Video Representations learning 관련 논문

End-to-End Learning of Visual Representations from Uncurated Instructional Videos. In CVPR, 2020(Oral) -Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev, Josef Sivic, and Andrew Zisserman

 

ActBERT: Learning GlobalLocal Video-Text Representations. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 - Linchao Zhu and Yi Yang

 

Self-Supervised MultiModal Versatile Networks, In NeurIPS 2020 - Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, ` Relja Arandjelovic, Jason Ramapuram, Jeffrey De Fauw, ´ Lucas Smaira, Sander Dieleman, and Andrew Zisserman

 

RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning, In AAAI 2021 - Peihao Chen, Deng Huang, Dongliang He, Xiang Long, Runhao Zeng, Shilei Wen, Mingkui Tan, and Chuang Gan

 

Hierarchically decoupled spatial-temporal contrast for self-supervised video representation learning, 2020 - Zehua Zhang and David Crandall. 

 

Memoryaugmented dense predictive coding for video representation learning, In ECCV2020, Spotlight - Tengda Han, Weidi Xie, Andrew Zisserman

 

Learning Correspondence from the Cycle-Consistency of Time, In CVPR 2019 - Xiaolong Wang, Allan Jabri, and Alexei A. Efros

 

Temporal CycleConsistency Learning, in CVPR 2019 - Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman.

 

Cycle-Contrast for Self-Supervised Video Representation Learning, In NeurlPS 2020 - Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga, and Tomokazu Murakami

 

Video Representation Learning by Dense Predictive Coding, In ECCV 2020 - Tengda Han, Weidi Xie, Andrew Zisserman

 

( O ) Self-supervised Co-training for Video Representation Learning, In NeurlPS 2020 -Tengda Han, Weidi Xie, and Andrew Zisserman. NeurIPS 2020

 

Self-Supervised Video Representation Learning by Pace Prediction, In ECCV 2020 - Jiangliu Wang, Jianbo Jiao, Yun-Hui Liu

 

Can Temporal Information Help with Contrastive Self-Supervised Learning, In Johns Hopkins, Facebook AI Research - Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra

 

Evidential Deep Learning for Open Set Action Recognition, In ICCV 2021 Oral - Wentao Bao, Qi Yu, Yu Kong

 

Adaptive Focus for Efficient Video Recognition, in ICCV 2021 oral - Yulin Wang∗ , Zhaoxi Chen∗ , Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang†

 

No frame left behind: Full Video Action Recognition, in CVPR 2021 - Xin Liu1 Silvia L. Pintea1 Fatemeh Karimi Nejadasl2 Olaf Booij2 Jan C. van Gemert

 

Self-Supervised Learning by Cross-Modal Audio-Video Clustering, in NeurlPS 2020 spotlight - Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran

 

Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA, in AAAI 2021 - Seonhoon Kim1,2, Seohyeong Jeong1 , Eunbyul Kim2 , Inho Kang2 , Nojun Kwak1

 

A Comprehensive Study of Deep Video Action Recognition, in CVPR2020 video tutorial - Yi Zhu, Xinyu Li, Chunhui Liu, Mohammadreza Zolfaghari, Yuanjun Xiong

 

Audio-Visual Instance Discrimination with Cross-Modal Agreement, in CVPR 2021 - Pedro Morgado, Nuno Vasconcelos, Ishan Misra

 

SlowFast Networks for Video Recognition, In ICCV 2019 oral - Christoph Feichtenhofer Haoqi Fan Jitendra Malik Kaiming He, FAIR

 

SpeedNet: Learning the Speediness in Videos In CVPR 2020 oral - Sagie Benaim1,2∗ Ariel Ephrat1 Oran Lang1 Inbar Mosseri1 William T. Freeman1 Michael Rubinstein1 Michal Irani1,3 Tali Dekel

 

 

---

Probabilistic Representations for Video Contrastive Learning (CVPR 2022)

Cross-Architecture Self-supervised Video Representation Learning (CVPR 2022)

Interact before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition (CVPR 2022)

-> Cross-Modal Knowledge

Large Scale Video Representation Learning via Relational Graph Clustering (CVPR 2020)

-> Grpah + Deep Metric Learning 스펙트럼 clustering 알고리즘(graph기반)

Deep Multimodal Clustering for Unsupervised Audiovisual Learning (CVPR 2019)

->Clustering + EM 알고리즘

Learning Cross-Modal Contrastive Features for Video Domain Adaptation