Austin O. Myers

About Me

I am a Research Engineer at Google DeepMind in San Francisco, working on video and language understanding using deep neural networks.

At Google I’ve worked on self-supervised video and language representation learning, using large multimodal models for AI-generated video in YouTube, and capturing special video moments in Google Photos. I’ve also open sourced object detection models, and I previously worked at Google X and Waymo on perception for self-driving cars.

I did my Ph.D. at the University of Maryland, where I worked on understanding the functionality of object parts to enable tool-use for everyday robots. I’m interested in computer vision, deep learning, generative models, large multimodal models, and robotics.

Selected Publications

Streaming Dense Video Captioning

Xingyi Zhou, Anurag Arnab, Shyamal Buch, Shen Yan, Austin Myers, Xuehan Xiong, Arsha Nagrani, and Cordelia Schmid

CVPR, 2024

arXiv Bib Code

@inproceedings{Zhou_2024_CVPR,
  title = {Streaming Dense Video Captioning},
  author = {Zhou, Xingyi and Arnab, Anurag and Buch, Shyamal and Yan, Shen and Myers, Austin and Xiong, Xuehan and Nagrani, Arsha and Schmid, Cordelia},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  showvenue = {CVPR},
  month = jun,
  year = {2024},
  pages = {18243-18252},
}

Distribution Aware Metrics for Conditional Natural Language Generation

David Chan, Yiming Ni, David Ross, Sudheendra Vijayanarasimhan, Austin Myers, and John Canny

LREC-COLING, 2024

arXiv Bib HTML

@inproceedings{Chan_2024_Distribution,
  title = {Distribution Aware Metrics for Conditional Natural Language Generation},
  author = {Chan, David and Ni, Yiming and Ross, David and Vijayanarasimhan, Sudheendra and Myers, Austin and Canny, John},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  showvenue = {LREC-COLING},
  pages = {5064--5095},
  year = {2024},
}

IC3: Image Captioning by Committee Consensus

David Chan, Austin Myers, Sudheendra Vijayanarasimhan, David Ross, and John Canny

EMNLP, 2023

arXiv Bib HTML Code

@inproceedings{Chan_2023_IC3,
  title = {IC3: Image Captioning by Committee Consensus},
  author = {Chan, David and Myers, Austin and Vijayanarasimhan, Sudheendra and Ross, David and Canny, John},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  showvenue = {EMNLP},
  pages = {8975--9003},
  year = {2023},
}

VideoBERT: A Joint Model for Video and Language Representation Learning

Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, and Cordelia Schmid

ICCV, 2019

arXiv Bib

@inproceedings{Sun_2019_ICCV,
  title = {VideoBERT: A Joint Model for Video and Language Representation Learning},
  author = {Sun, Chen and Myers, Austin and Vondrick, Carl and Murphy, Kevin and Schmid, Cordelia},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  showvenue = {ICCV},
  month = oct,
  year = {2019},
}

Im2Calories: towards an automated mobile vision food diary

Austin Myers, Nick Johnston, Vivek Rathod, Anoop Korattikara, Alex Gorban, Nathan Silberman, Sergio Guadarrama, George Papandreou, Jonathan Huang, and Kevin P Murphy

ICCV, 2015

Bib HTML PDF

@inproceedings{Myers_2015_ICCV_im2calories,
  title = {Im2Calories: towards an automated mobile vision food diary},
  author = {Myers, Austin and Johnston, Nick and Rathod, Vivek and Korattikara, Anoop and Gorban, Alex and Silberman, Nathan and Guadarrama, Sergio and Papandreou, George and Huang, Jonathan and Murphy, Kevin P},
  booktitle = {Proceedings of the IEEE international conference on computer vision},
  showvenue = {ICCV},
  pages = {1233--1241},
  year = {2015},
}

Affordance detection of tool parts from geometric features

Austin Myers, Ching L Teo, Cornelia Fermüller, and Yiannis Aloimonos

ICRA, 2015

Bib HTML PDF

@inproceedings{Myers_2015_affordance,
  title = {Affordance detection of tool parts from geometric features},
  author = {Myers, Austin and Teo, Ching L and Ferm{\"u}ller, Cornelia and Aloimonos, Yiannis},
  booktitle = {2015 IEEE International Conference on Robotics and Automation (ICRA)},
  showvenue = {ICRA},
  pages = {1374--1381},
  year = {2015},
}

Affordance of Object Parts from Geometric Features

Austin Myers, Angjoo Kanazawa, Cornelia Fermüller, and Yiannis Aloimonos

RSS, 2014

Bib PDF

@article{Myers_2014_RSS_affordance,
  title = {Affordance of Object Parts from Geometric Features},
  author = {Myers, Austin and Kanazawa, Angjoo and Ferm{\"u}ller, Cornelia and Aloimonos, Yiannis},
  journal = {RGB-D: Advanced Reasoning with Depth Cameras: RSS.},
  showvenue = {RSS},
  year = {2014},
}