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

@inproceedings{cvpr2017_lip_12435,
  title = {{Lip Reading Sentences in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_end_13071,
  title = {{End-to-End Dense Video Captioning With Masked Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_End-to-End_Dense_Video_CVPR_2018_paper.html},
}

@inproceedings{aaai2020_learning_103877,
  title = {{Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6984},
}

@inproceedings{aaai2019_to_103551,
  title = {{To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4950},
}

@inproceedings{cvpr2023_vid2seq_22514,
  title = {{Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23232},
}

@inproceedings{cvpr2018_bidirectional_12867,
  title = {{Bidirectional Attentive Fusion With Context Gating for Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Bidirectional_Attentive_Fusion_CVPR_2018_paper.html},
}

@inproceedings{cvpr2017_tracking_12704,
  title = {{Tracking by Natural Language Specification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_jointly_13244,
  title = {{Jointly Localizing and Describing Events for Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Li_Jointly_Localizing_and_CVPR_2018_paper.html},
}

@inproceedings{aaai2020_rethinking_103591,
  title = {{Rethinking the Bottom-Up Framework for Query-Based Video Localization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6627},
}

@inproceedings{aaai2020_weakly_103713,
  title = {{Weakly-Supervised Video Moment Retrieval via Semantic Completion Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6820},
}

@inproceedings{aaai2021_boundary_208,
  title = {{Boundary Proposal Network for Two-stage Natural Language Video Localization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02986-boundary-proposal-network-for-two-stage-natural-language-video-localization/},
}

@inproceedings{cvpr2019_streamlined_14874,
  title = {{Streamlined Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2017_query_12559,
  title = {{Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2018_video_100333,
  title = {{Video Summarization via Semantic Attended Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11297},
}

@inproceedings{cvpr2017_weakly_12752,
  title = {{Weakly Supervised Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2024_vtimellm_25199,
  title = {{VTimeLLM: Empower LLM to Grasp Video Moments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31139},
}

@inproceedings{aaai2019_localizing_103431,
  title = {{Localizing Natural Language in Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4827},
}

@inproceedings{aaai2022_weakly_2945,
  title = {{Weakly Supervised Video Moment Localization with Contrastive Negative Sample Mining}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03517-weakly-supervised-video-moment-localization-with-contrastive-negative-sample-mining/},
}

@inproceedings{cvpr2021_structured_17952,
  title = {{Structured Multi-Level Interaction Network for Video Moment Localization via Language Query}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_multi_17449,
  title = {{Multi-Stage Aggregated Transformer Network for Temporal Language Localization in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2024_streaming_24895,
  title = {{Streaming Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31433},
}

@inproceedings{cvpr2024_do_23246,
  title = {{Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31661},
}

@inproceedings{cvpr2024_dibs_23084,
  title = {{DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31019},
}

@inproceedings{aaai2025_dense_8691,
  title = {{Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33185},
}

@inproceedings{cvpr2025_seq2time_27643,
  title = {{Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34923},
}

@inproceedings{aaai2025_hicm_9424,
  title = {{HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32451},
}

@inproceedings{cvpr2025_event_26167,
  title = {{Event-Equalized Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34080},
}

@inproceedings{aaai2024_commonsense_5433,
  title = {{Commonsense for Zero-Shot Natural Language Video Localization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27989},
}

@inproceedings{aaai2025_cardiff_8374,
  title = {{CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32785},
}

@inproceedings{aaai2025_exploring_9081,
  title = {{Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32948},
}

@inproceedings{cvpr2024_learning_23989,
  title = {{Learning to Segment Referred Objects from Narrated Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29467},
}

@inproceedings{aaai2025_boundary_8294,
  title = {{Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32276},
}

@inproceedings{aaai2025_implicit_9512,
  title = {{Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32320},
}

@inproceedings{aaai2025_vidchain_11238,
  title = {{VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32474},
}

@inproceedings{cvpr2025_relocate_27355,
  title = {{RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32703},
}

@inproceedings{icml2026_timechat_52171,
  title = {{TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=TL787dxmIM},
}

@inproceedings{cvpr2026_stay_97539,
  title = {{Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Baek_Stay_in_your_Lane_Role_Specific_Queries_with_Overlap_Suppression_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_follow_97660,
  title = {{Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Choi_Follow_the_Saliency_Supervised_Saliency_for_Retrieval-augmented_Dense_Video_Captioning_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_sail_99015,
  title = {{SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Kim_SAIL_Similarity-Aware_Guidance_and_Inter-Caption_Augmentation-based_Learning_for_Weakly-Supervised_Dense_CVPR_2026_paper.html},
}