Attending to Visual Differences for Situated Language Generation in Changing Scenes

Peter Anderson, Xiaodong He, Chris Buehler, Mark Teney, Stephen Johnson, Gould Lei, Anya Belz, Simon Mille, David M. Howcroft, Raffaella Bernardi, Ruket Cakici, Desmond Elliott, David L Chen, Joohyun Kim, Raymond J. Mooney, Howard Chen, Alane Suhr, Dipendra Misra, Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollár, Alasdair Daniel, Francis Clarke, Micha Elsner, Marcella Cornia, Matteo Stefanini, L. Baraldi, Liunian Harold, Mark Li, Da Yatskar, Yin, Cho-Jui, Kai-Wei Chang, Visualbert, Zhuowan Li, Quan Hung, Long Tran, Zhe Mai, Lin, Zhunga Liu, G. Li, G. Mercier, Jiasen Lu, Dhruv Batra, Devi Parikh, Caiming Xiong, Andrew Bennett, Eyvind Valts Blukis, Max Niklasson, Shatkhin Yoav, Artzi, S. Oh, A. Hoogs, A. Perera, Naresh P. Cuntoor, Chia-Chih Chen, J. T. Lee, S. Mukherjee, J. Aggarwal, Q. Ji, K. K. Reddy, M. Shah, Carl Vondrick, H. Pirsiavash, D. Ramanan, Jenny Yuen, A. Torralba, Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Llion Uszkoreit, Aidan N Jones, Łukasz Gomez, Kaiser Illia, Polosukhin. 2017, Attention, Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Ting Yao, Yingwei Pan, Yehao Li, Licheng Yu, Patrick Poirson, Shan Yang, L. BergTamara, Berg, Modeling