{"total":74,"rows":[{"id":"2404.01292","title":"Measuring Style Similarity in Diffusion Models","created":"2024-04-01","cited_by_count":109,"area":"diffusion"},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2206.11404","title":"The ArtBench Dataset: Benchmarking Generative Models with Artworks","created":"2022-06-22","cited_by_count":64,"area":null},{"id":"2102.09109","title":"Understanding and Creating Art with AI: Review and Outlook","created":"2021-02-18","cited_by_count":60,"area":null},{"id":"2202.01747","title":"The Met Dataset: Instance-level Recognition for Artworks","created":"2022-02-03","cited_by_count":40,"area":null},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2305.03701","title":"LMEye: An Interactive Perception Network for Large Language Models","created":"2023-05-05","cited_by_count":27,"area":"mllm"},{"id":"2306.03932","title":"Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!","created":"2023-06-06","cited_by_count":19,"area":"mllm"},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2304.10278","title":"Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis","created":"2023-04-20","cited_by_count":18,"area":"diffusion"},{"id":"2408.01415","title":"Conditional LoRA Parameter Generation","created":"2024-08-02","cited_by_count":16,"area":null},{"id":"2102.03942","title":"Iconographic Image Captioning for Artworks","created":"2021-02-07","cited_by_count":15,"area":null},{"id":"2602.05576","title":"OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph","created":"2026-02-05","cited_by_count":13,"area":null},{"id":"2203.05321","title":"StyleBabel: Artistic Style Tagging and Captioning","created":"2022-03-10","cited_by_count":12,"area":null},{"id":"2105.11852","title":"GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graph","created":"2021-05-25","cited_by_count":11,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2302.09795","title":"Simple Disentanglement of Style and Content in Visual Representations","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2308.15284","title":"ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques","created":"2023-08-29","cited_by_count":10,"area":null},{"id":"2105.08190","title":"Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2211.01226","title":"DEArt: Dataset of European Art","created":"2022-11-02","cited_by_count":9,"area":null},{"id":"2309.02401","title":"Prototype-based Dataset Comparison","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2505.06020","title":"ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding","created":"2025-05-09","cited_by_count":7,"area":"rag"},{"id":"2510.12750","title":"VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage","created":"2025-10-14","cited_by_count":7,"area":"mllm"},{"id":"2204.14034","title":"A Challenging Benchmark of Anime Style Recognition","created":"2022-04-29","cited_by_count":6,"area":null},{"id":"2207.02976","title":"Semi-supervised Human Pose Estimation in Art-historical Images","created":"2022-07-06","cited_by_count":6,"area":null},{"id":"2211.10567","title":"CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering","created":"2022-11-19","cited_by_count":6,"area":null},{"id":"2301.05124","title":"Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History","created":"2023-01-12","cited_by_count":6,"area":null},{"id":"2311.11888","title":"SniffyArt: The Dataset of Smelling Persons","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2406.00423","title":"Multimodal Metadata Assignment for Cultural Heritage Artifacts","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2507.21917","title":"ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval","created":"2025-07-29","cited_by_count":5,"area":"lr"},{"id":"2106.06234","title":"A deep learning approach to clustering visual arts","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2308.10562","title":"Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2409.10921","title":"KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph","created":"2024-09-17","cited_by_count":4,"area":"mllm"},{"id":"2208.10758","title":"Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks","created":"2022-08-23","cited_by_count":3,"area":null},{"id":"2504.12805","title":"Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation","created":"2025-04-17","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":"2602.09839","title":"ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.27723","title":"TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution","created":"2026-03-29","cited_by_count":3,"area":null},{"id":"2605.11919","title":"STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2410.12369","title":"Context-Infused Visual Grounding for Art","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2507.08384","title":"Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2605.11468","title":"CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.17359","title":"Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2608.24795","title":"LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2105.15028","title":"Integrating Contextual Knowledge to Visual Features for Fine Art Classification","created":"2021-05-31","cited_by_count":1,"area":null},{"id":"2112.08219","title":"Quantitative analysis of visual representation of sign elements in COVID-19 context","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2304.07999","title":"Everyone Can Be Picasso? A Computational Framework into the Myth of Human versus AI Painting","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2507.09242","title":"PPJudge: Towards Human-Aligned Assessment of Artistic Painting Process","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2603.10814","title":"HanMoVLM: Large Vision-Language Models for Professional Artistic Painting Evaluation","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2604.19689","title":"A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding","created":"2026-04-21","cited_by_count":1,"area":"agents"},{"id":"2606.32016","title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.16321","title":"Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.00623","title":"Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2212.06868","title":"Deep Image Style Transfer from Freeform Text","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2403.07578","title":"AACP: Aesthetics assessment of children's paintings based on self-supervised learning","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2511.13378","title":"Moving Pictures of Thought: Extracting Visual Knowledge in Charles S. Peirce's Manuscripts with Vision-Language Models","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.12503","title":"KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs","created":"2025-12-14","cited_by_count":0,"area":"mllm"},{"id":"2601.21453","title":"LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11349","title":"ArtContext: Contextualizing Artworks with Open-Access Art History Articles and Wikidata Knowledge through a LoRA-Tuned CLIP Model","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.19133","title":"A Dataset for Named Entity Recognition and Relation Extraction from Art-historical Image Descriptions","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.02557","title":"Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.04071","title":"Detecting Media Clones in Cultural Repositories Using a Positive Unlabeled Learning Approach","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.08641","title":"On Semiotic-Grounded Interpretive Evaluation of Generative Art","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.15755","title":"Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language Models","created":"2026-05-15","cited_by_count":0,"area":"lr"},{"id":"2606.09648","title":"ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.09855","title":"MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.27947","title":"Understanding How MLLMs Describe Artworks Using Token Activation Maps","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.28644","title":"Seeing Differently: Modeling Interpretive Perspectives in Computational Creativity using a Four-World Framework","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.10706","title":"MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.13974","title":"ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.28339","title":"Abstract4D: A Large-Scale Dataset and Framework for Understanding the Visual Language of Abstract Art","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.33431","title":"MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2610.02881","title":"Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}