasting Interaction Residuals26 Sep 2026
- 2026Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis24 Sep 2026
- 2026MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions10 Sep 2026
- 2026Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion27 Aug 2026
- 2026CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery24 Aug 2026
- 2026Fusion Anything: A Generalized Multimodal Foundation Model16 Aug 2026
- 2026Conformal Fusion Under Missing Modalities7 Aug 2026
- 2026Reading Between the Frames of Multimodal Drivelology5 Aug 2026
- 2026MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning18 Jul 2026
- 2026Information-Theoretic Decomposition for Multimodal Interaction Learning10 Jun 2026
- 2026MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model25 May 2026
- 2026SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning12 May 2026
12 newest of 117 All 117 (JSON)