Multimodal contrastive training for visual representation learning

X Yuan, Z Lin, J Kuen, J Zhang… - Proceedings of the …, 2021 - openaccess.thecvf.com
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …
被引用次数：172 相关文章

Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang… - 2021 IEEE/CVF …, 2021 - computer.org
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …

Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang… - arXiv e …, 2021 - ui.adsabs.harvard.edu
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …
[PDF] uchicago.edu

[PDF][PDF] Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang, M Maire… - people.cs.uchicago.edu
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …

Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang… - arXiv preprint arXiv …, 2021 - arxiv.org
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …

Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang… - 2021 IEEE/CVF …, 2021 - ieeexplore.ieee.org
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …
[PDF] uchicago.edu

[PDF][PDF] Multimodal Contrastive Training for Visual Representation Learning

X Yuan, Z Lin, J Kuen, J Zhang, Y Wang, M Maire… - people.cs.uchicago.edu
We develop an approach to learning visual representations that embraces multimodal data,
driven by a combination of intra-and inter-modal similarity preservation objectives. Unlike …