Cultural Heritage

Follow this topic Ask about this topic

Cultural heritage research applies AI to make collections and traditions easier to document, study, preserve, and share. Common approaches include computer vision and OCR for images and manuscripts, satellite change detection for archaeological sites, spectral imaging and 3D reconstruction for fragile objects, and multimodal models for search and interpretation. Knowledge graphs and retrieval-augmented generation connect answers to collection records, while expert annotation and human-in-the-loop systems help keep outputs grounded. Models can perform well on broad recognition tasks but often struggle with fine-grained cultural context, historical reasoning, authenticity, and evidence-based interpretation.

Latest papers

57 papers8 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

NRITYAM: Language Models Meet Art and Heritage of Dance
Jun 18, 2026Punit Kumar Singh, Niladri Ghosh, Advait Joshiınst +3Multilingual Language Model Evaluation LLM Evaluation
Shenzhen Technology University, 518118 Shenzhen, China · Indian Institute of Technology, India · Ramakrishna Mission Vivekananda Educational and Research Institute, India +4
Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing
Jun 11, 2026Anugrah Aidin Yotolembah, Novanto Yudistira, Gembong Edhi SetyawanRetrieval-Augmented Generation Image Captioning
Department of Informatics Engineering Faculty of Computer Science Brawijaya University Malang, Indonesia
TimeLens: On-Device Artifact Recognition with Retrieval-Augmented Question Answering for the Grand Egyptian Museum
Jun 11, 2026Rawan Hesham, Ali Ashraf, Amr Ahmed +3Real-Time Object Detection Cultural Heritage
Faculty of Computers and AI Capital University Cairo, Egypt
ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset
Jun 8, 2026Luciano Duarte, Olga Ovcharenko, Sebastian SchelterCultural Heritage Multimodal Dataset
BIFOLD & TU Berlin
ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China
Jun 8, 2026Yi Zhang, Bolei Ma, Yong Cao +3VLM Evaluation Visual Question Answering
1LMU Munich · 2FAU Erlangen-Nuremberg · 3Munich Center for Machine Learning +4
MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting
May 26, 2026Joonhyung BaeMultimodal Grounding Multimodal Classification
Korea Advanced Institute of Science and Technology (KAIST), South Korea · Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
A Dataset for the Recognition of Historical and Handwritten Music Scores in Western Notation
May 18, 2026Pau Torras, Jiří Mayer, Carles Badal +7Optical Music Recognition Cultural Heritage
Computer Vision Center, Barcelona, Spain · Institute of Formal and Applied Linguistics, Charles University, Prague, Czechia · Department of Arts and Musicology, Universitat Autònoma de Barcelona +2
Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models
May 17, 2026Yang Zhang, Nada Mimouni, Jean-Claude Moissinac +1KG Construction Cultural Heritage
Télécom Paris, Institut Polytechnique de Paris, France · Center for Studies and Research in Computer Science and Communication, CNAM · Center for Studies and Research in Computer Science and Communication, CNAM, France +1
WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI
May 16, 2026Jingjing Li, Zhi Liu, Xiyao Jin +2Human-AI Interaction Cultural Heritage
University of Tsukuba, Japan
On the Cultural Anachronism and Temporal Reasoning in Vision Language Models
May 14, 2026Mukul Ranjan, Prince Jha, Khushboo Kumari +1VLM Evaluation VLM Reasoning
MBZUAI, UAE · Inception, UAE
AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents
May 14, 2026Vicent Briva-Iglesias, María Ferre-FernándezLLM Prompting Cultural Heritage
SALIS, CTTS, ADAPT Centre · Dublin City University · Universidad de Almer´ıa
Probabilistic Dating of Historical Manuscripts via Evidential Deep Regression on Visual Script Features
May 7, 2026Ranjith ChodavarapuHistorical Document Analysis Evidential Deep Learning
Kent State University
WATCH: Wide-Area Archaeological Site Tracking for Change Detection
May 4, 2026Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali +7Geospatial Foundation Models Remote Sensing Change Detection
Microsoft AI for Good Research Lab · Iconem, Paris, France · Planet Labs PBC
ATLAS: Article Tracking, Linking, and Analysis of Swedish Encyclopedias
May 4, 2026Albin Andersson, Salam Jonasson, Fredrik Wastring +1KG Construction Historical Document Analysis
Lund University · Lund, Sweden
CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity
Apr 13, 2026Xuefeng Wei, Zhixuan Wang, Xuan Zhou +5VLM Evaluation VLM Reasoning
Nara Institute of Science and Technology · Liaoning Normal University
A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures
Apr 8, 2026Riccardo Pallotto, Pierluigi Feliciati, Tiberio UricchioDigital Cultural Heritage 3D Reconstruction
University of Macerata, Macerata, Italy · University of Pisa, Pisa, Italy
High-Fidelity Mural Restoration via a Unified Hybrid Mask-Aware Transformer
Apr 5, 2026Jincheng Jiang, Qianhao Han, Chi Zhang +1Image Restoration Image Inpainting
Northeastern University (Toronto Campus), Toronto, Canada · The Bishop Strachan School, Toronto, Canada
Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
Apr 2, 2026Naga Sowjanya Barla, Jacopo de BerardinisGrounded Text Generation Graph Retrieval-Augmented Generation
School of Computer Science and Informatics, University of Liverpool, Brownlow Hill, Liverpool, L69 7ZX, United Kingdom
Digital hybridity and relics in cultural heritage: using corpus linguistics to inform design in emerging technologies from AI to VR
Apr 1, 2026Emma McClaughlin, Glenn McGarry, Alan Chamberlain +2Corpus Linguistics Digital Cultural Heritage
School of English, University of Nottingham, Nottingham, UK. · School of Computer Science, University of Nottingham, Nottingham, UK. · Department of Modern Languages, Aberystwyth University, Aberystwyth, UK. +1
CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains
Mar 30, 2026Wenhan Wang, Zhixiang Zhou, Zhongtian Ma +8Cultural Heritage Cultural Knowledge in Language Models
Shanghai Innovation Institute · Shanghai AI Laboratory · Shaanxi Academy of Cultural Relics Conservation
Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion
Mar 24, 2026Shuangwu Qian, Xiaochan Yuan, Pengfei LiuImage Captioning Cultural Heritage
Sichuan Agricultural University
Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History Museums
Mar 11, 2026Yiyuan Wang, Andrew Johnston, Zoë Sadokierski +2Cultural Heritage Conversational Agents
School of Computer Science, University of Technology Sydney, Australia · School of Design, University of Technology Sydney, Australia · Australian Museum Research Institute, Australian Museum, Australia
Unmixing ATR-μFTIR spectroscopic images of cross-sections of historical oil paintings
Mar 3, 2026Shivam Pande, Nicolas Nadisic, Francisco Mederos-Henry +1Hyperspectral Unmixing Hyperspectral Imaging
Department of Telecommunications and Information Processing, Ghent University, Belgium. · Royal Institute for Cultural Heritage (KIK-IRPA), Belgium. · Engineering of Molecular Nanosystems (EMNS) Laboratory, Université Libre de Bruxelles (ULB), Belgium.
Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta
Mar 2, 2026Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang PhamImage Classification Fine-Grained Image Classification
College of Information and Communication Technology, Can Tho University · School of Graduate, Can Tho University
GeMi: A Graph-based, Multimodal Recommendation System for Narrative Scroll Paintings
Mar 1, 2026Haimonti Dutta, Pruthvi Moluguri, Jin Dai +1Recommender Systems Multimodal Recommendation
Department of Management Science and Systems, The State University of New York, Jacobs Management Center, Buffalo, 14260, NY, USA. · Institute for Artificial Intelligence and Data Science, The State University of New York, Lockwood Hall, Buffalo, 14260, NY, USA. · Department of Computer Science and Engineering, The State University of New York, Davis Hall, Buffalo, 14260, NY, USA. +1
Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning
Feb 23, 2026Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali +7Cultural Heritage Remote Sensing Image Understanding
Microsoft AI for Good Research Lab · Iconem · Planet Labs PBC
Computational Social Linguistics for Telugu Cultural Preservation: Novel Algorithms for Chandassu Metrical Pattern Recognition
Sep 23, 2025Boddu Sri Pavan, Boddu Swathi SreeCultural Heritage Computational Literary Studies
Independent Researcher · Department of Computer Science and Engineering RGUKT, Nuzvid

