@inproceedings{bb103900,
AUTHOR = "Fu, T.J. and Wang, X.E. and Grafton, S.T. and Eckstein, M.P. and Wang, W.Y.",
TITLE = "M3L: Language-based Video Editing via Multi-Modal Multi-Level
Transformers",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10503-10512",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100608"}
@inproceedings{bb103901,
AUTHOR = "Ardino, P. and de Nadai, M. and Lepri, B. and Ricci, E. and Lathuiliere, S.",
TITLE = "Click to Move: Controlling Video Generation with Sparse Motion",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14729-14738",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100609"}
@inproceedings{bb103902,
AUTHOR = "Kumar, B.G.V. and Subramanian, J. and Chordia, V. and Bart, E. and Fang, S.B. and Guan, K. and Bala, R.",
TITLE = "STRIVE: Scene Text Replacement In Videos",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "14529-14538",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100610"}
@inproceedings{bb103903,
AUTHOR = "Koorathota, S. and Adelman, P. and Cotton, K. and Sajda, P.",
TITLE = "Editing like Humans: A Contextual, Multimodal Framework for Automated
Video Editing",
BOOKTITLE = MULA21,
YEAR = "2021",
PAGES = "1701-1709",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100611"}
@inproceedings{bb103904,
AUTHOR = "Bermudez, L. and Dabby, N. and Lin, Y.X.A. and Hilmarsdottir, S. and Sundararajan, N. and Kar, S.",
TITLE = "A Learning-Based Approach to Parametric Rotoscoping of Multi-Shape
Systems",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "776-785",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100612"}
@inproceedings{bb103905,
AUTHOR = "Tripathi, S. and Chandra, S. and Agrawal, A. and Tyagi, A. and Rehg, J.M. and Chari, V.",
TITLE = "Learning to Generate Synthetic Data via Compositing",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "461-470",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100613"}
@inproceedings{bb103906,
AUTHOR = "Meyer, S. and Sorkine Hornung, A. and Gross, M.",
TITLE = "Phase-Based Modification Transfer for Video",
BOOKTITLE = ECCV16,
YEAR = "2016",
PAGES = "III: 633-648",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100614"}
@inproceedings{bb103907,
AUTHOR = "Taylor, W. and Qureshi, F.Z.",
TITLE = "Automatic video editing for sensor-rich videos",
BOOKTITLE = WACV16,
YEAR = "2016",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100615"}
@inproceedings{bb103908,
AUTHOR = "Manickam, N. and Chandran, S.",
TITLE = "Automontage: Photo sessions made easy",
BOOKTITLE = ICIP13,
YEAR = "2013",
PAGES = "1321-1325",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100616"}
@inproceedings{bb103909,
AUTHOR = "Chen, J.W. and Paris, S. and Wang, J. and Matusik, W. and Cohen, M. and Durand, F.",
TITLE = "The video mesh: A data structure for image-based three-dimensional
video editing",
BOOKTITLE = ICCP11,
YEAR = "2011",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100617"}
@inproceedings{bb103910,
AUTHOR = "Durand, F. and Cohen, M. and Chen, J.W. and Paris, S. and Wang, J. and Matusik, W.",
TITLE = "The Video Mesh: A Data Structure for Image-based Video Editing",
BOOKTITLE = CSAIL,
YEAR = "2009",
PAGES = "TR-2009-062",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100618"}
@inproceedings{bb103911,
AUTHOR = "Rajgopalan, V. and Ranganathan, A. and Rajagopalan, R. and Mudur, S.P.",
TITLE = "Keyframe-Guided Automatic Non-linear Video Editing",
BOOKTITLE = ICPR10,
YEAR = "2010",
PAGES = "3236-3239",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100619"}
@inproceedings{bb103912,
AUTHOR = "Yoshitaka, A. and Deguchi, Y.",
TITLE = "Rendition-based video editing for public contents authoring",
BOOKTITLE = ICIP09,
YEAR = "2009",
PAGES = "1825-1828",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100620"}
@inproceedings{bb103913,
AUTHOR = "Slot, K. and Truelsen, R. and Sporring, J.",
TITLE = "Content-Aware Video Editing in the Temporal Domain",
BOOKTITLE = SCIA09,
YEAR = "2009",
PAGES = "490-499",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100621"}
@inproceedings{bb103914,
AUTHOR = "Wang, H.C. and Xu, N. and Raskar, R. and Ahuja, N.",
