@article{bb207600,
AUTHOR = "Fang, Z.Y. and Yu, J. and Hong, R.C.",
TITLE = "Boundary Discretization and Reliable Classification Network for
Temporal Action Detection",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "5198-5211",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202919"}
@article{bb207601,
AUTHOR = "Song, P.P. and Zhang, L. and Lan, L. and Chen, W.D. and Guo, D. and Yang, X. and Wang, M.",
TITLE = "Towards Efficient Partially Relevant Video Retrieval With Active
Moment Discovering",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6740-6751",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202920"}
@article{bb207602,
AUTHOR = "Zheng, Z.C. and Zhou, Y. and Chen, Y. and Gu, Y.H. and Zhou, J.S. and Ji, Z.",
TITLE = "Multiple Temporal Scale Aggregate Network for Temporal Action
Segmentation",
JOURNAL = PR,
VOLUME = "171",
YEAR = "2026",
PAGES = "112165",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202921"}
@article{bb207603,
AUTHOR = "Zhang, R.Z. and Duan, Y. and Chen, Y. and Hu, W.P. and Cai, C. and Wang, S. and Tan, Y.P.",
TITLE = "Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised
Action Segmentation",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11323-11336",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202922"}
@article{bb207604,
AUTHOR = "Ou, Y.J. and Mi, L. and Chen, Z.Z.",
TITLE = "HARG: Hierarchical Adaptive Reasoning Graph for Activity Parsing",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7946-7960",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202923"}
@inproceedings{bb207605,
AUTHOR = "Zhao, S.Z. and Ghoddoosian, R. and Dwivedi, I. and Agarwal, N. and Dariush, B.",
TITLE = "Pose-Aware Weakly-Supervised Action Segmentation",
BOOKTITLE = "MULA25",
YEAR = "2025",
PAGES = "97-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202924"}
@inproceedings{bb207606,
AUTHOR = "Ding, G.D. and Chen, R. and Yao, A.",
TITLE = "Condensing Action Segmentation Datasets via Generative Network
Inversion",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "17733-17742",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202925"}
@inproceedings{bb207607,
AUTHOR = "Yang, M. and Gao, H. and Guo, P. and Wang, L.M.",
TITLE = "Adapting Short-Term Transformers for Action Detection in Untrimmed
Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18570-18579",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202926"}
@inproceedings{bb207608,
AUTHOR = "Zheng, Z.W. and He, L.J. and Yang, L. and Li, F.",
TITLE = "Fine-grained Dynamic Network for Generic Event Boundary Detection",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIII: 107-123",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202927"}
@inproceedings{bb207609,
AUTHOR = "Pang, Z.Z. and Sener, F. and Ramasubramanian, S. and Yao, A.",
TITLE = "Long-tail Temporal Action Segmentation with Group-wise Temporal Logit
Adjustment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXX: 320-338",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202928"}
@inproceedings{bb207610,
AUTHOR = "Su, Y.H. and Elhamifar, E.",
TITLE = "Two-stage Active Learning for Efficient Temporal Action Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVII: 161-183",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202929"}
@inproceedings{bb207611,
AUTHOR = "Ji, H.Y. and Chen, B. and Xu, X.L. and Ren, W.H. and Wang, Z.Y. and Liu, H.H.",
TITLE = "Language-assisted Skeleton Action Understanding for Skeleton-based
Temporal Action Segmentation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIV: 400-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202930"}
@inproceedings{bb207612,
AUTHOR = "Huang, S. and Zhang, H.X. and Xu, Y.Y. and Gao, Y. and Hu, Y. and Qin, Z.C.",
TITLE = "Caseg: CLIP-Based Action Segmentation with Learnable Text Prompt",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "2201-2207",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202931"}
@inproceedings{bb207613,
AUTHOR = "Moltisanti, D. and Bilen, H. and Sevilla Lara, L. and Keller, F.",
TITLE = "Coarse or Fine? Recognising Action End States without Labels",
BOOKTITLE = FGVC24,
YEAR = "2024",
PAGES = "1191-1200",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202932"}
@inproceedings{bb207614,
AUTHOR = "Chen, Z.W. and Zhu, Z.Y. and Zhang, Y.F. and Hou, J.H. and Shi, G.M. and Wu, J.J.",
TITLE = "Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3890-3900",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202933"}
@inproceedings{bb207615,
AUTHOR = "Ding, G.D. and Golong, H. and Yao, A.",
TITLE = "Coherent Temporal Synthesis for Incremental Action Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28485-28494",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202934"}
@inproceedings{bb207616,
AUTHOR = "Xu, A. and Zheng, W.S.",
TITLE = "Efficient and Effective Weakly-Supervised Action Segmentation via
Action-Transition-Aware Boundary Alignment",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18253-18262",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202935"}
@inproceedings{bb207617,
AUTHOR = "Shen, Y.H. and Elhamifar, E.",
TITLE = "Progress-Aware Online Action Segmentation for Egocentric Procedural
Task Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18186-18197",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202936"}
@inproceedings{bb207618,
AUTHOR = "Lu, Z. and Elhamifar, E.",
TITLE = "FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient
Action Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18175-18185",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202937"}
@inproceedings{bb207619,
AUTHOR = "Hirsch, R. and Cohen, R. and Golany, T. and Freedman, D. and Rivlin, E.",
TITLE = "Random Walks for Temporal Action Segmentation with Timestamp
