Esfandiarpoor, R., Menghini, C., & Bach, S. H. (2024). If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions.
Style de citation Chicago (17e éd.)Esfandiarpoor, Reza, Cristina Menghini, et Stephen H. Bach. If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions. 2024.
Style de citation MLA (9e éd.)Esfandiarpoor, Reza, et al. If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions. 2024.
Attention : ces citations peuvent ne pas être correctes à 100%.