TITLE = "Videoshop: A New Framework for Spatio-Temporal Video Editing in
Gradient Domain",
BOOKTITLE = CVPR05,
YEAR = "2005",
PAGES = "II: 1201",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100622"}
@inproceedings{bb103915,
AUTHOR = "Wang, H.C. and Raskar, R. and Ahuja, N.",
TITLE = "Seamless video editing",
BOOKTITLE = ICPR04,
YEAR = "2004",
PAGES = "III: 858-861",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100623"}
@inproceedings{bb103916,
AUTHOR = "Kumano, M. and Ariki, Y. and Amano, M. and Uehara, K. and Shunto, K. and Tsukada, K.",
TITLE = "Video editing support system based on video grammar and content
analysis",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 1031-1036",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ve1.html#TT100624"}
@article{bb103917,
AUTHOR = "Zhang, J. and Mei, K.Z. and Zheng, Y. and Fan, J.P.",
TITLE = "Exploiting Mid-Level Semantics for Large-Scale Complex Video
Classification",
JOURNAL = MultMed,
VOLUME = "21",
YEAR = "2019",
NUMBER = "10",
MONTH = "October",
PAGES = "2518-2530",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100625"}
@inproceedings{bb103918,
AUTHOR = "Zhang, J. and Mei, K.Z. and Wang, X. and Zheng, Y. and Fan, J.P.",
TITLE = "From Text to Video: Exploiting Mid-Level Semantics for Large-Scale
Video Classification",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "1695-1700",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100626"}
@article{bb103919,
AUTHOR = "Yang, M. and Liu, J.H. and Shen, Y. and Zhao, Z. and Chen, X.J. and Wu, Q.Y. and Li, C.M.",
TITLE = "An Ensemble of Generation- and Retrieval-Based Image Captioning With
Dual Generator Generative Adversarial Network",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
PAGES = "9627-9640",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100627"}
@article{bb103920,
AUTHOR = "Chen, Q. and Wu, Q. and Chen, J. and Wu, Q.Y. and van den Hengel, A.J. and Tan, M.K.",
TITLE = "Scripted Video Generation With a Bottom-Up Generative Adversarial
Network",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
PAGES = "7454-7467",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100628"}
@article{bb103921,
AUTHOR = "Sheng, L. and Pan, J.T. and Guo, J.M. and Shao, J. and Loy, C.C.",
TITLE = "High-Quality Video Generation from Static Structural Annotations",
JOURNAL = IJCV,
VOLUME = "128",
YEAR = "2020",
NUMBER = "10-11",
MONTH = "November",
PAGES = "2552-2569",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100629"}
@article{bb103922,
AUTHOR = "Sener, F. and Saraf, R. and Yao, A.",
TITLE = "Transferring Knowledge From Text to Video:
Zero-Shot Anticipation for Procedural Actions",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "7836-7852",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100630"}
@article{bb103923,
AUTHOR = "Liu, S.Y. and Dragotti, P.L.",
TITLE = "Sensing Diversity and Sparsity Models for Event Generation and Video
Reconstruction from Events",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "10",
MONTH = "October",
PAGES = "12444-12458",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100631"}
@article{bb103924,
AUTHOR = "Koksal, A. and Ak, K.E. and Sun, Y. and Rajan, D. and Lim, J.H.",
TITLE = "Controllable Video Generation With Text-Based Instructions",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "190-201",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100632"}
@article{bb103925,
AUTHOR = "Liu, J.W. and Wang, W.N. and Chen, S. and Zhu, X.X. and Liu, J.",
TITLE = "Sounding Video Generator: A Unified Framework for Text-Guided
Sounding Video Generation",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "141-153",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100633"}
@article{bb103926,
AUTHOR = "Hu, Y. and Luo, C. and Chen, Z.Z.",
TITLE = "A Benchmark for Controllable Text-Image-to-Video Generation",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1706-1719",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100634"}
@article{bb103927,
AUTHOR = "Fang, S. and Dang, T.T. and Wang, S.H. and Huang, Q.M.",
TITLE = "Linguistic Hallucination for Text-Based Video Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "9692-9705",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100635"}