Supervision",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6600-6610",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202938"}
@inproceedings{bb207620,
AUTHOR = "Tran, Q.H. and Mehmood, A. and Ahmed, M. and Naufil, M. and Zafar, A. and Konin, A. and Zia, M.Z.",
TITLE = "Permutation-Aware Activity Segmentation via Unsupervised
Frame-to-Segment Alignment",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6412-6422",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202939"}
@inproceedings{bb207621,
AUTHOR = "Li, Y.R. and Xue, Z.R. and Xu, H.Z.",
TITLE = "OTAS: Unsupervised Boundary Detection for Object-Centric Temporal
Action Segmentation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6423-6432",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202940"}
@inproceedings{bb207622,
AUTHOR = "Bahrami, E. and Francesca, G. and Gall, J.",
TITLE = "How Much Temporal Long-Term Context is Needed for Action
Segmentation?",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10317-10327",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202941"}
@inproceedings{bb207623,
AUTHOR = "Aziere, N. and Todorovic, S.",
TITLE = "Markov Game Video Augmentation for Action Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13459-13468",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202942"}
@inproceedings{bb207624,
AUTHOR = "Jiang, B. and Jin, Y. and Tan, Z.T. and Mu, Y.D.",
TITLE = "Video Action Segmentation via Contextually Refined Temporal Keypoints",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13790-13799",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202943"}
@inproceedings{bb207625,
AUTHOR = "Liu, K.Y. and Li, Y.H. and Liu, S.L. and Tan, C.W. and Shao, Z.H.",
TITLE = "Reducing the Label Bias for Timestamp Supervised Temporal Action
Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6503-6513",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202944"}
@inproceedings{bb207626,
AUTHOR = "van Amsterdam, B. and Kadkhodamohammadi, A. and Luengo, I. and Stoyanov, D.",
TITLE = "ASPnet: Action Segmentation with Shared-Private Representation of
Multiple Data Sources",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2384-2393",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202945"}
@inproceedings{bb207627,
AUTHOR = "Han, H.F. and Lu, Z.W. and Wen, J.R.",
TITLE = "CTDA: Contrastive Temporal Domain Adaptation for Action Segmentation",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "II: 562-574",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202946"}
@inproceedings{bb207628,
AUTHOR = "Behrmann, N. and Golestaneh, S.A. and Kolter, Z. and Gall, J. and Noroozi, M.",
TITLE = "Unified Fully and Timestamp Supervised Temporal Action Segmentation via
Sequence to Sequence Translation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:52-68",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202947"}
@inproceedings{bb207629,
AUTHOR = "Ishihara, K. and Nakano, G. and Inoshita, T.",
TITLE = "MCFM: Mutual Cross Fusion Module for Intermediate Fusion-Based Action
Segmentation",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1701-1705",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202948"}
@inproceedings{bb207630,
AUTHOR = "Sun, Z.N. and Messikommer, N. and Gehrig, D. and Scaramuzza, D.",
TITLE = "ESS: Learning Event-Based Semantic Segmentation from Still Images",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXIV:341-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202949"}
@inproceedings{bb207631,
AUTHOR = "Chen, L. and Tong, Z. and Song, Y.B. and Wu, G.S. and Wang, L.M.",
TITLE = "Efficient Video Action Detection with Token Dropout and Context
Refinement",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10354-10365",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202950"}
@inproceedings{bb207632,
AUTHOR = "Tang, J.Q. and Liu, Z.Y. and Qian, C. and Wu, W. and Wang, L.M.",
TITLE = "Progressive Attention on Multi-Level Dense Difference Maps for
Generic Event Boundary Detection",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3345-3354",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202951"}
@inproceedings{bb207633,
AUTHOR = "Du, Z.X. and Wang, X. and Zhou, G.Q. and Wang, Q.",
TITLE = "Fast and Unsupervised Action Boundary Detection for Action
Segmentation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3313-3322",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202952"}
@inproceedings{bb207634,
AUTHOR = "Kang, H. and Kim, J. and Kim, T. and Kim, S.J.",
TITLE = "UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event
Boundary Detection",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20041-20050",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202953"}
@inproceedings{bb207635,
AUTHOR = "Kumar, S. and Haresh, S. and Ahmed, A. and Konin, A. and Zia, M.Z. and Tran, Q.H.",
TITLE = "Unsupervised Action Segmentation by Joint Representation Learning and
Online Clustering",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20142-20153",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202954"}
@inproceedings{bb207636,
AUTHOR = "Dimiccoli, M. and Garrido, L. and Rodriguez Corominas, G. and Wendt, H.",
TITLE = "Graph Constrained Data Representation Learning for Human Motion
Segmentation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1440-1449",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202955"}
@inproceedings{bb207637,
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#TT202956"}
@inproceedings{bb207638,
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#TT202957"}
@inproceedings{bb207639,
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#TT202958"}
@inproceedings{bb207640,
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#TT202959"}
@inproceedings{bb207641,
