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

@inproceedings{aaai2019_multilevel_103539,
  title = {{Multilevel Language and Vision Integration for Text-to-Clip Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4938},
}

@inproceedings{cvpr2019_dual_14116,
  title = {{Dual Encoding for Zero-Example Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_x_20230,
  title = {{X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_cap4video_20566,
  title = {{Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22386},
}

@inproceedings{cvpr2022_bridging_18395,
  title = {{Bridging Video-Text Retrieval With Multiple Choice Questions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2017_collaborative_12112,
  title = {{Collaborative Summarization of Topic-Related Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2024_text_24982,
  title = {{Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31715},
}

@inproceedings{cvpr2023_vop_22550,
  title = {{VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22906},
}

@inproceedings{aaai2024_covr_5411,
  title = {{CoVR: Learning Composed Video Retrieval from Web Video Captions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28334},
}

@inproceedings{cvpr2022_sign_19874,
  title = {{Sign Language Video Retrieval With Free-Form Textual Queries}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_holistic_23707,
  title = {{Holistic Features are almost Sufficient for Text-to-Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29177},
}

@inproceedings{cvpr2024_retrieval_24645,
  title = {{Retrieval-Augmented Egocentric Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31318},
}

@inproceedings{cvpr2024_mv_24089,
  title = {{MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31670},
}

@inproceedings{aaai2022_visual_2938,
  title = {{Visual Consensus Modeling for Video-Text Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00167-visual-consensus-modeling-for-video-text-retrieval/},
}

@inproceedings{aaai2024_towards_7591,
  title = {{Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28327},
}

@inproceedings{aaai2020_a_103834,
  title = {{A Proposal-Based Approach for Activity Image-to-Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6941},
}

@inproceedings{aaai2024_gmmformer_6089,
  title = {{GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28389},
}

@inproceedings{cvpr2020_large_15736,
  title = {{Large Scale Video Representation Learning via Relational Graph Clustering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_composed_23004,
  title = {{Composed Video Retrieval via Enriched Context and Discriminative Embeddings}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30088},
}

@inproceedings{cvpr2023_towards_22378,
  title = {{Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21259},
}

@inproceedings{cvpr2025_learning_26736,
  title = {{Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32395},
}

@inproceedings{cvpr2025_narrating_27051,
  title = {{Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32652},
}

@inproceedings{cvpr2025_video_28087,
  title = {{Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33381},
}

@inproceedings{aaai2025_muse_9884,
  title = {{MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32778},
}

@inproceedings{aaai2024_vvs_7752,
  title = {{VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28046},
}

@inproceedings{aaai2025_text_10953,
  title = {{Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32935},
}

@inproceedings{neurips2024_diffusion_72273,
  title = {{Diffusion-Inspired Truncated Sampler for Text-Video Retrieval}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95072},
}

@inproceedings{aaai2026_retrack_107155,
  title = {{ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39507},
}

@inproceedings{aaai2025_bridging_8318,
  title = {{Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32437},
}

@inproceedings{aaai2025_ambiguity_8094,
  title = {{Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32252},
}

@inproceedings{cvpr2025_rethinking_27445,
  title = {{Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32598},
}

@inproceedings{aaai2025_learning_9730,
  title = {{Learning Dynamic Similarity by Bidirectional Hierarchical Sliding Semantic Probe for Efficient Text Video Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32604},
}