论文阅读
文章平均质量分 92
BXDBB
通过博客分享部分自己看过的论文、总结自己做的一些有意义的工作,欢迎大家一起交流讨论呀~
1728823367@qq.com
展开
-
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition——2022 TPAMI论文笔记
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition——2022 TPAMI论文笔记。分层详细介绍模型架构。原创 2022-11-10 17:30:13 · 904 阅读 · 2 评论 -
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in ... ——2022 CVPR 论文笔记
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering——2022 CVPR 论文笔记原创 2022-07-15 11:41:16 · 683 阅读 · 6 评论 -
MCAN:Deep Modular Co-Attention Networks for Visual Question Answering——2019 CVPR 论文笔记
经典VQA模型:MCAN——《Deep Modular Co-Attention Networks for Visual Question Answering》, 2019 CVPR论文阅读笔记。原创 2022-06-30 09:04:21 · 657 阅读 · 1 评论 -
《Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning》—论文笔记
《Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning》—2021 CVPR Oral 论文笔记,以及自己跑的实验效果,供大家参考~原创 2022-06-23 10:28:44 · 359 阅读 · 3 评论 -
《Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering》——2018 CVPR论文笔记
《Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering》和《Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challeng》——2018 CVPR 论文阅读笔记原创 2022-06-13 20:50:41 · 619 阅读 · 1 评论 -
《Stacked Attention Networks for Image Question Answering》论文解读与实验
《Stacked Attention Networks for Image Question Answering》论文解读与实验效果原创 2022-06-02 10:29:06 · 616 阅读 · 7 评论 -
VOLO: Vision Outlooker for Visual Recognition——2022 TPAMI论文笔记
VOLO: Vision Outlooker for Visual Recognition——2022 TPAMI论文笔记。用具体数据说明Outlook Attention实现过程中的维度变化。原创 2022-11-03 17:29:55 · 702 阅读 · 4 评论