卷积神经网络 Top-Down VS Bottom-Up Processing
原文出处： https://explorable.com/top-down-vs-bottom-up-processing Generally speaking, there are two approaches to understanding the process ...
原文：论文：Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering-阅读总结
Bottom Up and Top Down Attention for Image Captioning and Visual Question Answering 阅读总结 笔记不能简单的抄写文中的内容，得有自己的思考和理解。 一 基本信息 .标题：Bottom Up and Top Down Attention for Image Captioning and Visual Question ...
2020-04-02 21:43 0 1149 推荐指数：
相关推荐
论文阅读：Learning Visual Question Answering by Bootstrapping Hard Attention
Learning Visual Question Answering by Bootstrapping Hard Attention Google DeepMind ECCV-2018 Updated on 2020-03-11 14:58:12 Paper：https ...
Hierarchical Question-Image Co-Attention for Visual Question Answering
Hierarchical Question-Image Co-Attention for Visual Question Answering NIPS 2016 Paper: https://arxiv.org/pdf/1606.00061.pdf Code: https ...
【CV论文阅读】Image Captioning 总结
初次接触Captioning的问题，第一印象就是Andrej Karpathy好聪明。主要从他的两篇文章开始入门，《Deep Fragment Embeddings for Bidirectional Image Sentence Mapping》和《Deep Visual ...
论文阅读 | ExtremeNet：Bottom-up Object Detection by Grouping Extreme and Center Points
相关链接 论文地址：https://arxiv.org/abs/1901.08043 论文代码：https://github.com/xingyizhou/ExtremeNet 概述 ExtremeNet是今年（2019）1月23号挂在arxiv上的目标检测论文，是至今为止检测效果 ...
论文阅读：《MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering》
标题：基于知识的视觉问答的多模态知识提取与积累 来源：CVPR 2022https://arxiv.org/abs/2203.09138 代码：https://github.com/Ander ...
论文阅读笔记（二十七）【AAAI2019】：A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification
Introduction 本文有如下3个贡献： ① 提出了一个自下而上（bottom-up）的聚类框架（BUC）来解决无监督的ReID问题； ② 采用repelled损失来优化模型，repelled损失直接优化了样本、聚类之间的余弦距离，可以挖掘聚类之间的相似性以及最大化不同身份之间的差异性 ...
论文：Show, Attend and Tell: Neural Image Caption Generation with Visual Attention-阅读总结
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention-阅读总结 笔记不能简单的抄写文中的内容，得有自己的思考和理解。 一、基本信息 \1.标题：Show, Attend and Tell ...