action-recognition.bib

@inproceedings{Arnab_2021_ICCV_ViVit,
  author    = {Arnab, Anurag and Dehghani, Mostafa and Heigold, Georg and Sun, Chen and Lu\v{c}i\'c, Mario and Schmid, Cordelia},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  pages     = {6836-6846},
  title     = {ViViT: A Video Vision Transformer},
  year      = {2021}
}

@inproceedings{Bertasius_ICML2021_TimeSformer,
  author    = {Bertasius, Gedas and Wang, Heng and Torresani, Lorenzo},
  booktitle = {Proceedings of the 38th International Conference on Machine Learning},
  editor    = {Meila, Marina and Zhang, Tong},
  month     = {18--24 Jul},
  pages     = {813--824},
  pdf       = {http://proceedings.mlr.press/v139/bertasius21a/bertasius21a.pdf},
  publisher = {PMLR},
  series    = {Proceedings of Machine Learning Research},
  title     = {Is Space-Time Attention All You Need for Video Understanding?},
  url       = {https://proceedings.mlr.press/v139/bertasius21a.html},
  volume    = {139},
  year      = {2021}
}

@inproceedings{Bulat_NeurIPS2021_X-ViT,
  author    = {Bulat, Adrian and Perez Rua, Juan Manuel and Sudhakaran, Swathikiran and Martinez, Brais and Tzimiropoulos, Georgios},
  booktitle = {Advances in Neural Information Processing Systems},
  editor    = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan},
  pages     = {19594--19607},
  publisher = {Curran Associates, Inc.},
  title     = {Space-time Mixing Attention for Video Transformer},
  url       = {https://proceedings.neurips.cc/paper/2021/file/a34bacf839b923770b2c360eefa26748-Paper.pdf},
  volume    = {34},
  year      = {2021}
}

@inproceedings{Carreira_2017CVPR_I3D,
  author    = {Carreira, Joao and Zisserman, Andrew},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {July},
  title     = {Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset},
  year      = {2017}
}

@article{Duan_arXiv2020_OmniSource,
  author     = {Haodong Duan and
                Yue Zhao and
                Yuanjun Xiong and
                Wentao Liu and
                Dahua Lin},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-2003-13042.bib},
  eprint     = {2003.13042},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Sat, 23 Jan 2021 01:12:44 +0100},
  title      = {Omni-sourced Webly-supervised Learning for Video Recognition},
  url        = {https://arxiv.org/abs/2003.13042},
  volume     = {abs/2003.13042},
  year       = {2020}
}

@inproceedings{Fan_ECCV2020_RubiksNet,
  address   = {Cham},
  author    = {Fan, Linxi
               and Buch, Shyamal
               and Wang, Guanzhi
               and Cao, Ryan
               and Zhu, Yuke
               and Niebles, Juan Carlos
               and Fei-Fei, Li},
  booktitle = {Computer Vision -- ECCV 2020},
  editor    = {Vedaldi, Andrea
               and Bischof, Horst
               and Brox, Thomas
               and Frahm, Jan-Michael},
  isbn      = {978-3-030-58529-7},
  publisher = {Springer International Publishing},
  title     = {RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition},
  year      = {2020}
}

@inproceedings{Fan_ICLR2022_SIFAR,
  author    = {Quanfu Fan and Chun-Fu Chen and Rameswar Panda},
  booktitle = {International Conference on Learning Representations},
  title     = {Can an Image Classifier Suffice For Action Recognition?},
  url       = {https://openreview.net/forum?id=qhkFX-HLuHV},
  year      = {2022}
}

@inproceedings{Feichtenhofer_2019ICCV_SlowFast,
  author    = {Feichtenhofer, Christoph and Fan, Haoqi and Malik, Jitendra and He, Kaiming},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  title     = {SlowFast Networks for Video Recognition},
  year      = {2019}
}

@inproceedings{Feichtenhofer_2020CVPR_X3D,
  author    = {Feichtenhofer, Christoph},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {X3D: Expanding Architectures for Efficient Video Recognition},
  url       = {https://openaccess.thecvf.com/content_CVPR_2020/html/Feichtenhofer_X3D_Expanding_Architectures_for_Efficient_Video_Recognition_CVPR_2020_paper.html},
  year      = {2020}
}

@inproceedings{Feichtenhofer_CVPR2016_Two-Stream_fusion,
  author    = {Feichtenhofer, Christoph and Pinz, Axel and Zisserman, Andrew},
  booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages     = {1933--1941},
  title     = {Convolutional two-stream network fusion for video action recognition},
  year      = {2016}
}

@inproceedings{Girdhar_2019_CVPR_VideoActionTransformerNetwork,
  author    = {Girdhar, Rohit and Carreira, Joao and Doersch, Carl and Zisserman, Andrew},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {Video Action Transformer Network},
  year      = {2019}
}

