arXiv Machine Learning June 10, 2026 By Joonhyung Bae

MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting

Read the original on arXiv Machine Learning →

arXiv:2606. 09855v1 Announce Type: cross Abstract: Korean folk painting (minhwa) is built from a small vocabulary of auspicious symbols, a tiger for protection, a pair of birds for marital harmony, a peony for wealth, that recur across many of its painted genres.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

multimodal

arXiv AI

Jul 7

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

arXiv:2607. 04147v1 Announce Type: cross Abstract: Automated fine-grained perception of calligraphy styles--a task vital to cultural heritage preservation--remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels.

By Yinsheng Yao, Yan Liu, Chen Ye

llms multimodal benchmarks

arXiv Machine Learning

Aug 17

Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings

arXiv:2608. 14435v1 Announce Type: cross Abstract: Frozen image embeddings from models such as CLIP are increasingly used to classify paintings by art-historical style, with high reported accuracy.

By Rory Ashton

rag

arXiv Machine Learning

Sep 21

Fragment-Aware Vision Transformers for Fresco-Fragment Style Classification

arXiv:2609.21012v1 Announce Type: cross Abstract: Artistic style classification is usually studied on complete artworks, where models can exploit global composition, spatial organisation, and iconogr...

By Sara Miketek, Biagio Barchielli, Nadeem Iqbal Kajla, Sinem Aslan

llms safety

arXiv Computer Vision

Sep 22

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding

arXiv:2608.10706v3 Announce Type: replace Abstract: Recent vision-language models demonstrate impressive general visual understanding, yet their art interpretation remains shallow: they describe surf...

By Shuai Wang, Wangyuan Ding, Yixian Shen, Jia-Hong Huang, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring

llms multimodal

arXiv AI

Sep 1

Conducting Stylistic Analysis of Paintings through an Art-History Agent

arXiv:2608.29644v1 Announce Type: cross Abstract: Attributing an artwork to an artist has traditionally relied on detailed visual observations and descriptions, known as stylistic analysis in art his...

By Marc S. Walton, Astrid Harth

llms rag agents computer-vision

arXiv AI

Jul 22

Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models

arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.

By Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan

llms rag multimodal

One email a morning, machine-written

Related stories

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings

Fragment-Aware Vision Transformers for Fresco-Fragment Style Classification

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding

Conducting Stylistic Analysis of Paintings through an Art-History Agent

Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models