arXiv AI
Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 8
ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China
We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO World Heritage sites in China. The dataset comprises 2,279 in-the-wild images paired with 14,133 bilingual (Chinese/English) multiple-choice QA pairs spanning seven cognitive dimensions, from basic identity recognition to historical periodization and architectural analysis.
arXiv Machine Learning
Oct 7
What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization
arXiv:2610.07269v1 Announce Type: cross Abstract: Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles thr...
arXiv Computation and Language
Aug 28
Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects
BanglaVerse is a new benchmark that evaluates multilingual vision‑language models on Bengali culture, covering nine visual domains and expanding to four languages and five Bangla dialects for a total of about 32,200 artifacts. It includes visual question answering and captioning tasks built from 1,152 manually curated images. Experiments show that models perform worse on dialectal variants and that missing cultural knowledge, rather than visual grounding, is the main bottleneck.
arXiv Computation and Language
Oct 5
WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models
arXiv:2510.22276v4 Announce Type: replace-cross Abstract: Contrastive vision-language models have achieved remarkable progress through large-scale pretraining. Recent work has shown that removing Eng...
arXiv Computation and Language
4d ago
MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages
MultiInpaintCOCO extends the English InpaintCOCO dataset to 13 typologically diverse languages, creating a multilingual benchmark of 953 minimal-pair examples focused on fine-grained visual details. The study evaluates state-of-the-art multilingual multimodal retrieval models, revealing that performance drops significantly for lower-resource languages and that many models exhibit a systematic bias toward English captions. The benchmark and code are publicly available at https://github.com/ufal/multi-inpaint-coco.
arXiv Computation and Language
Sep 28
SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages
SEA-CLIP-Tiny is a compact multilingual text‑vision embedding model designed for Southeast Asian languages, containing fewer than 50 million parameters. It adapts a CLIP‑KD framework with region‑specific data curation and multilingual teacher guidance. Across seven languages, it outperforms other student models, achieving R@1 = 12.9%, R@5 = 31.5%, and R@10 = 42.2%, and surpasses MobileCLIP2 by 12.1 points in R@10 while using 38.4% fewer parameters and lower CPU latency.