T2V.bib

@String(ICLR  = {ICLR})
@String(ICML  = {ICML})
@String(NIPS  = {NeurIPS})
@String(CVPR  = {CVPR})
@String(ICCV  = {ICCV})
@String(ECCV  = {ECCV})
@String(IJCV  = {IJCV})

% methods
@article{wu2021godiva,
    title={{GODIVA}: Generating Open-DomaIn Videos from nAtural Descriptions},
    author={Wu, Chenfei and Huang, Lun and Zhang, Qianxi and Li, Binyang and Ji, Lei and Yang, Fan and Sapiro, Guillermo and Duan, Nan},
    journal={arXiv preprint arXiv:2104.14806},
    year={2021}
}

@inproceedings{wu2022nuwa,
    title={{N{\"U}WA}: Visual Synthesis Pre-training for Neural visUal World creAtion},
    author={Wu, Chenfei and Liang, Jian and Ji, Lei and Yang, Fan and Fang, Yuejian and Jiang, Daxin and Duan, Nan},
    booktitle=ECCV,
    pages={720--736},
    year={2022}
}

@inproceedings{ho2022video,
    title={Video Diffusion Models}, 
    author={Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David J},
    booktitle=NIPS,
    pages={8633--8646},
    year={2022},
}

@article{ho2022imagen,
    title={Imagen Video: High Definition Video Generation with Diffusion Models},
    author={Ho, Jonathan and Chan, William and Saharia, Chitwan and Whang, Jay and Gao, Ruiqi and Gritsenko, Alexey and Kingma, Diederik P and Poole, Ben and Norouzi, Mohammad and Fleet, David J and others},
    journal={arXiv preprint arXiv:2210.02303},
    year={2022}
}

@article{zhou2022magicvideo,
    title={{MagicVideo}: Efficient Video Generation With Latent Diffusion Models},
    author={Zhou, Daquan and Wang, Weimin and Yan, Hanshu and Lv, Weiwei and Zhu, Yizhe and Feng, Jiashi},
    journal={arXiv preprint arXiv:2211.11018},
    year={2022}
}

%% LVDM
@article{he2023latent,
    title={Latent Video Diffusion Models for High-Fidelity Long Video Generation},
    author={He, Yingqing and Yang, Tianyu and Zhang, Yong and Shan, Ying and Chen, Qifeng},
    journal={arXiv preprint arXiv:2211.13221},
    year={2023}
}

@inproceedings{singer2023make,
    title={{Make-A-Video}: Text-to-Video Generation without Text-Video Data},
    author={Singer, Uriel and Polyak, Adam and Hayes, Thomas and Yin, Xi and An, Jie and Zhang, Songyang and Hu, Qiyuan and Yang, Harry and Ashual, Oron and Gafni, Oran and others},
    booktitle=ICLR,
    year={2023}
}

@inproceedings{villegas2023phenaki,
    title={Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions},
    author={Villegas, Ruben and Babaeizadeh, Mohammad and Kindermans, Pieter-Jan and Moraldo, Hernan and Zhang, Han and Saffar, Mohammad Taghi and Castro, Santiago and Kunze, Julius and Erhan, Dumitru},
    booktitle=ICLR,
    year={2023}
}

@inproceedings{hong2023cogvideo,
    title={{CogVideo}: Large-scale Pretraining for Text-to-Video Generation via Transformers},
    author={Hong, Wenyi and Ding, Ming and Zheng, Wendi and Liu, Xinghan and Tang, Jie},
    booktitle=ICLR,
    year={2023}
}

%% Video LDM
@inproceedings{blattmann2023align,
    title={Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models},
    author={Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten},
    booktitle=CVPR,
    pages={22563--22575},
    year={2023}
}

%% Gen1
@inproceedings{esser2023structure,
    title={Structure and Content-Guided Video Synthesis with Diffusion Models},
    author={Esser, Patrick and Chiu, Johnathan and Atighehchian, Parmida and Granskog, Jonathan and Germanidis, Anastasis},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={7346--7356},
    year={2023}
}

%% PYoCo
@inproceedings{ge2023preserve,
    title={Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models},
    author={Ge, Songwei and Nah, Seungjun and Liu, Guilin and Poon, Tyler and Tao, Andrew and Catanzaro, Bryan and Jacobs, David and Huang, Jia-Bin and Liu, Ming-Yu and Balaji, Yogesh},
    booktitle=ICCV,
    pages={22930--22941},
    year={2023}
}

@inproceedings{wang2023videocomposer,
    title={{VideoComposer}: Compositional Video Synthesis with Motion Controllability},
    author={Wang, Xiang and Yuan, Hangjie and Zhang, Shiwei and Chen, Dayou and Wang, Jiuniu and Zhang, Yingya and Shen, Yujun and Zhao, Deli and Zhou, Jingren},
    booktitle=NIPS,
    year={2023}
}

@inproceedings{sun2023glober,
    title={{GLOBER}: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER},
    author={Sun, Mingzhen and Wang, Weining and Qin, Zihan and Sun, Jiahui and Chen, Sihan and Liu, Jing},
    booktitle=NIPS,
    year={2023}
}

