目錄

1. Scene Graph Generation with External Knowledge and Image Reconstruction

2. Knowledge Acquisition for Visual Question Answering via Iterative Querying

Author: 李飛飛

publish: CVPR 2017

3. Towards VQA Models That Can Read

4. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

1.1 將BERT用于image roi 和text, 然后將text的word embedding和image roi的embedding用于其他任務，取得2-10個百分點的提升。

5. VL-BERT: PRE-TRAINING OF GENERIC VISUAL LINGUISTIC REPRESENTATIONS

6. VISUALBERT: A SIMPLE AND PERFORMANT BASELINE FOR VISION AND LANGUAGE

7.Dynamic Memory Networks for Visual and Textual Question Answering

publlish: ICML 2016

轉載于:https://www.cnblogs.com/yeran/p/11447810.html

總結

以上是生活随笔為你收集整理的论文笔记03的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。