NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling

1 code implementation • CVPR 2023 • Shishira R Maiya, Sharath Girish, Max Ehrlich, Hanyu Wang, Kwot Sin Lee, Patrick Poirson, Pengxiang Wu, Chen Wang, Abhinav Shrivastava

This design shares computation within each group, in the spatial and temporal dimensions, resulting in reduced encoding time of the video.

Quantization Video Compression

Revisiting Neighborhood-based Link Prediction for Collaborative Filtering

no code implementations • 29 Mar 2022 • Hao-Ming Fu, Patrick Poirson, Kwot Sin Lee, Chen Wang

While there is a rich literature of such works using advanced models for learning user and item representations separately, item recommendation is essentially a link prediction problem between users and items.

Collaborative Filtering Link Prediction +1

InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning

1 code implementation • 9 Jul 2020 • Kwot Sin Lee, Ngoc-Trung Tran, Ngai-Man Cheung

While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues.

Contrastive Learning Image Generation

Mimicry: Towards the Reproducibility of GAN Research

3 code implementations • AI for Content Creation Workshop at CVPR 2020 2020 • Kwot Sin Lee, Christopher Town

Advancing the state of Generative Adversarial Networks (GANs) research requires one to make careful and accurate comparisons with existing works.