@inproceedings{bb214800,
AUTHOR = "Ahn, H. and Lee, D.",
TITLE = "Refining Action Segmentation with Hierarchical Video Representations",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "16282-16290",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210097"}
@inproceedings{bb214801,
AUTHOR = "Lu, Z.J. and Elhamifar, E.",
TITLE = "Set-Supervised Action Learning in Procedural Task Videos via Pairwise
Order Consistency",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19871-19881",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210098"}
@inproceedings{bb214802,
AUTHOR = "Lu, Z.J. and Elhamifar, E.",
TITLE = "Weakly-Supervised Action Segmentation and Alignment via
Transcript-Aware Union-of-Subspaces Learning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "8065-8075",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210099"}
@inproceedings{bb214803,
AUTHOR = "Pan, G. and Zhang, H. and Yu, F. and Song, Y.H. and Zhang, Y.L. and Yuan, H.",
TITLE = "You Ought to Look Around: Precise, Large Span Action Detection",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "1574-1581",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210100"}
@inproceedings{bb214804,
AUTHOR = "He, J.Y. and Li, G.H. and Lei, J.",
TITLE = "Feature Pyramid Hierarchies for Multi-scale Temporal Action Detection",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "2158-2165",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210101"}
@inproceedings{bb214805,
AUTHOR = "Li, J. and Todorovic, S.",
TITLE = "Action Shuffle Alternating Learning for Unsupervised Action
Segmentation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "12623-12631",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210102"}
@inproceedings{bb214806,
AUTHOR = "Shen, Y.H. and Wang, L. and Elhamifar, E.",
TITLE = "Learning to Segment Actions from Visual and Language Instructions via
Differentiable Weak Sequence Alignment",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "10151-10160",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210103"}
@inproceedings{bb214807,
AUTHOR = "Ishikawa, Y. and Kondo, M. and Aoki, Y.",
TITLE = "Data Collection-free Masked Video Modeling",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XI: 37-56",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210104"}
@inproceedings{bb214808,
AUTHOR = "Ishikawa, Y. and Kasai, S. and Aoki, Y. and Kataoka, H.",
TITLE = "Alleviating Over-segmentation Errors by Detecting Action Boundaries",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "2321-2330",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210105"}
@inproceedings{bb214809,
AUTHOR = "Nicora, E. and Pastore, V.P. and Noceti, N.",
TITLE = "GCK-Maps: A Scene Unbiased Representation for Efficient Human Action
Recognition",
BOOKTITLE = CIAP23,
YEAR = "2023",
PAGES = "I:62-73",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210106"}
@inproceedings{bb214810,
AUTHOR = "Vignolo, A. and Noceti, N. and Sciutti, A. and Odone, F. and Sandini, G.",
TITLE = "Learning dictionaries of kinematic primitives for action
classification",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5965-5972",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210107"}
@inproceedings{bb214811,
AUTHOR = "Gao, S.H. and Han, Q. and Li, Z.Y. and Peng, P. and Wang, L. and Cheng, M.M.",
TITLE = "Global2Local:
Efficient Structure Search for Video Action Segmentation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "16800-16809",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210108"}
@inproceedings{bb214812,
AUTHOR = "Li, Z. and Abu Farha, Y. and Gall, J.",
TITLE = "Temporal Action Segmentation from Timestamp Supervision",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8361-8370",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210109"}
@inproceedings{bb214813,
AUTHOR = "Li, J. and Todorovic, S.",
TITLE = "Anchor-Constrained Viterbi for Set-Supervised Action Segmentation",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "9801-9810",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210110"}
@inproceedings{bb214814,
AUTHOR = "Li, J. and Todorovic, S.",
TITLE = "Set-Constrained Viterbi for Set-Supervised Action Segmentation",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10817-10826",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210111"}
@inproceedings{bb214815,
AUTHOR = "Haring, S. and Memmesheimer, R. and Paulus, D.",
