Yang Zhang

> Our paper titled "Bilateral-ViT for Robust Fovea Localization" has been accepted to ISBI 2022 conference and a preprint is available at this link: https://arxiv.org/abs/2110.09860 > > I would appreciate...

> Hi @Yangzhangcst > Thank you for this repo. > The code for paper "STAR: Sparse Transformer-based Action Recognition" is available at the link: > https://github.com/imj2185/STAR Thanks for your help....

> Hello, > > Just thought that this paper: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation by Valada et al. might > be useful to add to this list, since...

> Hi, > > Thanks for the great collection! > Hope our 2019 work could help as a complement with evaluation on NYUv2 dataset. > > https://arxiv.org/abs/1910.01460 Thanks for your...

> Hello, Thanks for the github. Thought that our work may also help for rgbd research. Depth-Adapted CNN for RGB-D cameras, ACCV 20 https://arxiv.org/pdf/2009.09976.pdf Thanks for your help. We have...

> It is used in line 51 of demo_AF_Graph_BSD300.m but I cannot see its creation before. It is predata (extracted features) which can be downloaded from [GL-Graph](https://github.com/xiaofanglegoc/global-local-affinity-graph) and placed in...

> Can I somehow use your approach for custom images? In that way how I can precompute those features? If you only use mLab feature, you can refer to our...

> Hello, thanks for the nice list, > > Please consider adding our recent work: https://arxiv.org/abs/2404.18849 > > We propose a Mixed Patches (MiPa), in conjunction with a patch-wise domain...