% Key papers for Video-language pretraining (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_msr_11690,
  title = {{MSR-VTT: A Large Video Description Dataset for Bridging Video and Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_less_17340,
  title = {{Less Is More: ClipBERT for Video-and-Language Learning via Sparse Sampling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_actbert_15105,
  title = {{ActBERT: Learning Global-Local Video-Text Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_learning_103121,
  title = {{Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6431},
}

@inproceedings{cvpr2017_end_12241,
  title = {{End-To-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2023_fine_21002,
  title = {{Fine-Tuned CLIP Models Are Efficient Video Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22851},
}

@inproceedings{cvpr2023_learning_21415,
  title = {{Learning Video Representations From Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22945},
}

@inproceedings{cvpr2023_all_20380,
  title = {{All in One: Exploring Unified Video-Language Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22225},
}

@inproceedings{cvpr2022_advancing_18268,
  title = {{Advancing High-Resolution Video-Language Representation With Large-Scale Video Transcriptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_panda_24430,
  title = {{Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29577},
}

@inproceedings{neurips2020_coot_59496,
  title = {{COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17953},
}

@inproceedings{cvpr2023_revisiting_22063,
  title = {{Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22725},
}

@inproceedings{cvpr2023_video_22520,
  title = {{Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22354},
}

@inproceedings{cvpr2022_object_19486,
  title = {{Object-Aware Video-Language Pre-Training for Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_vindlu_22526,
  title = {{VindLU: A Recipe for Effective Video-and-Language Pretraining}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22817},
}

@inproceedings{cvpr2020_visual_16461,
  title = {{Visual-Textual Capsule Routing for Text-Based Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_an_20387,
  title = {{An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22798},
}

@inproceedings{neurips2022_language_65329,
  title = {{Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53904},
}

@inproceedings{neurips2022_egocentric_65938,
  title = {{Egocentric Video-Language Pretraining}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54579},
}

@inproceedings{neurips2021_value_61507,
  title = {{VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=9E3dTIMxL8S},
}

@inproceedings{iclr2024_internvid_34246,
  title = {{InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18829},
}

@inproceedings{cvpr2024_victr_25213,
  title = {{VicTR: Video-conditioned Text Representations for Activity Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29654},
}

@inproceedings{cvpr2024_a_22657,
  title = {{A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30266},
}

@inproceedings{cvpr2024_tri_25087,
  title = {{Tri-Modal Motion Retrieval by Learning a Joint Embedding Space}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30571},
}

@inproceedings{cvpr2024_distilling_23237,
  title = {{Distilling Vision-Language Models on Millions of Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30028},
}

@inproceedings{cvpr2024_enhanced_23367,
  title = {{Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29755},
}

@inproceedings{cvpr2024_vidla_25214,
  title = {{VidLA: Video-Language Alignment at Scale}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30730},
}

@inproceedings{aaai2024_multi_6680,
  title = {{MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28448},
}

@inproceedings{aaai2024_stitching_7417,
  title = {{Stitching Segments and Sentences towards Generalization in Video-Text Pre-training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28202},
}

@inproceedings{cvpr2024_detours_23161,
  title = {{Detours for Navigating Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31370},
}

@inproceedings{cvpr2024_videocon_25227,
  title = {{VideoCon: Robust Video-Language Alignment via Contrast Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31448},
}

@inproceedings{aaai2024_read_7050,
  title = {{READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29847},
}

@inproceedings{cvpr2025_efficient_26101,
  title = {{Efficient Transfer Learning for Video-language Foundation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34228},
}

@inproceedings{cvpr2025_videocomp_28093,
  title = {{VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32712},
}

@inproceedings{iclr2024_multi_33772,
  title = {{Multi-granularity Correspondence Learning from Long-term Noisy Videos}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19303},
}

@inproceedings{aaai2025_text_10957,
  title = {{Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32112},
}

@inproceedings{cvpr2024_srtube_24728,
  title = {{SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29914},
}

@inproceedings{aaai2026_vtd_105652,
  title = {{VTD-CLIP: Video-to-Text Discretization via Prompting CLIP}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38408},
}

@inproceedings{cvpr2025_dtos_25844,
  title = {{DTOS: Dynamic Time Object Sensing with Large Multimodal Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32970},
}