Jun 18, 2026J/K move · Enter open · S save

NRITYAM: Language Models Meet Art and Heritage of Dance

Punit Kumar Singh, Niladri Ghosh, Advait Joshiınst, Shailee Choudhary+2

Shenzhen Technology University, 518118 Shenzhen, China · Indian Institute of Technology, India · Ramakrishna Mission Vivekananda Educational and Research Institute, India+4

Multilingual Language Model Evaluation LLM Evaluation Cultural Knowledge in Language Models Cultural Heritage

Open paper AskPDF arXiv

Language models have become essential tools in shaping modern workflows. However, their global effectiveness hinges on a nuanced understanding of local socio-cultural contexts. To address this gap, we present NRITYAM, a comprehensive benchmark for evaluating the cultural comprehension capabilities of language models in the context of global dance traditions. NRITYAM comprises 9,260 carefully curated question-answer pairs spanning 12 languages, making it the largest dataset dedicated to evaluating cultural knowledge in dance. The dataset has been developed from the ground up through close collaboration with native dance artists and native speakers of the languages, who authored and validated culturally relevant questions specific to their regions. We evaluate a broad set of models, including large language models, small language models, multimodal large language models, and small multimodal language models. As a multilingual and multicultural benchmark, NRITYAM sets a new standard for evaluating the ability of AI systems to understand and reason about traditional performing arts. Detailed dataset samples are available at~https://github.com/niladrighosh03/NRITYAM.