@article{bb103928,
AUTHOR = "Nadeem, M. and Sohail, S.S. and Cambria, E. and Schuller, B.W. and Hussain, A.",
TITLE = "Gender Bias in Text-to-Video Generation Models: A Case Study of Sora",
JOURNAL = IEEE_Int_Sys,
VOLUME = "40",
YEAR = "2025",
NUMBER = "3",
MONTH = "May",
PAGES = "10-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100636"}
@article{bb103929,
AUTHOR = "Kuang, Q. and Chen, Y.",
TITLE = "Visual-Aware Text as Query for Referring Video Object Segmentation",
JOURNAL = IVC,
VOLUME = "161",
YEAR = "2025",
PAGES = "105608",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100637"}
@article{bb103930,
AUTHOR = "He, H.G. and Yang, H. and Tuo, Z.X. and Zhou, Y. and Wang, Q.Y. and Zhang, Y.H. and Liu, Z. and Huang, W.H. and Chao, H.Y. and Yin, J.",
TITLE = "DreamStory: Open-Domain Story Visualization by LLM-Guided
Multi-Subject Consistent Diffusion",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "11874-11891",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100638"}
@article{bb103931,
AUTHOR = "Wang, X.H. and Kang, Z.X. and Mu, Y.D.",
TITLE = "Text-Controlled Motion Mamba: Text-Instructed Temporal Grounding of
Human Motion",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "7079-7092",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100639"}
@article{bb103932,
AUTHOR = "Wang, F.M. and Wang, W.L. and Gao, D. and Huang, X. and Song, X.D. and Sun, H.Y. and Peng, C.",
TITLE = "A LLM-guided hybrid Mamba-Transformer architecture for part-to-whole
motion synthesis",
JOURNAL = CVIU,
VOLUME = "262",
YEAR = "2025",
PAGES = "104549",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100640"}
@article{bb103933,
AUTHOR = "Huang, Z.Q. and Zhang, F. and Xu, X.J. and He, Y. and Yu, J. and Dong, Z.Y. and Ma, Q.L. and Chanpaisit, N. and Si, C.Y. and Jiang, Y.M. and Wang, Y.H. and Chen, X.Y. and Chen, Y.C. and Wang, L.M. and Lin, D. and Qiao, Y. and Liu, Z.W.",
TITLE = "VBench++: Comprehensive and Versatile Benchmark Suite for Video
Generative Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "3268-3285",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100641"}
@inproceedings{bb103934,
AUTHOR = "Huang, Z.Q. and He, Y. and Yu, J. and Zhang, F. and Si, C.Y. and Jiang, Y.M. and Zhang, Y.H. and Wu, T.X. and Jin, Q.Y. and Chanpaisit, N. and Wang, Y.H. and Chen, X.Y. and Wang, L.M. and Lin, D. and Qiao, Y. and Liu, Z.W.",
TITLE = "VBench: Comprehensive Benchmark Suite for Video Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "21807-21818",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100642"}
@article{bb103935,
AUTHOR = "Chen, Y.H. and Li, H.R. and Jiang, Z.N. and Wen, H. and Zhao, D.B.",
TITLE = "TeViR: Text-to-Video Reward With Diffusion Models for Efficient
Reinforcement Learning",
JOURNAL = SMCS,
VOLUME = "56",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "893-905",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100643"}
@inproceedings{bb103936,
AUTHOR = "Nakanose, Y. and Nakagawa, C. and Inoue, K. and Yoshioka, M.",
TITLE = "Temporal Conditioning for Realistic Performance Video Generation from
Instrumental Sounds",
BOOKTITLE = MVA25,
YEAR = "2025",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100644"}
@inproceedings{bb103937,
AUTHOR = "Sun, C.Y. and Han, J.L. and Deng, W.J. and Wang, X.L. and Qin, Z.S. and Gould, S.",
TITLE = "3D-GPT: Procedural 3D Modeling with Large Language Models",
BOOKTITLE = "3DV25",
YEAR = "2025",
PAGES = "1253-1263",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100645"}
@inproceedings{bb103938,
AUTHOR = "Zhang, R. and Yu, B. and Min, J.J. and Xin, Y. and Wei, Z. and Shi, J.C.N. and Huang, M.Z. and Kong, X.H. and Xin, N.L. and Jiang, S.S. and Bahuguna, P. and Chan, M. and Hora, K. and Yang, L.J. and Liang, Y.Q. and Bian, R. and Liu, Y.L. and Valencia, I.C. and Tredinick, P.M. and Kozlov, I. and Jiang, S. and Huang, P. and Chen, N. and Liu, X. and Rao, A.",
TITLE = "Generative AI for Film Creation: A Survey of Recent Advances",
BOOKTITLE = AIConGen25,
YEAR = "2025",
PAGES = "6257-6269",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100646"}
@inproceedings{bb103939,
