1、In this paper, we address this problem by jointly learning a deep model for two tasks, i.e. face hallucination and recognition.
本文是連接兩個任務模型：hallucination和recognition。
2、The recognition subnetwork are responsible for producing discriminative feature representations using the hallucinated images as inputs generated by hallucination sub-network.
recognition網絡的輸入就是hallucination網絡的輸出。
3、Empirical studies [14] in face recognition proved that a minimum face resolution between 32 × 32 and 64×64 is required for stand-alone recognition algorithms.
經驗研究發現用於人臉識別算法的最小的人臉圖像大小是32x32到64x64之間。
4、