/Self-supervised-Video-Representation-Learning

Overview of self-supervised video representation learning methods.

Self-supervised-Video-Representation-Learning

视频自监督表示学习

[ Updating ...... ]

Self-supervised video representation learning aims to learn general representations from video datasets to initialize downstream video tasks.

Image-level self-supervised learning methods can be found in this repository.

We list related papers from conferences and journals such as CVPR, ICCV, ECCV, ICLR, ICML, NeurIPS, AAAI, TPAMI, TIP, TNNLS, TCSVT, TMM etc.

Key words: Unsupervised learning, self-supervised learning, representation learning, pre-training, transfer learning, contrastive learning, pretext task

关键词： 无监督学习，自监督学习，表示学习，预训练，迁移学习，对比学习，借口（代理）任务

2022

  • Masked Autoencoders As Spatiotemporal Learners (**** - NeurIPS22) [paper]
    More Info · · Author(s): Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, Kaiming He
    · · Organization(s): Facebook AI Research (FAIR)
    · · Description:
    · · Tags: Transformer
  • VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training (VideoMAE - NeurIPS22) [paper] [code]
    More Info · · Author(s): Zhan Tong, Yibing Song, Jue Wang, Limin Wang
    · · Organization(s): State Key Laboratory for Novel Software Technology, Nanjing University; Tencent AI Lab
    · · Description:
    · · Tags: Transformer
  • TransRank: Self-Supervised Video Representation Learning via Ranking-Based Transformation Recognition (TransRank - CVPR22 Oral) [paper] [code] [supp]
    More Info · · Author(s): Haodong Duan, Nanxuan Zhao, Kai Chen, Dahua Lin
    · · Organization(s): The Chinese University of HongKong; Shanghai AI Laboratory; Centre of Perceptual and Interactive Intelligence; University of Bath; SenseTime Research
    · · Description:
    · · Tags: Transformer

2021

  • VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples (VideoMoCo - CVPR21) [paper]
    More Info · · Author(s): Tian Pan, Yibing Song, Tianyu Yang, Wenhao Jiang, Wei Liu
    · · Organization(s): Tencent AI Lab; Tencent Data Platform
    · · Description:
    · · Tags:

2020

  • Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning (PRP - CVPR20) [paper]
    More Info · · Author(s): Yuan Yao, Chang Liu, Dezhao Luo, Yu Zhou, Qixiang Ye
    · · Organization(s): UCAS; IIE, CAS
    · · Description:
    · · Tags: Pretext Task
  • Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning (VCP - AAAI20 Oral) [paper]
    More Info · · Author(s): Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, Weiping Wang
    · · Organization(s): IIE, CAS; UCAS
    · · Description:
    · · Tags: Pretext Task

Thanks for the support of Prof. Yu Zhou.