TITLE = "Action Segmentation on Representations of Skeleton Sequences Using
Transformer Networks",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "3053-3057",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210112"}
@inproceedings{bb214816,
AUTHOR = "Huang, Y. and Sugano, Y. and Sato, Y.",
TITLE = "Improving Action Segmentation via Graph-Based Temporal Reasoning",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "14021-14031",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210113"}
@inproceedings{bb214817,
AUTHOR = "Kwak, I.S. and Guo, J. and Hantman, A. and Branson, K. and Kriegman, D.",
TITLE = "Detecting the Starting Frame of Actions in Video",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "478-486",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210114"}
@inproceedings{bb214818,
AUTHOR = "Ulutan, O. and Rallapalli, S. and Srivatsa, M. and Torres, C. and Manjunath, B.S.",
TITLE = "Actor Conditioned Attention Maps for Video Action Detection",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "516-525",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210115"}
@inproceedings{bb214819,
AUTHOR = "Jain, H. and Harit, G.",
TITLE = "Unsupervised Temporal Segmentation of Human Action Using Community
Detection",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "1892-1896",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210116"}
@inproceedings{bb214820,
AUTHOR = "Wang, W. and Wu, Y. and Liu, H. and Wang, S. and Cheng, J.",
TITLE = "Temporal Action Detection by Joint Identification-Verification",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2026-2031",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210117"}
@inproceedings{bb214821,
AUTHOR = "Ali, A. and Taylor, G.W.",
TITLE = "Real-Time End-to-End Action Detection with Two-Stream Networks",
BOOKTITLE = CRV18,
YEAR = "2018",
PAGES = "31-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210118"}
@inproceedings{bb214822,
AUTHOR = "Mavroudi, E. and Bhaskara, D. and Sefati, S. and Ali, H. and Vidal, R.",
TITLE = "End-to-End Fine-Grained Action Segmentation and Recognition Using
Conditional Random Field Models and Discriminative Sparse Coding",
BOOKTITLE = WACV18,
YEAR = "2018",
PAGES = "1558-1567",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210119"}
@inproceedings{bb214823,
AUTHOR = "Kuehne, H. and Gall, J. and Serre, T.",
TITLE = "An end-to-end generative framework for video segmentation and
recognition",
BOOKTITLE = WACV16,
YEAR = "2016",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210120"}
@inproceedings{bb214824,
AUTHOR = "Ni, B.B. and Yang, X.K. and Gao, S.H.",
TITLE = "Progressively Parsing Interactional Objects for Fine Grained Action
Detection",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "1020-1028",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210121"}
@inproceedings{bb214825,
AUTHOR = "Garcia Hernando, G.B. and Kim, T.K.",
TITLE = "Transition Forests: Learning Discriminative Temporal Transitions for
Action Recognition and Detection",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "407-415",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210122"}
@inproceedings{bb214826,
AUTHOR = "Li, S. and Li, K. and Fu, Y.",
TITLE = "Temporal Subspace Clustering for Human Motion Segmentation",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "4453-4461",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210123"}
@inproceedings{bb214827,
AUTHOR = "Lu, J. and Xu, R. and Corso, J.J.",
TITLE = "Human action segmentation with hierarchical supervoxel consistency",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "3762-3771",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210124"}
@inproceedings{bb214828,
AUTHOR = "Kim, Y. and Chen, J.X. and Chang, M.C. and Wang, X. and Provost, E.M. and Lyu, S.W.",
TITLE = "Modeling transition patterns between events for temporal human action
segmentation and classification",
BOOKTITLE = FG15,
YEAR = "2015",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210125"}
@inproceedings{bb214829,
AUTHOR = "Ghodrati, A. and Pedersoli, M. and Tuytelaars, T.",
TITLE = "Coupling video segmentation and action recognition",
BOOKTITLE = WACV14,
YEAR = "2014",
PAGES = "618-625",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210126"}
@inproceedings{bb214830,
AUTHOR = "Shu, Z.X. and Yun, K. and Samaras, D.",
TITLE = "Action Detection with Improved Dense Trajectories and Sliding Window",
BOOKTITLE = ChaLearn14,