@article{Girdhar_arXiv2022_OmniMAE,
  author     = {Rohit Girdhar and
                Alaaeldin El{-}Nouby and
                Mannat Singh and
                Kalyan Vasudev Alwala and
                Armand Joulin and
                Ishan Misra},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-2206-08356.bib},
  doi        = {10.48550/arXiv.2206.08356},
  eprint     = {2206.08356},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Tue, 21 Jun 2022 17:35:15 +0200},
  title      = {OmniMAE: Single Model Masked Pretraining on Images and Videos},
  url        = {https://doi.org/10.48550/arXiv.2206.08356},
  volume     = {abs/2206.08356},
  year       = {2022}
}

@inproceedings{Girdhar_CVPR2022_Omnivore,
  author    = {Girdhar, Rohit and Singh, Mannat and Ravi, Nikhila and van der Maaten, Laurens and Joulin, Armand and Misra, Ishan},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  pages     = {16102-16112},
  title     = {Omnivore: A Single Model for Many Visual Modalities},
  year      = {2022}
}

@inproceedings{Hara_2018CVPR_3D_ResNet,
  author    = {Hara, Kensho and Kataoka, Hirokatsu and Satoh, Yutaka},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?},
  year      = {2018}
}

@inproceedings{Hara_ICCVW2017_3D_ResNet,
  author    = {Hara, Kensho and Kataoka, Hirokatsu and Satoh, Yutaka},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops},
  pages     = {3154--3160},
  title     = {Learning spatio-temporal features with 3d residual networks for action recognition},
  year      = {2017}
}

@article{Liang_arXiv2022_MultiDataset,
  author     = {Junwei Liang and
                Enwei Zhang and
                Jun Zhang and
                Chunhua Shen},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-2209-12362.bib},
  doi        = {10.48550/arXiv.2209.12362},
  eprint     = {2209.12362},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Thu, 06 Oct 2022 14:41:30 +0200},
  title      = {Multi-dataset Training of Transformers for Robust Action Recognition},
  url        = {https://doi.org/10.48550/arXiv.2209.12362},
  volume     = {abs/2209.12362},
  year       = {2022}
}

@article{Likhosherstov_arXiv2021_PolyViT,
  author     = {Valerii Likhosherstov and
                Anurag Arnab and
                Krzysztof Choromanski and
                Mario Lucic and
                Yi Tay and
                Adrian Weller and
                Mostafa Dehghani},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-2111-12993.bib},
  eprint     = {2111.12993},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Wed, 01 Dec 2021 15:16:43 +0100},
  title      = {PolyViT: Co-training Vision Transformers on Images, Videos and Audio},
  url        = {https://arxiv.org/abs/2111.12993},
  volume     = {abs/2111.12993},
  year       = {2021}
}

@inproceedings{Lin_2019ICCV_TSM,
  author    = {Lin, Ji and Gan, Chuang and Han, Song},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  title     = {TSM: Temporal Shift Module for Efficient Video Understanding},
  year      = {2019}
}

@inproceedings{Liu_2022CVPR_VideoSwin,
  author    = {Liu, Ze and Ning, Jia and Cao, Yue and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Hu, Han},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  pages     = {3202-3211},
  title     = {Video Swin Transformer},
  year      = {2022}
}

@inproceedings{Neimark_2021_ICCVW_VideoTransformerNetwork,
  author    = {Neimark, Daniel and Bar, Omri and Zohar, Maya and Asselmann, Dotan},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
  month     = {October},
  pages     = {3163-3172},
  title     = {Video Transformer Network},
  year      = {2021}
}

@inproceedings{Qiu_2017ICCV_P3D,
  author    = {Qiu, Zhaofan and Yao, Ting and Mei, Tao},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  month     = {Oct},
  title     = {Learning Spatio-Temporal Representation With Pseudo-3D Residual Networks},
  year      = {2017}
}

@article{Sharir_arxiv2021_STAM,
  author     = {Gilad Sharir and
                Asaf Noy and
                Lihi Zelnik{-}Manor},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-2103-13915.bib},
  eprint     = {2103.13915},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Wed, 07 Apr 2021 15:31:46 +0200},
  title      = {An Image is Worth 16x16 Words, What is a Video Worth?},
  url        = {https://arxiv.org/abs/2103.13915},
  volume     = {abs/2103.13915},
  year       = {2021}
}

@inproceedings{Simonyan_NIPS2014_Two-Stream,
  author    = {Simonyan, Karen and Zisserman, Andrew},
  booktitle = {Advances in Neural Information Processing Systems},
  editor    = {Z. Ghahramani and M. Welling and C. Cortes and N. Lawrence and K.Q. Weinberger},
  pages     = {},
  publisher = {Curran Associates, Inc.},
  title     = {Two-Stream Convolutional Networks for Action Recognition in Videos},
  url       = {https://proceedings.neurips.cc/paper/2014/file/00ec53c4682d36f5c4359f4ae7bd7ba1-Paper.pdf},
  volume    = {27},
  year      = {2014}
}

