Highly skewed long-tail item distribution is very common in recommendation systems. It significantly affects model performance, and especially on tail items. To improve tail-item recommendation, we conduct research to transfer knowledge from head items to tail items, leveraging the rich user feedback in head items and the semantic connections between head and tail items. Specifically, we propose a novel dual transfer learning framework that collaboratively learns the knowledge transfer from both model-level and item-level. The model-level knowledge transfer builds a generic meta- mapping of model parameters from few-shot to many-shot model. It captures the implicit data augmentation on the model level to improve the representation learning of tail items. The item-level transfer connects head and tail items through item-level features, to ensure a smooth transfer of meta-mapping from head items to tail items. The two types of transfers are incorporated to ensure the learned knowledge from head items can be well applied for tail item representation learning in the long-tail distribution settings. Through extensive experiments on two benchmark datasets, results show that our proposed dual transfer learning framework significantly outperforms other state-of-the-art methods for tail item recommendation in hit ratio and NDCG. It is also very encouraging that our framework further improves head items and overall performance on top of the gains on tail items.