YEAR = "2014",
PAGES = "541-551",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210127"}
@inproceedings{bb214831,
AUTHOR = "Natarajan, P. and Wu, S. and Vitaladevuni, S. and Zhuang, X.D. and Tsakalidis, S. and Park, U.S. and Prasad, R. and Natarajan, P.",
TITLE = "Multimodal feature fusion for robust event detection in web videos",
BOOKTITLE = CVPR12,
YEAR = "2012",
PAGES = "1298-1305",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210128"}
@inproceedings{bb214832,
AUTHOR = "Sorschag, R. and Horhan, M.",
TITLE = "Action scene detection from motion and events",
BOOKTITLE = ICIP11,
YEAR = "2011",
PAGES = "3641-3644",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT210129"}
@article{bb214833,
AUTHOR = "Hu, Y.P. and Liu, M. and Su, X.O. and Gao, Z. and Nie, L.Q.",
TITLE = "Video Moment Localization via Deep Cross-Modal Hashing",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "4667-4677",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210130"}
@article{bb214834,
AUTHOR = "Gao, J.Y. and Xu, C.S.",
TITLE = "Learning Video Moment Retrieval Without a Single Annotated Video",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "3",
MONTH = "March",
PAGES = "1646-1657",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210131"}
@article{bb214835,
AUTHOR = "Liu, M. and Nie, L.Q. and Wang, Y.X. and Wang, M. and Rui, Y.",
TITLE = "A Survey on Video Moment Localization",
JOURNAL = Surveys,
VOLUME = "55",
YEAR = "2023",
NUMBER = "9",
MONTH = "January",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210132"}
@article{bb214836,
AUTHOR = "Sun, X. and Gao, J.L. and Zhu, Y.Z. and Wang, X. and Zhou, X.",
TITLE = "Video Moment Retrieval via Comprehensive Relation-Aware Network",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "5281-5295",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210133"}
@article{bb214837,
AUTHOR = "Fang, X. and Liu, D.Z. and Zhou, P. and Hu, Y.C.",
TITLE = "Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "7517-7532",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210134"}
@article{bb214838,
AUTHOR = "Yang, X. and Wang, S.S. and Dong, J. and Dong, J.F. and Wang, M. and Chua, T.S.",
TITLE = "Video Moment Retrieval With Cross-Modal Neural Architecture Search",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "1204-1216",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210135"}
@article{bb214839,
AUTHOR = "Han, N. and Yang, X. and Lim, E.P. and Chen, H. and Sun, Q.",
TITLE = "Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "10924-10936",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210136"}
@article{bb214840,
AUTHOR = "Teng, J. and Lu, X.K. and Gong, Y.S. and Liu, X.F. and Nie, X.S. and Yin, Y.L.",
TITLE = "Regularized Two Granularity Loss Function for Weakly Supervised Video
Moment Retrieval",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "1141-1151",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210137"}
@article{bb214841,
AUTHOR = "Wang, G.M. and Xu, X. and Shen, F.M. and Lu, H.M. and Ji, Y.L. and Shen, H.T.",
TITLE = "Cross-Modal Dynamic Networks for Video Moment Retrieval With Text
Query",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "1221-1232",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210138"}
@article{bb214842,
AUTHOR = "Huo, S.W. and Zhou, Y. and Wang, R.L. and Xiang, W. and Kung, S.Y.",
TITLE = "Semantic Relevance Learning for Video-Query Based Video Moment
Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9290-9301",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210139"}
@article{bb214843,
AUTHOR = "Wang, Y.X. and Liu, M. and Wei, Y.W. and Cheng, Z.Y. and Wang, Y.L. and Nie, L.Q.",
TITLE = "Siamese Alignment Network for Weakly Supervised Video Moment
Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "3921-3933",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210140"}
@article{bb214844,
AUTHOR = "Wang, R.M. and Feng, J.W. and Zhang, F. and Luo, X.N. and Luo, Y.M.",
TITLE = "Modality-Aware Heterogeneous Graph for Joint Video Moment Retrieval
and Highlight Detection",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "8896-8911",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210141"}
@article{bb214845,
AUTHOR = "Wang, D. and Lu, X.T. and Wang, Q. and Tian, Y.M. and Wan, B. and He, L.",
TITLE = "Gist, Content, Target-Oriented: A 3-Level Human-Like Framework for
