attentive专题

[读论文]精读Self-Attentive Sequential Recommendation

论文链接：https://arxiv.org/abs/1808.09781 其他解读文章：https://mp.weixin.qq.com/s/cRQi3FBi9OMdO7imK2Y4Ew 摘要顺序动态是许多现代推荐系统的一个关键特征，这些系统试图根据用户最近执行的操作来捕获用户活动的“上下文”。为了捕捉这种模式，两种方法已经激增：马尔可夫链（MC）和递归神经网络（RNN）。马尔可夫链假设用

[论文解读-单图像去雨-SPANet] Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset

[论文解读-单图像去雨]Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset 目录 [论文解读-单图像去雨]Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset 目录1.相关链接2.发现问题

Transformer-XL: 非固定长度上下文的注意力语言模型（Attentive Language Models Beyond a Fixed-Length Context）

文章目录 Vanilla Transformer Language ModelsSegment-Level Recurrence with State ReuseRelative Positional Encodings Reference 1. Transformer-XL: Attentive Language Models Beyond a Fixed-Length Con

群组推荐模型---AGREE(Attentive Group Recommendation)

群组推荐模型---AGREE AGREE简单概述基于注意力的群组表征学习（Attentive Group Representation Learning）NCF(Neural Collaborative Filtering) AGREE简单概述群组推荐领域比较经典的论文便是AGREE(Attentive Group Recommendation)，此文的主要贡献如下：（1）利用

Action Recognition-Temporal Attentive Alignment for Large-Scale Video Domain Adaptation——ICCV2019

Abstract image-based domain adaptation, domain shift in videos, Two large-scale DA datasets (UCF-HMDB_full, Kinetics-Gameplay) Introduction videos can suffer from domain discrepancy along both th