Report/Presentation

2022.11 CS231n学习汇报

介绍CS231n部分的学习，包含计算机视觉简介、图像分类（K最邻近算法、线性分类）、神经网络以及卷积神经网络部分

2022.12 行人重识别任务汇报

关于行人重识别第一个阶段的学习汇报

2023.9 行人检测汇报

关于行人检测系列论文汇报汇总

• Co-Scale Conv-Attentional Image Transformers
• LEAPS: End-to-End One-Step Person Search With Learnable Proposals
• Cascade Transformers for End-to-End Person Search
• PSTR: End-to-End One-Step Person Search With Transformers
• FCOS: Fully Convolutional One-Stage Object Detection
• Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection

2024.1 相关论文阅读汇报

包含其他方面结合MAE部分的汇报

• Generic-to-Specific Distillation of Masked Autoencoders

2024.3 2024春季论文汇报

包含MAE有关工作及文章部分汇总

• Masked Autoencoders Are Scalable Vision Learners

• BEiT: BERT Pre-Training of Image Transformers

• BEIT V2: Masked Image Modeling with Vector-Quantized Visual Tokenizers

• Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality

• HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling

• MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

• MultiMAE: Multi-modal Multi-task Masked Autoencoders

• ConvMAE: Masked Convolution Meets Masked Autoencoders

• RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder

• Siamese Masked Autoencoders

• Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

• Integral Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

• Masked Image Modeling with Local Multi-Scale Reconstruction

• VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking