自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(5)
  • 收藏
  • 关注

原创 【论文阅读】Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

【论文阅读】Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQAmotivation motivation

2022-03-25 16:48:50 3357

原创 【论文阅读】Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data

【论文阅读】Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Datamotivationtaskdifficultcontributionmethodexperimentdatasetsimage descriptionvideo descriptionmetricsResults可视化conclusionRelated WorkDeep CaptioningZero-Shot

2022-03-01 15:07:54 539

原创 【论文阅读】TextCaps: a Dataset for Image Captioning with Reading Comprehension

【论文阅读】TextCaps: a Dataset for Image Captioning with Reading Comprehensionmotivationtaskdifficultychallengescontributionrelated worksImage CaptioningOptical Character Recognition (OCR)Visual Question Answering with Text Reading AbilityTextCaps Dataset数据集构建数

2022-02-28 12:12:24 3207

原创 【2022.02.25】AnchorCaptioner配环境

AnchorCaptioner配环境配环境conda env create -f textcap.yaml时pip报错pycocoevalcap安装问题 代码: https://github.com/guanghuixu/AnchorCaptioner paper: Towards Accurate Text-based Image Captioning with Content Diversity Exploration 配环境 conda env create -f textcap.yaml conda

2022-02-25 18:28:54 442

原创 screen的用法总结

screen的用法总结

2022-02-09 18:21:31 416

空空如也

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除