AUTHOR = "Li, A.",
TITLE = "Evaluating Text-to-Video Alignment: A Hierarchical Benchmark for
Video Generation Models",
BOOKTITLE = ICIVC25,
YEAR = "2025",
PAGES = "583-590",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100647"}
@inproceedings{bb103940,
AUTHOR = "Li, X.M. and Liu, Y.X. and Isobe, T. and Jia, X. and Cui, Q.P. and Zhou, D. and Li, D. and He, Y. and Lu, H.C. and Wang, Z.D. and Barsoum, E.",
TITLE = "ReNeg: Learning Negative Embedding with Reward Guidance",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23636-23645",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100648"}
@inproceedings{bb103941,
AUTHOR = "Deo, A. and Bhat, S. and Karande, S.",
TITLE = "VisualFusion: Enhancing Blog Content with Advanced Infographic
Pipeline",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5591-5600",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100649"}
@inproceedings{bb103942,
AUTHOR = "Shin, C. and Choi, J.Y. and Kim, H. and Yoon, S.",
TITLE = "Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot
Subject-Driven Image Generator",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7986-7996",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100650"}
@inproceedings{bb103943,
AUTHOR = "Liang, F. and Ma, H.Y. and He, Z.C. and Hou, T.B. and Hou, J. and Li, K.P. and Dai, X.L. and Juefei Xu, F. and Azadi, S. and Sinha, A. and Zhang, P.Z. and Vajda, P. and Marculescu, D.",
TITLE = "Movie Weaver: Tuning-Free Multi-Concept Video Personalization with
Anchored Prompts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13146-13156",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100651"}
@inproceedings{bb103944,
AUTHOR = "Nguyen, T. and Singh, K.K. and Shi, J. and Bui, T. and Lee, Y.J. and Li, Y.H.",
TITLE = "Yo'Chameleon: Personalized Vision and Language Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14438-14448",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100652"}
@inproceedings{bb103945,
AUTHOR = "Wang, H.L. and Ouyang, H. and Wang, Q.Y. and Wang, W. and Cheng, K.L. and Chen, Q.F. and Shen, Y.J. and Wang, L.M.",
TITLE = "LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12490-12500",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100653"}
@inproceedings{bb103946,
AUTHOR = "Lai, Z.H. and Vedaldi, A.",
TITLE = "Tracktention: Leveraging Point Tracking to Attend Videos Faster and
Better",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "22809-22819",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100654"}
@inproceedings{bb103947,
AUTHOR = "Ji, B. and Pan, Y. and Liu, Z.M. and Tan, S. and Jin, X.G. and Yang, X.K.",
TITLE = "POMP: Physics-constrainable Motion Generative Model through Phase
Manifolds",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "22690-22701",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100655"}
@inproceedings{bb103948,
AUTHOR = "Wang, Y.F. and Yang, P. and Xu, Z. and Sun, J.M. and Zhang, Z. and Chen, Y. and Bao, H.J. and Peng, S. and Zhou, X.W.",
TITLE = "FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic
Scene Reconstruction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "21750-21760",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100656"}
@inproceedings{bb103949,
AUTHOR = "Wang, S.J. and Azadi, S. and Girdhar, R. and Rambhatla, S. and Sun, C. and Yin, X.",
TITLE = "MotiF: Making Text Count in Image Animation with Motion Focal Loss",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7773-7783",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100657"}
@inproceedings{bb103950,
AUTHOR = "Bian, W. and Huang, Z.Y. and Shi, X.Y. and Li, Y.J. and Wang, F.Y. and Li, H.S.",
TITLE = "GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields
through Efficient Dense 3D Point Tracking",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "21717-21727",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100658"}
@inproceedings{bb103951,
AUTHOR = "Ren, X. and Shen, T. and Huang, J.H. and Ling, H. and Lu, Y.F. and Nimier David, M. and Muller, T. and Keller, A. and Fidler, S. and Gao, J.",
TITLE = "Gen3C: 3D-Informed World-Consistent Video Generation with Precise
