``` @inproceedings{wolf-etal-2020-transformers, title = "Transformers: State-of-the-Art Natural Language Processing", author = "Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and RĂ©mi Louf and Morgan Funtowicz and Joe Davison and Sam Shleifer and Patrick von Platen and Clara Ma and Yacine Jernite and Julien Plu and Canwen Xu and Teven Le Scao and Sylvain Gugger and Mariama Drame and Quentin Lhoest and Alexander M. Rush", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", month = oct, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.emnlp-demos.6", pages = "38--45" } ``` ``` @inproceedings{changpinyo2021cc12m, title = {{Conceptual 12M}: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}, author = {Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu}, booktitle = {CVPR}, year = {2021}, } ``` ``` @InProceedings{mariannmt, title = {Marian: Fast Neural Machine Translation in {C++}}, author = {Junczys-Dowmunt, Marcin and Grundkiewicz, Roman and Dwojak, Tomasz and Hoang, Hieu and Heafield, Kenneth and Neckermann, Tom and Seide, Frank and Germann, Ulrich and Fikri Aji, Alham and Bogoychev, Nikolay and Martins, Andr\'{e} F. T. and Birch, Alexandra}, booktitle = {Proceedings of ACL 2018, System Demonstrations}, pages = {116--121}, publisher = {Association for Computational Linguistics}, year = {2018}, month = {July}, address = {Melbourne, Australia}, url = {http://www.aclweb.org/anthology/P18-4020} } ``` ``` @misc{agrawal2016vqa, title={VQA: Visual Question Answering}, author={Aishwarya Agrawal and Jiasen Lu and Stanislaw Antol and Margaret Mitchell and C. Lawrence Zitnick and Dhruv Batra and Devi Parikh}, year={2016}, eprint={1505.00468}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ``` @misc{li2019visualbert, title={VisualBERT: A Simple and Performant Baseline for Vision and Language}, author={Liunian Harold Li and Mark Yatskar and Da Yin and Cho-Jui Hsieh and Kai-Wei Chang}, year={2019}, eprint={1908.03557}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` ``` @misc{vaswani2017attention, title={Attention Is All You Need}, author={Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin}, year={2017}, eprint={1706.03762}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ``` @misc{radford2021learning, title={Learning Transferable Visual Models From Natural Language Supervision}, author={Alec Radford and Jong Wook Kim and Chris Hallacy and Aditya Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever}, year={2021}, eprint={2103.00020}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```