Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey E. Hinton. Pix2seq: A Language Modeling Framework for Object Detection. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022. [doi]
@inproceedings{ChenSLFH22, title = {Pix2seq: A Language Modeling Framework for Object Detection}, author = {Ting Chen and Saurabh Saxena and Lala Li and David J. Fleet and Geoffrey E. Hinton}, year = {2022}, url = {https://openreview.net/forum?id=e42KbIw6Wb}, researchr = {https://researchr.org/publication/ChenSLFH22}, cites = {0}, citedby = {0}, booktitle = {The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022}, publisher = {OpenReview.net}, }