Camera Control",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6121-6132",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100659"}
@inproceedings{bb103952,
AUTHOR = "Wang, X. and Courant, R. and Christie, M. and Kalogeiton, V.",
TITLE = "AKiRa: Augmentation Kit on Rays for optical video generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2609-2619",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100660"}
@inproceedings{bb103953,
AUTHOR = "Han, H.N. and Wu, X.Z. and Liao, H. and Xu, Z. and Hu, Z.Y. and Li, R.H. and Zhang, Y.C. and Li, X.",
TITLE = "AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision
Reward",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "22746-22755",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100661"}
@inproceedings{bb103954,
AUTHOR = "Wu, Y.S. and Zhang, Z.X. and Li, Y.Y. and Xu, Y. and Kag, A. and Sui, Y. and Coskun, H. and Ma, K. and Lebedev, A. and Hu, J. and Metaxas, D.N. and Wang, Y.Z. and Tulyakov, S. and Ren, J.",
TITLE = "SnapGen-V: Generating a Five-Second Video within Five Seconds on a
Mobile Device",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2479-2490",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100662"}
@inproceedings{bb103955,
AUTHOR = "Han, H. and Li, S.Y. and Chen, J.Q. and Yuan, Y.W. and Wu, Y.L. and Deng, Y.F. and Leong, C.T. and Du, H. and Fu, J.C. and Li, Y. and Zhang, J. and Zhang, C. and Li, L.J. and Ni, Y.X.",
TITLE = "Video-Bench: Human-Aligned Video Generation Benchmark",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18858-18868",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100663"}
@inproceedings{bb103956,
AUTHOR = "Shen, X.Q. and Elhoseiny, M.",
TITLE = "StoryGPT-V: Large Language Models as Consistent Story Visualizers",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13273-13283",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100664"}
@inproceedings{bb103957,
AUTHOR = "Chen, T.S. and Siarohin, A. and Menapace, W. and Fang, Y.W. and Lee, K.S. and Skorokhodov, I. and Aberman, K. and Zhu, J.Y. and Yang, M.H. and Tulyakov, S.",
TITLE = "Multi-subject Open-set Personalization in Video Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6099-6110",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100665"}
@inproceedings{bb103958,
AUTHOR = "Huang, Z.P. and Zhuang, S. and Fu, C. and Yang, B.X. and Zhang, Y. and Sun, C. and Zhang, Z.Z. and Wang, Y. and Li, C. and Zha, Z.J.",
TITLE = "WeGen: A Unified Model for Interactive Multimodal Generation as We
Chat",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23679-23689",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100666"}
@inproceedings{bb103959,
AUTHOR = "Su, T.T. and Wang, C.Y. and Liu, B.Y. and Huang, J. and Lu, D.M.",
TITLE = "Encapsulated Composition of Text-to-Image and Text-to-Video Models
for High-Quality Video Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18209-18218",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100667"}
@inproceedings{bb103960,
AUTHOR = "Wang, L.Z. and Li, Y.J. and Chen, Z.F. and Wang, J.H. and Zhang, Z.F. and Zhang, H. and Lin, Z. and Chen, Y.C.",
TITLE = "TransPixeler: Advancing Text-to-Video Generation with Transparency",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18229-18239",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100668"}
@inproceedings{bb103961,
AUTHOR = "Wang, J.R. and Duan, H.Y. and Zhai, G.T. and Wang, J.T. and Min, X.K.",
TITLE = "AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of
Text-to-Video Generation with LMM",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18869-18880",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100669"}
@inproceedings{bb103962,
AUTHOR = "Reddy, A. and Martin, A. and Yang, E. and Yates, A. and Sanders, K. and Murray, K. and Kriz, R. and de Melo, C.M. and van Durme, B. and Chellappa, R.",
TITLE = "Video-ColBERT: Contextualized Late Interaction for Text-to-Video
Retrieval",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19691-19701",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100670"}
@inproceedings{bb103963,
AUTHOR = "Zanella, L. and Mancini, M. and Menapace, W. and Tulyakov, S. and Wang, Y.M. and Ricci, E.",