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#TT202960"}
@inproceedings{bb207642,
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#TT202961"}
@inproceedings{bb207643,
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#TT202962"}
@inproceedings{bb207644,
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#TT202963"}
@inproceedings{bb207645,
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#TT202964"}
@inproceedings{bb207646,
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#TT202965"}
@inproceedings{bb207647,
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#TT202966"}
@inproceedings{bb207648,
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#TT202967"}
@inproceedings{bb207649,
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#TT202968"}
@inproceedings{bb207650,
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#TT202969"}
@inproceedings{bb207651,
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#TT202970"}
@inproceedings{bb207652,
AUTHOR = "Gao, M.F. and Zhou, Y.B. and Xu, R. and Socher, R. and Xiong, C.M.",
TITLE = "WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "1915-1923",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202971"}
@inproceedings{bb207653,
AUTHOR = "Gao, M.F. and Xu, M.Z. and Davis, L.S. and Socher, R. and Xiong, C.M.",
TITLE = "StartNet: Online Detection of Action Start in Untrimmed Videos",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "5541-5550",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202972"}
@inproceedings{bb207654,
AUTHOR = "Bai, R. and Zhao, Q. and Zhou, S. and Li, Y. and Zhao, X. and Wang, J.",
TITLE = "Continuous Action Recognition and Segmentation in Untrimmed Videos",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2534-2539",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742ase2.html#TT202973"}
@inproceedings{bb207655,
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#TT202974"}
@inproceedings{bb207656,
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#TT202975"}
@inproceedings{bb207657,
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#TT202976"}
@inproceedings{bb207658,
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#TT202977"}
@inproceedings{bb207659,
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#TT202978"}
@inproceedings{bb207660,
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#TT202979"}
@article{bb207661,
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#TT202980"}
@article{bb207662,
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#TT202981"}
@article{bb207663,
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#TT202982"}
@article{bb207664,
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#TT202983"}
@article{bb207665,
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#TT202984"}
@article{bb207666,
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#TT202985"}
@article{bb207667,
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#TT202986"}
@article{bb207668,
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#TT202987"}
@article{bb207669,
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#TT202988"}
@article{bb207670,
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#TT202989"}
@article{bb207671,
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#TT202990"}
@article{bb207672,
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#TT202991"}
@article{bb207673,
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#TT202992"}
@article{bb207674,
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#TT202993"}
@article{bb207675,
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#TT202994"}
@article{bb207676,
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#TT202995"}
@article{bb207677,
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#TT202996"}
@article{bb207678,
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#TT202997"}
@article{bb207679,
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#TT202998"}
@article{bb207680,
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#TT202999"}
@article{bb207681,
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#TT203000"}
@article{bb207682,
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#TT203001"}
@article{bb207683,
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#TT203002"}
@article{bb207684,
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#TT203003"}
@article{bb207685,
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#TT203004"}
@article{bb207686,
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#TT203005"}
@article{bb207687,
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#TT203006"}
@inproceedings{bb207688,
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#TT203007"}
@inproceedings{bb207689,
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#TT203008"}
@inproceedings{bb207690,
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#TT203009"}
@inproceedings{bb207691,
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#TT203010"}
@inproceedings{bb207692,
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#TT203011"}
@inproceedings{bb207693,
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#TT203012"}
@inproceedings{bb207694,
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#TT203013"}
@inproceedings{bb207695,
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#TT203014"}
@inproceedings{bb207696,
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#TT203015"}
@inproceedings{bb207697,
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#TT203016"}
@inproceedings{bb207698,
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#TT203017"}
@inproceedings{bb207699,
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#TT203018"}
Last update:Jan 8, 2026 at 12:52:16