@inproceedings{Sudhakaran_CVPR2020_GatedShiftNetwork,
  author    = {Sudhakaran, Swathikiran and Escalera, Sergio and Lanz, Oswald},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {Gate-Shift Networks for Video Action Recognition},
  year      = {2020}
}

@inproceedings{Tran_2015ICCV_C3D,
  author    = {Tran, Du and Bourdev, Lubomir and Fergus, Rob and Torresani, Lorenzo and Paluri, Manohar},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  month     = {December},
  title     = {Learning Spatiotemporal Features With 3D Convolutional Networks},
  year      = {2015}
}


@inproceedings{Tran_2018CVPR_R(2+1)D,
  author    = {Tran, Du and Wang, Heng and Torresani, Lorenzo and Ray, Jamie and LeCun, Yann and Paluri, Manohar},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {A Closer Look at Spatiotemporal Convolutions for Action Recognition},
  year      = {2018}
}


@inproceedings{Wang_2013ICCV_IDT,
  author    = {Wang, Heng and Schmid, Cordelia},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  month     = {December},
  title     = {Action Recognition with Improved Trajectories},
  year      = {2013}
}


@inproceedings{Wang_2018CVPR_NonLocal,
  author    = {Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  title     = {Non-Local Neural Networks},
  year      = {2018}
}



@article{Wang_arXiv2019_UniDual,
  author     = {Yufei Wang and
                Du Tran and
                Lorenzo Torresani},
  bibsource  = {dblp computer science bibliography, https://dblp.org},
  biburl     = {https://dblp.org/rec/journals/corr/abs-1906-03857.bib},
  eprint     = {1906.03857},
  eprinttype = {arXiv},
  journal    = {CoRR},
  timestamp  = {Fri, 14 Jun 2019 09:38:24 +0200},
  title      = {UniDual: {A} Unified Model for Image and Video Understanding},
  url        = {http://arxiv.org/abs/1906.03857},
  volume     = {abs/1906.03857},
  year       = {2019}
}


@inproceedings{Wang_ECCV2016_TSN,
  author    = {Limin Wang and
               Yuanjun Xiong and
               Zhe Wang and
               Yu Qiao and
               Dahua Lin and
               Xiaoou Tang and
               Luc Van Gool},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl    = {https://dblp.org/rec/conf/eccv/WangXW0LTG16.bib},
  booktitle = {Computer Vision - {ECCV} 2016 - 14th European Conference, Amsterdam,
               The Netherlands, October 11-14, 2016, Proceedings, Part {VIII}},
  doi       = {10.1007/978-3-319-46484-8\_2},
  editor    = {Bastian Leibe and
               Jiri Matas and
               Nicu Sebe and
               Max Welling},
  pages     = {20--36},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  timestamp = {Wed, 25 Sep 2019 18:11:12 +0200},
  title     = {Temporal Segment Networks: Towards Good Practices for Deep Action
               Recognition},
  url       = {https://doi.org/10.1007/978-3-319-46484-8\_2},
  volume    = {9912},
  year      = {2016}
}


@article{Wang_IJCV2013_DT,
  author    = {Heng Wang and
               Alexander Kl{\"{a}}ser and
               Cordelia Schmid and
               Cheng{-}Lin Liu},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl    = {https://dblp.org/rec/journals/ijcv/WangKSL13.bib},
  doi       = {10.1007/s11263-012-0594-8},
  journal   = {International Journal of Computer Vision},
  number    = {1},
  pages     = {60--79},
  timestamp = {Fri, 13 Mar 2020 10:58:58 +0100},
  title     = {Dense Trajectories and Motion Boundary Descriptors for Action Recognition},
  url       = {https://doi.org/10.1007/s11263-012-0594-8},
  volume    = {103},
  year      = {2013}
}


@inproceedings{Xie_2018ECCV_S3D_Kinetics200,
  author    = {Xie, Saining and Sun, Chen and Huang, Jonathan and Tu, Zhuowen and Murphy, Kevin},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  month     = {September},
  title     = {Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification},
  year      = {2018}
}

@inproceedings{Zhang_2021ICCV_VidTr,
  author    = {Zhang, Yanyi and Li, Xinyu and Liu, Chunhui and Shuai, Bing and Zhu, Yi and Brattoli, Biagio and Chen, Hao and Marsic, Ivan and Tighe, Joseph},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  pages     = {13577-13587},
  title     = {VidTr: Video Transformer Without Convolutions},
  year      = {2021}
}


@inproceedings{Zhang_ACMMM2021_TokenShift,
  address   = {New York, NY, USA},
  author    = {Zhang, Hao and Hao, Yanbin and Ngo, Chong-Wah},
  booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
  doi       = {10.1145/3474085.3475272},
  isbn      = {9781450386517},
  keywords  = {transformer, self-attention, shift, video classification},
  location  = {Virtual Event, China},
  numpages  = {9},
  pages     = {917–925},
  publisher = {Association for Computing Machinery},
  series    = {MM '21},
  title     = {Token Shift Transformer for Video Classification},
  url       = {https://doi.org/10.1145/3474085.3475272},
  year      = {2021}
}