@article{luo2023videofusion,
    title={{VideoFusion}: Decomposed Diffusion Models for High-Quality Video Generation},
    author={Luo, Zhengxiong and Chen, Dayou and Zhang, Yingya and Huang, Yan and Wang, Liang and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Tan, Tieniu},
    journal={arXiv preprint arXiv:2303.08320},
    year={2023}
}

@article{an2023latent,
    title={{Latent-Shift}: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation},
    author={An, Jie and Zhang, Songyang and Yang, Harry and Gupta, Sonal and Huang, Jia-Bin and Luo, Jiebo and Yin, Xi},
    journal={arXiv preprint arXiv:2304.08477},
    year={2023}
}

@article{wang2023videofactory,
    title={{VideoFactory}: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation},
    author={Wang, Wenjing and Yang, Huan and Tuo, Zixi and He, Huiguo and Zhu, Junchen and Fu, Jianlong and Liu, Jiaying},
    journal={arXiv preprint arXiv:2305.10874},
    year={2023}
}

@article{xing2023make,
    title={{Make-Your-Video}: Customized Video Generation Using Textual and Structural Guidance},
    author={Xing, Jinbo and Xia, Menghan and Liu, Yuxin and Zhang, Yuechen and Zhang, Yong and He, Yingqing and Liu, Hanyuan and Chen, Haoxin and Cun, Xiaodong and Wang, Xintao and others},
    journal={arXiv preprint arXiv:2306.00943},
    year={2023}
}

@article{he2023animate,
    title={{Animate-A-Story}: Storytelling with Retrieval-Augmented Video Generation},
    author={He, Yingqing and Xia, Menghan and Chen, Haoxin and Cun, Xiaodong and Gong, Yuan and Xing, Jinbo and Zhang, Yong and Wang, Xintao and Weng, Chao and Shan, Ying and others},
    journal={arXiv preprint arXiv:2307.06940},
    year={2023}
}

@article{wang2023internvid,
    title={{InternVid}: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation},
    author={Wang, Yi and He, Yinan and Li, Yizhuo and Li, Kunchang and Yu, Jiashuo and Ma, Xin and Chen, Xinyuan and Wang, Yaohui and Luo, Ping and Liu, Ziwei and others},
    journal={arXiv preprint arXiv:2307.06942},
    year={2023}
}

@article{wang2023modelscope,
    title={{ModelScope} Text-to-Video Technical Report},
    author={Wang, Jiuniu and Yuan, Hangjie and Chen, Dayou and Zhang, Yingya and Wang, Xiang and Zhang, Shiwei},
    journal={arXiv preprint arXiv:2308.06571},
    year={2023}
}

%% Dysen-VDM
@article{fei2023empowering,
    title={Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models},
    author={Fei, Hao and Wu, Shengqiong and Ji, Wei and Zhang, Hanwang and Chua, Tat-Seng},
    journal={arXiv preprint arXiv:2308.13812},
    year={2023}
}

%% VidRD
@article{gu2023reuse,
    title={Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation},
    author={Gu, Jiaxi and Wang, Shicong and Zhao, Haoyu and Lu, Tianyi and Zhang, Xing and Wu, Zuxuan and Xu, Songcen and Zhang, Wei and Jiang, Yu-Gang and Xu, Hang},
    journal={arXiv preprint arXiv:2309.03549},
    year={2023}
}

@article{wang2023lavie,
    title={{LAVIE}: High-Quality Video Generation with Cascaded Latent Diffusion Models},
    author={Wang, Yaohui and Chen, Xinyuan and Ma, Xin and Zhou, Shangchen and Huang, Ziqi and Wang, Yi and Yang, Ceyuan and He, Yinan and Yu, Jiashuo and Yang, Peiqing and others},
    journal={arXiv preprint arXiv:2309.15103},
    year={2023}
}

@article{zhang2023show,
    title={Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation},
    author={Zhang, David Junhao and Wu, Jay Zhangjie and Liu, Jia-Wei and Zhao, Rui and Ran, Lingmin and Gu, Yuchao and Gao, Difei and Shou, Mike Zheng},
    journal={arXiv preprint arXiv:2309.15818},
    year={2023}
}

@article{chen2023videocrafter1,
    title={{VideoCrafter1}: Open Diffusion Models for High-Quality Video Generation},
    author={Chen, Haoxin and Xia, Menghan and He, Yingqing and Zhang, Yong and Cun, Xiaodong and Yang, Shaoshu and Xing, Jinbo and Liu, Yaofang and Chen, Qifeng and Wang, Xintao and others},
    journal={arXiv preprint arXiv:2310.19512},
    year={2023}
}

@article{girdhar2023emu,
    title={Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning},
    author={Girdhar, Rohit and Singh, Mannat and Brown, Andrew and Duval, Quentin and Azadi, Samaneh and Rambhatla, Sai Saketh and Shah, Akbar and Yin, Xi and Parikh, Devi and Misra, Ishan},
    journal={arXiv preprint arXiv:2311.10709},
    year={2023}
}

