% Key papers for Contrastive video representation learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2021_is_39483,
  title = {{Is Space-Time Attention All You Need for Video Understanding?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8941},
}

@inproceedings{cvpr2016_anticipating_11401,
  title = {{Anticipating Visual Representations From Unlabeled Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_self_12618,
  title = {{Self-Supervised Video Representation Learning With Odd-One-Out Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_self_14800,
  title = {{Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2019_self_103476,
  title = {{Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4873},
}

@inproceedings{neurips2021_vatt_62247,
  title = {{VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27777},
}

@inproceedings{neurips2018_cooperative_56983,
  title = {{Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11745},
}

@inproceedings{cvpr2020_few_15548,
  title = {{Few-Shot Video Classification via Temporal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2020_self_60809,
  title = {{Self-supervised Co-Training for Video Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16825},
}

@inproceedings{neurips2020_self_60802,
  title = {{Self-Supervised Learning by Cross-Modal Audio-Video Clustering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16912},
}

@inproceedings{cvpr2019_adaframe_13821,
  title = {{AdaFrame: Adaptive Frame Selection for Fast Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_video_16448,
  title = {{Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2022_memvit_19325,
  title = {{MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2020_video_103733,
  title = {{Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6840},
}

@inproceedings{cvpr2016_slow_11872,
  title = {{Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_geometry_13158,
  title = {{Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gan_Geometry_Guided_Convolutional_CVPR_2018_paper.html},
}

@inproceedings{cvpr2016_you_11985,
  title = {{You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{aaai2020_an_99763,
  title = {{An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5364},
}

@inproceedings{cvpr2022_self_19838,
  title = {{Self-Supervised Video Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_vita_22549,
  title = {{Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21282},
}

@inproceedings{cvpr2024_ost_24318,
  title = {{OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29252},
}

@inproceedings{cvpr2024_understanding_25120,
  title = {{Understanding Video Transformers via Universal Concept Discovery}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31314},
}

@inproceedings{cvpr2025_beyond_25578,
  title = {{Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32730},
}

@inproceedings{cvpr2025_viewpoint_28109,
  title = {{Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33713},
}

@inproceedings{neurips2025_smooth_80236,
  title = {{Smooth Regularization for Efficient Video Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xcrAO2jYPi},
}

@inproceedings{iclr2026_privacy_88516,
  title = {{Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=ncA3UUL0Ri},
}

@inproceedings{neurips2026_lookwhen_91004,
  title = {{LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149223},
}

@inproceedings{neurips2026_not_95063,
  title = {{Not All Layers Are Equal in Image-to-Video Transfer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/153476},
}