Xi Meng, Hao Kong, Dongqi Tang, Tong Lu. Multimodal Image Captioning Through Combining Reinforced Cross Entropy Loss and Stochastic Deprecation. In IEEE International Conference on Multimedia and Expo, ICME 2019, Shanghai, China, July 8-12, 2019. pages 1318-1323, IEEE, 2019. [doi]
Abstract is missing.