@article{blattmann2023stable,
    title={Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets},
    author={Blattmann, Andreas and Dockhorn, Tim and Kulal, Sumith and Mendelevitch, Daniel and Kilian, Maciej and Lorenz, Dominik and Levi, Yam and English, Zion and Voleti, Vikram and Letts, Adam and others},
    journal={arXiv preprint arXiv:2311.15127},
    year={2023}
}

%% PixelDance
@article{zeng2023make,
    title={Make Pixels Dance: High-Dynamic Video Generation},
    author={Zeng, Yan and Wei, Guoqiang and Zheng, Jiani and Zou, Jiaxin and Wei, Yang and Zhang, Yuchen and Li, Hang},
    journal={arXiv preprint arXiv:2311.10982},
    year={2023}
}

@article{kondratyuk2023videopoet,
    title={{VideoPoet}: A Large Language Model for Zero-Shot Video Generation},
    author={Kondratyuk, Dan and Yu, Lijun and Gu, Xiuye and Lezama, Jos{\'e} and Huang, Jonathan and Hornung, Rachel and Adam, Hartwig and Akbari, Hassan and Alon, Yair and Birodkar, Vighnesh and others},
    journal={arXiv preprint arXiv:2312.14125},
    year={2023}
}

% datasets
%% UCF-101
@article{soomro2012dataset,
    title={A Dataset of 101 Human Action Classes From Videos in the Wild},
    author={Soomro, Khurram and Zamir, Amir Roshan and Shah, Mubarak},
    journal={Center for Research in Computer Vision},
    volume={2},
    number={11},
    year={2012}
}

@inproceedings{xu2016msr,
    title={{MSR-VTT}: A Large Video Description Dataset for Bridging Video and Language},
    author={Xu, Jun and Mei, Tao and Yao, Ting and Rui, Yong},
    booktitle=CVPR,
    pages={5288--5296},
    year={2016}
}

@article{kay2017kinetics,
    title={The {Kinetics} Human Action Video Dataset},
    author={Kay, Will and Carreira, Joao and Simonyan, Karen and Zhang, Brian and Hillier, Chloe and Vijayanarasimhan, Sudheendra and Viola, Fabio and Green, Tim and Back, Trevor and Natsev, Paul and others},
    journal={arXiv preprint arXiv:1705.06950},
    year={2017}
}

@inproceedings{miech2019howto100m,
    title={{HowTo100M}: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips},
    author={Miech, Antoine and Zhukov, Dimitri and Alayrac, Jean-Baptiste and Tapaswi, Makarand and Laptev, Ivan and Sivic, Josef},
    booktitle=ICCV,
    pages={2630--2640},
    year={2019}
}

%% WebVid-10M
@inproceedings{bain2021frozen,
    title={Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval},
    author={Bain, Max and Nagrani, Arsha and Varol, G{\"u}l and Zisserman, Andrew},
    booktitle=ICCV,
    pages={1728--1738},
    year={2021}
}

%% HD-VILA-100M
@inproceedings{xue2022advancing,
    title={Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions},
    author={Xue, Hongwei and Hang, Tiankai and Zeng, Yanhong and Sun, Yuchong and Liu, Bei and Yang, Huan and Fu, Jianlong and Guo, Baining},
    booktitle=CVPR,
    pages={5036--5045},
    year={2022}
}

article{wang2023internvid,
    title={{InternVid}: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation},
    author={Wang, Yi and He, Yinan and Li, Yizhuo and Li, Kunchang and Yu, Jiashuo and Ma, Xin and Chen, Xinyuan and Wang, Yaohui and Luo, Ping and Liu, Ziwei and others},
    journal={arXiv preprint arXiv:2307.06942},
    year={2023}
}

% metrics
%% FID
@inproceedings{heusel2017gans,
    title={{GAN}s Trained by a Two Time-Scale Update Rule Converge to a Local {Nash} Equilibrium},
    author={Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp},
    booktitle=NIPS,
    pages={6629--6640},
    year={2017}
}

%% FVD
@article{unterthiner2018towards,
    title={Towards Accurate Generative Models of Video: A New Metric \& Challenges},
    author={Unterthiner, Thomas and Van Steenkiste, Sjoerd and Kurach, Karol and Marinier, Raphael and Michalski, Marcin and Gelly, Sylvain},
    journal={arXiv preprint arXiv:1812.01717},
    year={2018}
}

%% IS
@article{saito2020train,
    title={Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal {GAN}},
    author={Saito, Masaki and Saito, Shunta and Koyama, Masanori and Kobayashi, Sosuke},
    journal=IJCV,
    volume={128},
    number={10-11},
    pages={2586--2606},
    year={2020}
}

%% CLIPSIM
article{wu2021godiva,
    title={{GODIVA}: Generating Open-DomaIn Videos from nAtural Descriptions},
    author={Wu, Chenfei and Huang, Lun and Zhang, Qianxi and Li, Binyang and Ji, Lei and Yang, Fan and Sapiro, Guillermo and Duan, Nan},
    journal={arXiv preprint arXiv:2104.14806},
    year={2021}
}