Video Moment Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "11044-11056",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210142"}
@article{bb214846,
AUTHOR = "Huang, Z.H. and Ji, Y. and Li, Y. and Liu, C.P.",
TITLE = "Gazing After Glancing: Edge Information Guided Perception Network for
Video Moment Retrieval",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1535-1539",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210143"}
@article{bb214847,
AUTHOR = "Han, D. and Cheng, X. and Guo, N. and Ye, X.C. and Rainer, B. and Priller, P.",
TITLE = "Momentum Cross-Modal Contrastive Learning for Video Moment Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "7",
MONTH = "July",
PAGES = "5977-5994",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210144"}
@article{bb214848,
AUTHOR = "Jiang, X. and Xu, X. and Zhou, Z.L. and Yang, Y. and Shen, F.M. and Shen, H.T.",
TITLE = "Zero-Shot Video Moment Retrieval with Angular Reconstructive Text
Embeddings",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9657-9670",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210145"}
@article{bb214849,
AUTHOR = "Zhou, S. and Zhang, F. and Wang, R.M. and Zhou, F. and Su, Z.",
TITLE = "Subtask Prior-Driven Optimized Mechanism on Joint Video Moment
Retrieval and Highlight Detection",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "11271-11285",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210146"}
@article{bb214850,
AUTHOR = "Ge, H.L. and Liu, X.L. and Guo, Z.H. and Qiu, Z.W.",
TITLE = "Learning to Diversify for Robust Video Moment Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "2894-2904",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210147"}
@article{bb214851,
AUTHOR = "Zhao, Y. and Gao, Z. and Ma, C.J. and Guan, W. and Wang, R. and Chen, S.Y.",
TITLE = "Fine-Grained Modality Relation-Aware Network for Video Moment
Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "3315-3327",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210148"}
@article{bb214852,
AUTHOR = "Jiang, X. and Zhu, L.Q. and Xu, X. and Shen, F.M. and Yang, Y. and Shen, H.T.",
TITLE = "Query as Supervision: Toward Low-Cost and Robust Video Moment and
Highlight Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3955-3968",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210149"}
@article{bb214853,
AUTHOR = "Zeng, R.H. and Zhuo, Y. and Li, J.L. and Yang, Y.J. and Wu, H. and Chen, Q. and Hu, X.P. and Leung, V.C.M.",
TITLE = "Improving Video Moment Retrieval by Auxiliary Moment-Query Pairs With
Hyper-Interaction",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3940-3954",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210150"}
@article{bb214854,
AUTHOR = "Liu, J. and Zhang, Z.B. and Su, Y.T. and Yang, B. and Min, X.K. and Zhai, G.T.",
TITLE = "Aggregate and Discriminate: Pseudo Clips-Guided Boundary Perception
for Video Moment Retrieval",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "4819-4830",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210151"}
@article{bb214855,
AUTHOR = "Cai, W.T. and Huang, J. and Gong, S.G. and Jin, H.L. and Liu, Y.",
TITLE = "MLLM as video narrator: Mitigating modality imbalance in video moment
retrieval",
JOURNAL = PR,
VOLUME = "166",
YEAR = "2025",
PAGES = "111670",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210152"}
@article{bb214856,
AUTHOR = "Liu, W.J. and Miao, B. and Cao, J.X. and Zhu, X.L. and Ge, J.W. and Liu, B. and Nasim, M. and Mian, A.",
TITLE = "Context-Enhanced Video Moment Retrieval With Large Language Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6296-6306",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210153"}
@article{bb214857,
AUTHOR = "Wang, D. and Yu, Y.S. and Li, S.F. and Zhong, H. and Liang, X. and Zhao, L.",
TITLE = "Scene-enhanced multi-scale temporal aware network for video moment
retrieval",
JOURNAL = PR,
VOLUME = "165",
YEAR = "2025",
PAGES = "111642",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210154"}
@article{bb214858,
AUTHOR = "Liu, J. and He, Z. and Nie, W.Z. and Zhang, Z.B. and Su, Y.T.",
TITLE = "What and Where: Semantic Grasping and Contextual Scanning for Moment
Retrieval and Highlight Detection",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "7155-7166",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210155"}
@article{bb214859,
AUTHOR = "Xie, P.Y. and Li, J.X. and Lu, G.M. and Xu, Y. and Zhang, D.",
TITLE = "Caption Assisted Multimodal Large Language Model for Video Moment