TITLE = "Can Text-to-Video Generation help Video-Language Alignment?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24097-24107",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100671"}
@inproceedings{bb103964,
AUTHOR = "Fan, T. and Nan, K. and Xie, R. and Zhou, P.H. and Yang, Z. and Fu, C. and Li, X. and Yang, J. and Tai, Y.",
TITLE = "InstanceCap: Improving Text-to-Video Generation via Instance-aware
Structured Caption",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28974-28983",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100672"}
@inproceedings{bb103965,
AUTHOR = "Huang, Y.Y. and Chen, Y. and Ding, L. and Zhang, X.P. and Dai, W.R. and Zou, J. and Xiong, H.K. and Tian, Q.",
TITLE = "IM-Zero: Instance-level Motion Controllable Video Generation in a
Zero-shot Manner",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7265-7275",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100673"}
@inproceedings{bb103966,
AUTHOR = "Wang, Y.P. and He, X. and Wang, K. and Ma, L. and Yang, J.W. and Wang, S. and Du, S.S.L. and Shen, Y.",
TITLE = "Is Your World Simulator a Good Story Presenter? A Consecutive
Events-Based Benchmark for Future Long Video Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13629-13638",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100674"}
@inproceedings{bb103967,
AUTHOR = "Chen, S. and Ge, C.J. and Zhang, Y.Q. and Zhang, Y. and Zhu, F. and Yang, H. and Hao, H.X. and Wu, H. and Lai, Z.C. and Hu, Y.F. and Lin, T.C. and Zhang, S.L. and Li, F. and Li, C. and Wang, X. and Peng, Y.H. and Sun, P. and Luo, P. and Jiang, Y. and Yuan, Z.H. and Peng, B. and Liu, X.B.",
TITLE = "Goku: Flow Based Video Generative Foundation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23516-23527",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100675"}
@inproceedings{bb103968,
AUTHOR = "Wang, H.J. and Ma, C.Y. and Liu, Y.C. and Hou, J. and Xu, T. and Wang, J.L. and Juefei Xu, F. and Luo, Y.Q. and Zhang, P.Z. and Hou, T.B. and Vajda, P. and Jha, N.K. and Dai, X.L.",
TITLE = "LinGen: Towards High-Resolution Minute-Length Text-to-Video
Generation with Linear Computational Complexity",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2578-2588",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100676"}
@inproceedings{bb103969,
AUTHOR = "Gao, B.J. and Gao, X.Y. and Wu, X.X. and Zhou, Y.J. and Qiao, Y. and Niu, L. and Chen, X.Y. and Wang, Y.H.",
TITLE = "The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization
for Text-To-Video Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3173-3183",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100677"}
@inproceedings{bb103970,
AUTHOR = "Sharan, S.P. and Choi, M. and Shah, S. and Goel, H. and Omama, M. and Chinchali, S.",
TITLE = "Neuro-Symbolic Evaluation of Text-to-Video Models using Formal
Verification",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8395-8405",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100678"}
@inproceedings{bb103971,
AUTHOR = "Sun, K.Y. and Huang, K.Y. and Liu, X. and Wu, Y. and Xu, Z. and Li, Z.G. and Liu, X.H.",
TITLE = "T2V-CompBench: A Comprehensive Benchmark for Compositional
Text-to-video Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8406-8416",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100679"}
@inproceedings{bb103972,
AUTHOR = "Yuan, S.H. and Huang, J. and He, X. and Ge, Y. and Shi, Y.J. and Chen, L. and Luo, J.B. and Yuan, L.",
TITLE = "Identity-Preserving Text-To-Video Generation by Frequency
Decomposition",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12978-12988",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100680"}
@inproceedings{bb103973,
AUTHOR = "Bu, J. and Ling, P.Y. and Zhang, P. and Wu, T. and Dong, X.Y. and Zang, Y.H. and Cao, Y.H. and Lin, D. and Wang, J.Q.",
TITLE = "ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality
in a Training-free Way",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12999-13008",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100681"}
@inproceedings{bb103974,
AUTHOR = "Weng, S. and Zheng, H.J. and Zhang, P.X. and Hong, Y.C. and Jiang, H. and Li, S. and Shi, B.X.",
TITLE = "VIRES: Video Instance Repainting via Sketch and Text Guided
