الملخص

تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.

Multilingual text-vision embedding models are essential for cross-lingual image-text retrieval, but Southeast Asian languages remain poorly supported due to the region's linguistic diversity and limited data and computing resources. In this paper, we introduce SEA-CLIP-Tiny, a compact multilingual text-vision embedding model for Southeast Asia with fewer than 50M parameters. Our model adapts a CLIP-KD-style framework to Southeast Asian multilingual settings through regional data curation and multilingual teacher guidance. Experiments across seven Southeast Asian languages show that SEA-CLIP-Tiny achieves the strongest average retrieval performance among the evaluated student models, reaching 12.9%, 31.5%, and 42.2% at R@1, R@5, and R@10, respectively. Compared with MobileCLIP2, it improves average R@10 by 12.1 points while using 38.4% fewer parameters and lower measured CPU latency. These results highlight the importance of region-aware training for efficient multilingual text-vision models in Southeast Asia.

الكلمات المفتاحية

الموضوع

بيانات النشر

المجلة
غير متاح
وصول مفتوح
وصول مفتوح أخضر

اقتبس هذه المقالة

APA 7

Habibi, P. A., Firdaus, F. A., S, A., Chuangsuwanich, E., Tuchinda, P., & Limkonchotiwat, P. (2026). SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا. https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages

MLA 9

Habibi, Puja Ahmad, et al. "SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا." https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages.

شيكاغو (المؤلف–التاريخ)

Habibi, Puja Ahmad, Faiz Assabil Firdaus, Ashvanth S, Ekapol Chuangsuwanich, Pume Tuchinda, and Peerat Limkonchotiwat. 2026. "SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا." https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages.

هارفارد

Habibi, P. A., Firdaus, F. A., S, A., Chuangsuwanich, E., Tuchinda, P. and Limkonchotiwat, P. (2026) 'SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا', Available at: https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages.

فانكوفر

Habibi PA, Firdaus FA, S A, Chuangsuwanich E, Tuchinda P, Limkonchotiwat P. SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا. https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages

IEEE

P. A. Habibi, F. A. Firdaus, A. S, E. Chuangsuwanich, P. Tuchinda, and P. Limkonchotiwat, "SEA-CLIP-Tiny: تضمين نص-صورة متعدد اللغات فعّال لدول جنوب شرق آسيا," https://omanscience.com/ar/articles/sea-clip-tiny-efficient-multilingual-text-vision-embedding-for-southeast-asian-languages.