Retrieval",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "6755-6766",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210156"}
@article{bb214860,
AUTHOR = "Yin, J. and Li, L. and Zhang, J. and Yan, C.G. and Wang, H. and Sun, Y.Q. and Zhu, Z.J.",
TITLE = "Hybrid Debiasing Transformer With Adaptive Regularization for Video
Moment Localization",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "3986-4001",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210157"}
@article{bb214861,
AUTHOR = "Hu, H.X. and Ran, R. and Wei, J. and Sun, C.W. and Zhou, Y.Y. and He, S.Y. and Liu, K. and Yang, Y.",
TITLE = "Mismatched Pairs Dynamic Correction for Cross-Modal Alignment in
Video Moment Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "8",
MONTH = "August",
PAGES = "12282-12295",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210158"}
@inproceedings{bb214862,
AUTHOR = "Plou, C. and Borja, C. and Martinez Cantin, R. and Murillo, A.C.",
TITLE = "FALCONEye: Finding Answers and Localizing Content in ONE-hour-long
videos with multi-modal LLMs",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1334-1344",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210159"}
@article{bb214863,
AUTHOR = "Zhao, J.L. and Li, H.F. and Zhang, Y.F. and Wang, W. and Hua, C.C.",
TITLE = "Training-Free Video Corpus Moment Retrieval via Synergistic
Collaboration and Adaptive Calibration",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "8952-8965",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210160"}
@article{bb214864,
AUTHOR = "Kim, S. and Yun, K. and Um, D.",
TITLE = "Finding Optimal Video Moment Without Training: Gaussian Boundary
Optimization for Weakly Supervised Video Grounding",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7425-7438",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210161"}
@article{bb214865,
AUTHOR = "Liu, Y. and Liu, F. and Jiao, L.C. and Bao, Q.Y. and Li, S. and Li, L.L. and Liu, X. and Chen, P. and Ma, W.P.",
TITLE = "CausalVEE: Adaptive KeyFrame-Based Causal Temporal Modeling for Video
Event Extraction",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7988-8002",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210162"}
@article{bb214866,
AUTHOR = "Guo, Z. and Yu, Z.H. and Zhang, Y.",
TITLE = "PointDiff: Conditional Diffusion Model for Point-Supervised Video
Moment Retrieval",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7734-7746",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210163"}
@article{bb214867,
AUTHOR = "Yang, J. and Wei, P. and Zheng, N.N.",
TITLE = "Learning Visual-Audio Dissonance for Moment Retrieval and Highlight
Detection",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "8734-8746",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210164"}
@inproceedings{bb214868,
AUTHOR = "Gordeev, A. and Dokholyan, V. and Tolstykh, I. and Kuprashevich, M.",
TITLE = "Saliency-Guided DETR for Moment Retrieval and Highlight Detection",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "907-916",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210165"}
@inproceedings{bb214869,
AUTHOR = "Cheng, W.Y. and Chang, K.P. and Huang, C.P. and Yang, F.E. and Wang, Y.C.A.F.",
TITLE = "TA-Prompting: Enhancing Video Large Language Models for Dense Video
Captioning via Temporal Anchors",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "225-235",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210166"}
@inproceedings{bb214870,
AUTHOR = "Park, S. and Choi, J. and Baek, K.J. and Shim, H.J.",
TITLE = "MomentMix Augmentation with Length-Aware DETR for Temporally Robust
Moment Retrieval",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1127-1136",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210167"}
@inproceedings{bb214871,
AUTHOR = "Kwon, S. and Lee, J.H. and Kang, J.W.",
TITLE = "Lightweight Temporal Contextual Fine-Tuning Method of Large
Multimodal Model for Video Moment Retrieval",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "2880-2885",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210168"}
@inproceedings{bb214872,
AUTHOR = "Nguyen Nhu, T.A. and Tran, H.L. and Le, N.K. and Nguyen, M.N. and Nguyen, T.H. and Nguyen Huu, H.L. and Phan Nguyen, H.P. and Pham, H.T. and Nguyen, Q. and Le, H.M. and Dinh, Q.V.",
TITLE = "A Lightweight Moment Retrieval System with Global Re-Ranking and
Robust Adaptive Bidirectional Temporal Search",
BOOKTITLE = IntVidSea25,