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28416-28425",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100682"}
@inproceedings{bb103975,
AUTHOR = "Huang, H.P. and Su, Y.C. and Sun, D.Q. and Jiang, L. and Jia, X.H. and Zhu, Y.K. and Yang, M.H.",
TITLE = "Fine-grained Controllable Video Generation via Object Appearance and
Context",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3698-3708",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100683"}
@inproceedings{bb103976,
AUTHOR = "Wu, W.J. and Li, Z. and Gu, Y.C. and Zhao, R. and He, Y.F. and Zhang, D.J.H. and Shou, M.Z. and Li, Y. and Gao, T.T. and Zhang, D.",
TITLE = "DragAnything: Motion Control for Anything Using Entity Representation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXII: 331-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100684"}
@inproceedings{bb103977,
AUTHOR = "Chen, X. and Liu, Z.H. and Chen, M.T. and Feng, Y.T. and Liu, Y. and Shen, Y.J. and Zhao, H.S.",
TITLE = "Livephoto: Real Image Animation with Text-guided Motion Control",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVIII: 475-491",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100685"}
@inproceedings{bb103978,
AUTHOR = "Dai, W.X. and Chen, L.H. and Wang, J.B. and Liu, J.P. and Dai, B. and Tang, Y.S.",
TITLE = "Motionlcm: Real-time Controllable Motion Generation via Latent
Consistency Model",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 390-408",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100686"}
@inproceedings{bb103979,
AUTHOR = "Huang, Y.M. and Wan, W.L. and Yang, Y. and Callison Burch, C. and Yatskar, M. and Liu, L.J.",
TITLE = "Como: Controllable Motion Generation Through Language Guided Pose Code
Editing",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIX: 180-196",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100687"}
@inproceedings{bb103980,
AUTHOR = "Zou, Q. and Yuan, S. and Du, S. and Wang, Y. and Liu, C. and Xu, Y. and Chen, J. and Ji, X.Y.",
TITLE = "Parco: Part-coordinating Text-to-motion Synthesis",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVI: 126-143",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100688"}
@inproceedings{bb103981,
AUTHOR = "Christie, R. and Kitchen, B. and Tumilowicz, W. and Hooper, S. and Wunsche, B.C.",
TITLE = "Procedurally Generating Large Synthetic Worlds: Chunked Hierarchical
Wave Function Collapse",
BOOKTITLE = IVCNZ24,
YEAR = "2024",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100689"}
@inproceedings{bb103982,
AUTHOR = "Kwon, M. and Oh, S.W. and Zhou, Y. and Liu, D. and Lee, J.Y. and Cai, H.R. and Liu, B. and Liu, F. and Uh, Y.J.",
TITLE = "Harivo: Harnessing Text-to-image Models for Video Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIII: 19-36",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100690"}
@inproceedings{bb103983,
AUTHOR = "Wu, R.Q. and Chen, L. and Yang, T. and Guo, C. and Li, C.Y. and Zhang, X.Y.",
TITLE = "LAMP: Learn A Motion Pattern for Few-Shot Video Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7089-7098",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100691"}
@inproceedings{bb103984,
AUTHOR = "Yang, S. and Zhou, Y.F. and Liu, Z.W. and Loy, C.C.",
TITLE = "Fresco: Spatial-Temporal Correspondence for Zero-Shot Video
Translation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8703-8712",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100692"}
@inproceedings{bb103985,
AUTHOR = "Bahmani, S. and Liu, X. and Wang, Y.F. and Skorokhodov, I. and Rong, V. and Liu, Z.W. and Liu, X.H. and Park, J.J. and Tulyakov, S. and Wetzstein, G. and Tagliasacchi, A. and Lindell, D.B.",
TITLE = "TC4D: Trajectory-Conditioned Text-to-4D Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVI: 53-72",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100693"}
@inproceedings{bb103986,
AUTHOR = "Fan, K. and Tang, J. and Cao, W.J. and Yi, R. and Li, M. and Gong, J.Y. and Zhang, J.N. and Wang, Y.B. and Wang, C.J. and Ma, L.Z.",
TITLE = "Freemotion:
A Unified Framework for Number-Free Text-to-Motion Synthesis",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 93-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100694"}
