/Paper

论文阅读笔记，github比百度云好用嘛。。。

Paper

目录

  • caption

    • 从视频到语言_ 视频标题生成与描述研究综述 自动化学报，2022

  • cv

    • 总结性文档

      • 视频方向论文粗分类.md

    • fine grain

      • FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding，2020，CVPR

    • image

      • Mask RCNN

    • 双流

      • Two-Stream Convolutional Networks for Action Recognition in Videos，2014
      • Long-term Recurrent Convolutional Networks for Visual Recognition and Description，2015，CVPR
      • Convolutional Two-Stream Network Fusion for Video Action Recognition，2016，CVPR
      • Temporal Segment Networks for Action Recognition in Videos，TSN，2018，IEEE
      • Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision，2019，AAAI
      • Multi-Instance Multi-Label Action Recognition and Localization Based on Spatio-Temporal Pre-Trimming for Untrimmed Videos，2020，AAAI

    • 3d

      • Learning Spatiotemporal Features with 3D Convolutional Networks，C3D，ICCV，2015

    • 姿态检测

      • 总结性文档
        • 姿态检测概述.md
        • ECCV2020 Pose Estimation.md
        • MPII数据集SOTA.md
        • PoseTrack17&18.md
        • Pose estimation.pdf
        • Pose estimation.mindnode
      • 单人
        • Learning Human Pose Estimation Features with Convolutional Networks，ICLR，2014
        • Convolutional Pose Machines，CVPR，2016。
        • Learning Feature Pyramids for Human Pose Estimation，ICCV，2017
        • Stacked Hourglass Networks for Human Pose Estimation，ECCV，2016
        • Multi-Context Attention for Human Pose Estimation CVPR，2017
        • A Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation，AAAI，2018
        • Human Pose Estimation with Spatial Contextual Information，2019，不知道是哪个会议的。。。
        • Cascade Feature Aggregation for Human Pose Estimation，2019，还是不知道是哪个会议的。。。

  • nlp

    • Self-Attentional Models for Lattice Inputs