Daniel Ward

Daniel Ward

Computer Science - Robotics - Learning

Temporally Coherent Embeddings for Self-Supervised Video Representation Learning

Published in ECCV (under review), 2020

Recommended citation: Knights, J., Vanderkop, A., Ward, D., Mackenzie-Ross, O., & Moghadam, P. (2020). Temporally Coherent Embeddings for Self-Supervised Video Representation Learning. arXiv preprint arXiv:2004.02753. https://arxiv.org/abs/2004.02753

Paper

Project Webpage The paper can be found here.

Code

The code can be obtained here.

Pretrained Model

The pretrained model for this study can be downloaded here

Attribution

If you use the code or pretrained models please cite:

Knights, J., Vanderkop, A., Ward, D., Mackenzie-Ross, O., & Moghadam, P. (2020). Temporally Coherent Embeddings for Self-Supervised Video Representation Learning. arXiv preprint arXiv:2004.02753.

Bibtext

@misc{knights2020temporally,
    title={Temporally Coherent Embeddings for Self-Supervised Video Representation Learning},
    author={Joshua Knights and Anthony Vanderkop and Daniel Ward and Olivia Mackenzie-Ross and Peyman Moghadam},
    year={2020},
    eprint={2004.02753},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}