@inproceedings{bb103987,
AUTHOR = "Oh, G. and Jeong, J. and Kim, S. and Byeon, W. and Kim, J. and Kim, S. and Kim, S.",
TITLE = "Mevg: Multi-event Video Generation with Text-to-video Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIII: 401-418",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100695"}
@inproceedings{bb103988,
AUTHOR = "Girdhar, R. and Singh, M. and Brown, A. and Duval, Q. and Azadi, S. and Rambhatla, S.S. and Shah, A. and Yin, X. and Parikh, D. and Misra, I.",
TITLE = "Factorizing Text-to-video Generation by Explicit Image Conditioning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXII: 205-224",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100696"}
@inproceedings{bb103989,
AUTHOR = "Materzynska, J. and Sivic, J. and Shechtman, E. and Torralba, A. and Zhang, R. and Russell, B.",
TITLE = "Newmove: Customizing Text-to-video Models with Novel Motions",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "V: 113-130",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100697"}
@inproceedings{bb103990,
AUTHOR = "Menapace, W. and Siarohin, A. and Skorokhodov, I. and Deyneka, E. and Chen, T.S. and Kag, A. and Fang, Y.W. and Stoliar, A. and Ricci, E. and Ren, J. and Tulyakov, S.",
TITLE = "Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video
Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7038-7048",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100698"}
@inproceedings{bb103991,
AUTHOR = "Tian, K.B. and Zhao, R.X. and Xin, Z.J. and Lan, B.X. and Li, X.R.",
TITLE = "Holistic Features are Almost Sufficient for Text-to-Video Retrieval",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "17138-17147",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100699"}
@inproceedings{bb103992,
AUTHOR = "Qing, Z.W. and Zhang, S.W. and Wang, J.Y. and Wang, X. and Wei, Y.J. and Zhang, Y.Y. and Gao, C.X. and Sang, N.",
TITLE = "Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6635-6645",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100700"}
@inproceedings{bb103993,
AUTHOR = "Wang, X. and Zhang, S.W. and Yuan, H.J. and Qing, Z.W. and Gong, B. and Zhang, Y.Y. and Shen, Y.J. and Gao, C.X. and Sang, N.",
TITLE = "A Recipe for Scaling up Text-to-Video Generation with Text-free
Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6572-6582",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100701"}
@inproceedings{bb103994,
AUTHOR = "Kim, T. and Kang, C. and Park, J. and Jeong, D. and Yang, C. and Kang, S.J. and Kong, K.",
TITLE = "Human Motion Aware Text-to-Video Generation with Explicit Camera
Control",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5069-5078",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100702"}
@inproceedings{bb103995,
AUTHOR = "Ji, P.L. and Xiao, C. and Tai, H.L. and Huo, M.X.",
TITLE = "T2VBench: Benchmarking Temporal Dynamics for Text-to-Video Generation",
BOOKTITLE = GenerativeFM24,
YEAR = "2024",
PAGES = "5325-5335",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100703"}
@inproceedings{bb103996,
AUTHOR = "Godfrey, W.W. and Ratna, A.",
TITLE = "Enhancing the Video Editing Capabilities of Text-to-Video Generators
Using DDPM Inversion",
BOOKTITLE = ICCVMI23,
YEAR = "2023",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100704"}
@inproceedings{bb103997,
AUTHOR = "Lee, H. and Kim, Y. and Lee, S.G.",
TITLE = "Multi-scale Contrastive Learning for Complex Scene Generation",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "764-774",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100705"}
@inproceedings{bb103998,
AUTHOR = "Loeschcke, S. and Belongie, S. and Benaim, S.",
TITLE = "Text-driven Stylization of Video Objects",
BOOKTITLE = CVEU22,
YEAR = "2022",
PAGES = "594-609",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100706"}
@inproceedings{bb103999,
AUTHOR = "Mazaheri, A. and Shah, M.",
TITLE = "Video Generation from Text Employing Latent Path Construction for
Temporal Modeling",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "5010-5016",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe490ttvid2.html#TT100707"}
Last update:Feb 26, 2026 at 10:58:24