深度学习视频理解相关热点论文汇总

  • Hand-crafted

       Dense Trajectory

 

  • Action Recognition

      suvery : https://blog.csdn.net/On_theway10/article/details/88866091

 

  • Action Localization

      https://blog.csdn.net/On_theway10/article/details/89207138

     [2016-CVPR] Temporal action localization in untrimmed videos via multi-stage CNNs.

     [2017-ICCV] TURN TAP: Temporal unit regression network for temporal action proposals.

     [2017-ICCV] R-C3D: Region convolutional 3D network for temporal activity detection.

     [2017-ICCV] Temporal action detection with structured segment networks

     [2017-CVPR] CDC: Convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos

  • Anomaly Detection

     [2018-CVPR] Real-world anomaly detection in surveillance videos.

 

  • Summarizaton/Synopsis

     [2014-ECCV] Creating summaries from user videos.

     [2016-TIP] Surveillance video synopsis via scaling down objects

 

  • Video Captioning

     [2015-ICCV] Sequence to Sequence–Video to Text.

 

  • Next Frame

     [2016-ICLR] Deep multi-scale video prediction beyond mean square error.

     [2016-NIPS] Generating videos with scene dynamics

 

  • Object tracking

    [2016-ECCV] Fully-convolutional siamese networks for object tracking.

    [2017-CVPR] ECO: Efficient Convolution Operators for tracking.

    [2017-CVPR] End-to-end representation learning for correlation filter based tracking 

 

视频理解研究进展: https://blog.csdn.net/sgfmby1994/article/details/80497537

  • 1
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

ReLuJie

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值