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

@inproceedings{cvpr2020_dense_15394,
  title = {{Dense Regression Network for Video Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_local_15847,
  title = {{Local-Global Video-Text Interactions for Temporal Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2019_semantic_58970,
  title = {{Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13290},
}

@inproceedings{cvpr2019_grounded_14265,
  title = {{Grounded Video Description}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2020_temporally_103790,
  title = {{Temporally Grounding Language Queries in Videos by Contextual Boundary-Aware Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6897},
}

@inproceedings{aaai2019_read_103458,
  title = {{Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4854},
}

@inproceedings{cvpr2021_interventional_17199,
  title = {{Interventional Video Grounding With Dual Contrastive Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_context_16742,
  title = {{Context-Aware Biaffine Localizing Network for Temporal Sentence Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2022_negative_2460,
  title = {{Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02613-negative-sample-matters-a-renaissance-of-metric-learning-for-temporal-grounding/},
}

@inproceedings{aaai2021_proposal_1206,
  title = {{Proposal-Free Video Grounding with Contextual Pyramid Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01902-proposal-free-video-grounding-with-contextual-pyramid-network/},
}

@inproceedings{cvpr2022_weakly_20208,
  title = {{Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2020_where_16494,
  title = {{Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2018_finding_13117,
  title = {{Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Finding_It_Weakly-Supervised_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_tubedetr_20097,
  title = {{TubeDETR: Spatio-Temporal Video Grounding With Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_mad_19285,
  title = {{MAD: A Scalable Dataset for Language Grounding in Videos From Movie Audio Descriptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_cascaded_16693,
  title = {{Cascaded Prediction Network via Segment Tree for Temporal Video Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2022_memory_2408,
  title = {{Memory-Guided Semantic Learning Network for Temporal Sentence Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/01665-memory-guided-semantic-learning-network-for-temporal-sentence-grounding/},
}

@inproceedings{cvpr2022_compositional_18488,
  title = {{Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_embracing_16941,
  title = {{Embracing Uncertainty: Decoupling and De-Bias for Robust Temporal Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_not_14581,
  title = {{Not All Frames Are Equal: Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2024_snag_24846,
  title = {{SnAG: Scalable and Accurate Video Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31102},
}

@inproceedings{aaai2024_bias_5294,
  title = {{Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28252},
}

@inproceedings{aaai2024_gaussian_6103,
  title = {{Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28059},
}

@inproceedings{cvpr2025_number_27089,
  title = {{Number it: Temporal Grounding Videos like Flipping Manga}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33164},
}

@inproceedings{aaai2024_local_6540,
  title = {{Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27831},
}

@inproceedings{cvpr2024_context_23025,
  title = {{Context-Guided Spatio-Temporal Video Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30828},
}

@inproceedings{cvpr2025_videoglamm_28098,
  title = {{VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33544},
}

@inproceedings{cvpr2024_videogrounding_25230,
  title = {{VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29844},
}

@inproceedings{aaai2024_exploiting_5903,
  title = {{Exploiting Auxiliary Caption for Video Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29812},
}

@inproceedings{cvpr2024_siamese_24817,
  title = {{Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29499},
}

@inproceedings{cvpr2025_decafnet_25862,
  title = {{DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32761},
}

@inproceedings{aaai2025_diversifying_8782,
  title = {{Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32766},
}

@inproceedings{aaai2024_comprehensive_5453,
  title = {{Comprehensive Visual Grounding for Video Description}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28032},
}

@inproceedings{aaai2025_multi_10030,
  title = {{Multi-Scale Contrastive Learning for Video Temporal Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32666},
}

@inproceedings{cvpr2025_revisionllm_27391,
  title = {{ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32795},
}

@inproceedings{aaai2025_multi_10026,
  title = {{Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32298},
}

@inproceedings{cvpr2025_stpro_27555,
  title = {{STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33976},
}

@inproceedings{aaai2024_costa_5410,
  title = {{CoSTA: End-to-End Comprehensive Space-Time Entanglement for Spatio-Temporal Video Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28118},
}

@inproceedings{cvpr2025_object_27108,
  title = {{Object-Shot Enhanced Grounding Network for Egocentric Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33418},
}

@inproceedings{neurips2024_temporal_73157,
  title = {{Temporal Sentence Grounding with Relevance Feedback in Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94274},
}