【PhD. in USM】2022/6 Study Notes

Study Target：

• understand of the current state of machine learning development
• study about GNN
• study about pretrain model about BERT-class multimodal
• review at least 20 papers

---

Studied Contents：

NLP：

1. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

GNN:

1. Literature：Vision GNN: An Image is Worth Graph of Nodes
2. Literature：Dynamic graph cnn for learning on point clouds
3. Literature：Deepgcns: Can gcns go as deep as cnns?

BERT-class multimodal model

1. Literature：LXMERT: Learning Cross-Modality Encoder Representations from Transformers
2. Literature：ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

Vision Transformer

1. Vision Xformers: Efficient Attention for Image Classification
2. A Survey of Visual Transformers

Thesis

1. Visual and Textual Common Semantic Spaces for the Analysis of Multimodal Content

Video

1. CMU’s Multimodal Machine Learning course (11-777), Fall 2020 - YouTube

---