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

@inproceedings{cvpr2016_learning_11669,
  title = {{Learning Temporal Regularity in Video Sequences}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2020_x3d_16500,
  title = {{X3D: Expanding Architectures for Efficient Video Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_unsupervised_12726,
  title = {{Unsupervised Video Summarization With Adversarial LSTM Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2022_masked_19317,
  title = {{Masked Feature Prediction for Self-Supervised Visual Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_videomae_22522,
  title = {{VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21454},
}

@inproceedings{aaai2018_deep_103996,
  title = {{Deep Reinforcement Learning for Unsupervised Video Summarization With Diversity-Representativeness Reward}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12255},
}

@inproceedings{neurips2022_videomae_64218,
  title = {{VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54362},
}

@inproceedings{cvpr2016_hierarchical_11589,
  title = {{Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_spatiotemporal_17933,
  title = {{Spatiotemporal Contrastive Video Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_central_15247,
  title = {{Central Similarity Quantization for Efficient Image and Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_highlight_11592,
  title = {{Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2016_deep_11469,
  title = {{Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_attention_12848,
  title = {{Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Long_Attention_Clusters_Purely_CVPR_2018_paper.html},
}

@inproceedings{neurips2022_masked_65064,
  title = {{Masked Autoencoders As Spatiotemporal Learners}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55378},
}

@inproceedings{cvpr2017_real_12568,
  title = {{Real-Time Neural Style Transfer for Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_videomoco_18122,
  title = {{VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial Examples}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2016_detecting_11492,
  title = {{Detecting Events and Key Actors in Multi-Person Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2019_self_14799,
  title = {{Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_a_16538,
  title = {{A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2016_summary_11903,
  title = {{Summary Transfer: Exemplar-Based Subset Selection for Video Summarization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2025_change3d_25691,
  title = {{Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34077},
}

@inproceedings{cvpr2024_csta_22936,
  title = {{CSTA: CNN-based Spatiotemporal Attention for Video Summarization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31330},
}

@inproceedings{cvpr2025_generalizing_26410,
  title = {{Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32632},
}

@inproceedings{cvpr2024_videomac_25232,
  title = {{VideoMAC: Video Masked Autoencoders Meet ConvNets}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31674},
}

@inproceedings{cvpr2024_pnerv_24414,
  title = {{PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29253},
}

@inproceedings{cvpr2024_mart_24054,
  title = {{MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29702},
}

@inproceedings{aaai2024_cread_5360,
  title = {{CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28752},
}

@inproceedings{aaai2024_mrmlrec_6588,
  title = {{MRMLREC: A Two-Stage Approach for Addressing Data Sparsity in MOOC Video Recommendation (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30536},
}

@inproceedings{aaai2024_no_6778,
  title = {{No More Shortcuts: Realizing the Potential of Temporal Self-Supervision}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27913},
}

@inproceedings{cvpr2025_autossvh_25537,
  title = {{AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34747},
}

@inproceedings{cvpr2025_smile_27531,
  title = {{SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34037},
}

@inproceedings{aaai2024_knowledge_6383,
  title = {{Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28221},
}

@inproceedings{aaai2025_efficient_8920,
  title = {{Efficient Self-Supervised Video Hashing with Selective State Spaces}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32835},
}

@inproceedings{cvpr2025_when_28154,
  title = {{When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34769},
}

@inproceedings{aaai2024_collaborative_5420,
  title = {{Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27983},
}

@inproceedings{cvpr2024_weakly_25273,
  title = {{Weakly Supervised Video Individual Counting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29221},
}

@inproceedings{cvpr2024_weakly_25274,
  title = {{Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29605},
}

@inproceedings{neurips2024_cross_72069,
  title = {{Cross-video Identity Correlating for Person Re-identification Pre-training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95254},
}

@inproceedings{icml2024_everest_45346,
  title = {{EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33105},
}

@inproceedings{neurips2025_ai_76667,
  title = {{AI-Generated Video Detection via Perceptual Straightening}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=LsmUgStXby},
}