mlsanityData to 7 Oct 2026

Contrastive Language-Image Pre-training for the Italian Language

arXiv 2108.08688 ↗First posted 19 Aug 2021cs.CL cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts. The model is trained on a massive amount of English data and shows impressive performance on zero-shot classification tasks. Training the same model on a different language is not trivial, since data in other languages might be not enough and the model needs high-quality translations of the texts to guarantee a good performance. In this paper, we present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-text pairs. Results show that CLIP-Italian outperforms the multilingual CLIP model on the tasks of image retrieval and zero-shot classification.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 12 of its 35 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

12 of 35 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  7. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  8. 2020How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Modelscited by 313
  9. 2021WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learningcited by 285
  10. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  11. 2020What the [MASK]? Making Sense of Language-Specific BERT Modelscited by 44
  12. 2020BERT Goes Shopping: Comparing Distributional Models for Product Representationscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 11; 2024: 2; 2025: 1; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  2. 2023MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiologycited by 149
  3. 2023Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Imagescited by 128
  4. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  5. 2022AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilitiescited by 84
  6. 2023Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languagescited by 52
  7. 2022Contrastive language and vision learning of general fashion conceptscited by 41
  8. 2023NLLB-CLIP -- train performant multilingual image retrieval model on a budgetcited by 24
  9. 2023UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classificationcited by 21
  10. 2022Name Your Style: An Arbitrary Artist-aware Image Style Transfercited by 14
  11. 2023Open-Vocabulary Object Detection using Pseudo Caption Labelscited by 13
  12. 2023Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representationscited by 11
7 more
  1. 2023CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languagescited by 7
  2. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferabilitycited by 5
  3. 2023C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative Gapcited by 3
  4. 2023UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguationcited by 0
  5. 2024Bridging Text and Image for Artist Style Transfer via Contrastive Learningcited by 0
  6. 2025Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuningcited by 0
  7. 2026SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languagescited by 0