YEAR = "2025",
PAGES = "3708-3718",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210169"}
@inproceedings{bb214873,
AUTHOR = "Tran, H.L. and Nguyen Nhu, T.A. and Phan Nguyen, H.P. and Nguyen, T.H. and Nguyen Dich, N.M. and Dao, A. and Do, H.D. and Nguyen, Q. and Le, H.M. and Dinh, Q.V.",
TITLE = "Towards Efficient and Robust Moment Retrieval System: A Unified
Framework for Multi-Granularity Models and Temporal Reranking",
BOOKTITLE = IntVidSea25,
YEAR = "2025",
PAGES = "3719-3729",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210170"}
@inproceedings{bb214874,
AUTHOR = "Tan, J.W. and Wang, H.X. and Weng, J. and Li, J.X. and Ou, Z.L. and Dang, K.",
TITLE = "Anchor-Aware Similarity Cohesion in Target Frames Enables Predicting
Temporal Moment Boundaries in 2D",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24180-24189",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210171"}
@inproceedings{bb214875,
AUTHOR = "Jung, M. and Jang, Y. and Choi, S. and Kim, J. and Kim, J.H. and Zhang, B.T.",
TITLE = "Background-Aware Moment Detection for Video Moment Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8586-8596",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210172"}
@inproceedings{bb214876,
AUTHOR = "Flanagan, K. and Damen, D. and Wray, M.",
TITLE = "Moment of Untruth: Dealing with Negative Queries in Video Moment
Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5336-5345",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210173"}
@inproceedings{bb214877,
AUTHOR = "Panta, L. and Shrestha, P. and Sapkota, B. and Bhattarai, A. and Manandhar, S. and Sah, A.K.",
TITLE = "Cross-modal Contrastive Learning with Asymmetric Co-attention Network
for Video Moment Retrieval",
BOOKTITLE = Pretrain24,
YEAR = "2024",
PAGES = "617-624",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210174"}
@inproceedings{bb214878,
AUTHOR = "Luo, D.Z. and Huang, J. and Gong, S.G. and Jin, H.L. and Liu, Y.",
TITLE = "Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5452-5461",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210175"}
@inproceedings{bb214879,
AUTHOR = "Huang, C. and Wu, Y.L. and Shuai, H.H. and Huang, C.C.",
TITLE = "Semantic Fusion Augmentation and Semantic Boundary Detection: A Novel
Approach to Multi-Target Video Moment Retrieval",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6769-6778",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210176"}
@inproceedings{bb214880,
AUTHOR = "Xiao, Y.C. and Luo, Z.Y. and Liu, Y. and Ma, Y. and Bian, H.W. and Ji, Y. and Yang, Y.J. and Li, X.",
TITLE = "Bridging the Gap: A Unified Video Comprehension Framework for Moment
Retrieval and Highlight Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18709-18719",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210177"}
@inproceedings{bb214881,
AUTHOR = "Huang, B. and Wang, X. and Chen, H. and Song, Z. and Zhu, W.W.",
TITLE = "VTimeLLM: Empower LLM to Grasp Video Moments",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14271-14280",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210178"}
@inproceedings{bb214882,
AUTHOR = "Luo, D.Z. and Huang, J. and Gong, S.G. and Jin, H.L. and Liu, Y.",
TITLE = "Towards Generalisable Video Moment Retrieval: Visual-Dynamic
Injection to Image-Text Pre-Training",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23045-23055",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210179"}
@inproceedings{bb214883,
AUTHOR = "Ma, K.J. and Zang, X.H. and Feng, Z. and Fang, H. and Ban, C. and Wei, Y.H. and He, Z.J. and Li, Y.X. and Sun, H.",
TITLE = "LLaViLo: Boosting Video Moment Retrieval via Adapter-Based Multimodal
Modeling",
BOOKTITLE = CLVL23,
YEAR = "2023",
PAGES = "2790-2795",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210180"}
@inproceedings{bb214884,
AUTHOR = "Togashi, R. and Otani, M. and Nakashima, Y. and Rahtu, E. and Heikkila, J. and Sakai, T.",
TITLE = "AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "21044-21053",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210181"}
@inproceedings{bb214885,
AUTHOR = "Zhang, L.Y. and Radke, R.J.",
TITLE = "Natural Language Video Moment Localization Through Query-Controlled
Temporal Convolution",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2524-2532",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210182"}
@inproceedings{bb214886,
AUTHOR = "Liu, Y. and Li, S.Y. and Wu, Y. and Chen, C.W. and Shan, Y. and Qie, X.H.",
