Bai Kai's Projects
3D ResNets for Action Recognition (CVPR 2018)
Awesome paper list for compositional zero-shot learning (CZSL)
Awesome Crowd Counting
TensorFlow code and pre-trained models for BERT
C3D-LSTM implementation in PyTorch
Pytorch porting of C3D network, with Sports1M weights
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
Code For MachineLearning
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,近30万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系[email protected] 版权所有,违权必究 Tan 2018.06
This is the code for Disentangled and Recurrent Prompt Tunning.
This is the repo for paper
This repository is an official Tensorflow 2 implementation of Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning
Implementation of Federated Learning to Person Re-identification (Code for ACMMM 2020 paper)
Must-read papers on graph neural networks (GNN)
Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification ECCV 2020
[VisDA-2020 (ECCVW)] Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID (Top-performing Solution).
Implementation of Non-local Block.
Open-source toolbox for unsupervised or domain adaptive object re-ID.
Pytorch implement of Person re-identification baseline. We arrived Rank@1=88.24%, mAP=70.68% only with softmax loss. Re-ranking is added.
Prompt Tuning based Adapter for Vision-Language Model Adaption
Model summary in PyTorch similar to `model.summary()` in Keras
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
Python HTTP Requests for Humans™ ✨🍰✨
Taming Transformers for High-Resolution Image Synthesis
ICML2022: Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning