“…The results are presented in Figures 11–13, respectively. For comparison purposes, we include methods such as [15] (Gao et al , 2021), [22] (Pu et al , 2018), [23] (Huang et al , 2018), [24] (Wang et al , 2018a), [25] (Venugopalan et al , 2015b), [26] (Luong et al , 2015), [27] (Chan et al , 2016), [28] (Bin et al , 2018), [29] (Camgoz et al , 2020), [30] (Li et al , 2020), [31] (Lafferty et al , 2001), [32] (Morency et al , 2007), [33] (Zhang et al , 2014), [34] (Venugopalan and Rohrbach, 2015a), [35] (Pan et al , 2016) and [36] (Guo et al , 2019). We observe that the proposed Savitar model performs better than the state-of-the-art with a large margin on the three datasets, indicating the superiority of our model.…”