TITLE = "UMT: Unified Multi-modal Transformers for Joint Video Moment
Retrieval and Highlight Detection",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3032-3041",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210183"}
@inproceedings{bb214887,
AUTHOR = "Gao, J.Y. and Xu, C.S.",
TITLE = "Fast Video Moment Retrieval",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1503-1512",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210184"}
@inproceedings{bb214888,
AUTHOR = "Wang, H. and Zha, Z.J. and Li, L. and Liu, D. and Luo, J.B.",
TITLE = "Structured Multi-Level Interaction Network for Video Moment
Localization via Language Query",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "7022-7031",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210185"}
@inproceedings{bb214889,
AUTHOR = "Mithun, N.C. and Paul, S. and Roy Chowdhury, A.K.",
TITLE = "Weakly Supervised Video Moment Retrieval From Text Queries",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "11584-11593",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742vidmo3.html#TT210186"}
@article{bb214890,
AUTHOR = "Song, H. and Wu, X.X. and Zhu, B. and Wu, Y.W. and Chen, M. and Jia, Y.D.",
TITLE = "Temporal Action Localization in Untrimmed Videos Using Action Pattern
Trees",
JOURNAL = MultMed,
VOLUME = "21",
YEAR = "2019",
NUMBER = "3",
MONTH = "March",
PAGES = "717-730",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210187"}
@article{bb214891,
AUTHOR = "Zhou, Z.L. and Ding, C. and Li, J. and Mohammadi, E. and Liu, G.C. and Yang, Y.M. and Wu, Q.M.J.",
TITLE = "Sequential Order-Aware Coding-Based Robust Subspace Clustering for
Human Action Recognition in Untrimmed Videos",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "13-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210188"}
@article{bb214892,
AUTHOR = "Jiang, Y.G. and Li, Z. and Chang, S.F.",
TITLE = "Modeling Scene and Object Contexts for Human Action Retrieval With Few
Examples",
JOURNAL = CirSysVideo,
VOLUME = "21",
YEAR = "2011",
NUMBER = "5",
MONTH = "May",
PAGES = "674-681",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210189"}
@inproceedings{bb214893,
AUTHOR = "Liu, Y. and Ma, L. and Zhang, Y.F. and Liu, W. and Chang, S.F.",
TITLE = "Multi-Granularity Generator for Temporal Action Proposal",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "3599-3608",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210190"}
@inproceedings{bb214894,
AUTHOR = "Shou, Z. and Gao, H. and Zhang, L. and Miyazawa, K. and Chang, S.F.",
TITLE = "AutoLoc:
Weakly-Supervised Temporal Action Localization in Untrimmed Videos",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XVI: 162-179",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210191"}
@inproceedings{bb214895,
AUTHOR = "Shou, Z. and Wang, D.A. and Chang, S.F.",
TITLE = "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "1049-1058",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210192"}
@inproceedings{bb214896,
AUTHOR = "Shou, Z. and Chan, J. and Zareian, A. and Miyazawa, K. and Chang, S.F.",
TITLE = "CDC: Convolutional-De-Convolutional Networks for Precise Temporal
Action Localization in Untrimmed Videos",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "1417-1426",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210193"}
@article{bb214897,
AUTHOR = "Hu, X.J. and Wang, S.J. and Li, M. and Li, Y. and Du, S.",
TITLE = "Distribution-Aware Activity Boundary Representation for Online
Detection of Action Start in Untrimmed Videos",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "765-769",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210194"}
@article{bb214898,
AUTHOR = "Yan, S. and Liu, M.Y. and Wang, Y. and Liu, Y. and Liu, H.",
TITLE = "MLP: Motion Label Prior for Temporal Sentence Localization in
Untrimmed 3D Human Motions",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "11",
MONTH = "November",
PAGES = "11535-11550",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210195"}
@article{bb214899,
AUTHOR = "Tang, Y. and Chen, M.S. and Chen, L.P. and Wang, S. and Liu, M. and Wang, Y.N. and Liu, J.",
TITLE = "Information-Bottleneck-Guided Hybrid Neural Architecture Search for
Temporal Action Detection in Untrimmed Videos",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "8664-8677",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742untr2.html#TT210196"}
Last update:Oct 8, 2026 at 11:03:09