@article{bb184400, AUTHOR = "Liu, M. and Nie, L.Q. and Wang, Y. 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-f742aloct1.html#TT179869"} @article{bb184401, AUTHOR = "Zhang, D.W.", TITLE = "Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "3", MONTH = "March", PAGES = "3019-3031", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179870"} @article{bb184402, AUTHOR = "Xue, C. and Zhong, X. and Cai, M.J. and Chen, H. and Wang, W.W.", TITLE = "Audio-Visual Event Localization by Learning Spatial and Semantic Co-Attention", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "418-429", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179871"} @article{bb184403, AUTHOR = "Yang, W.F. and Zhang, T.Z. and Zhang, Y.D. and Wu, F.", TITLE = "Uncertainty Guided Collaborative Training for Weakly Supervised and Unsupervised Temporal Action Localization", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "4", MONTH = "April", PAGES = "5252-5267", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179872"} @article{bb184404, AUTHOR = "Su, Y.T. and Wang, W.K. and Liu, J. and Ma, S. and Yang, X.K.", TITLE = "Sequence as a Whole: A Unified Framework for Video Action Localization With Long-Range Text Query", JOURNAL = IP, VOLUME = "32", YEAR = "2023", PAGES = "1403-1418", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179873"} @article{bb184405, AUTHOR = "Wang, C. and Wang, J. and Liu, P.", TITLE = "Complementary adversarial mechanisms for weakly-supervised temporal action localization", JOURNAL = PR, VOLUME = "139", YEAR = "2023", PAGES = "109426", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179874"} @article{bb184406, AUTHOR = "Zhang, H.P. and Ma, C.H. and Yu, D.J. and Guan, L.M. and Wang, D.J. and Hu, Z.P. and Liu, X.", TITLE = "MTSCANet: Multi temporal resolution temporal semantic context aggregation network", JOURNAL = IET-CV, VOLUME = "17", YEAR = "2023", NUMBER = "3", PAGES = "366-378", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179875"} @article{bb184407, AUTHOR = "Gao, Z. and Cui, X. and Zhuo, T. and Cheng, Z.Y. and Liu, A.A. and Wang, M. and Chen, S.", TITLE = "A Multitemporal Scale and Spatial-Temporal Transformer Network for Temporal Action Localization", JOURNAL = HMS, VOLUME = "53", YEAR = "2023", NUMBER = "3", MONTH = "June", PAGES = "569-580", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179876"} @article{bb184408, AUTHOR = "Zhu, Z.X. and Wang, L. and Tang, W. and Zheng, N.N. and Hua, G.", TITLE = "ContextLoc++: A Unified Context Model for Temporal Action Localization", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "8", MONTH = "August", PAGES = "9504-9519", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179877"} @inproceedings{bb184409, AUTHOR = "Zhu, Z.X. and Tang, W. and Wang, L. and Zheng, N.N. and Hua, G.", TITLE = "Enriching Local and Global Contexts for Temporal Action Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13496-13505", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179878"} @article{bb184410, AUTHOR = "Liu, S. and Quan, W. and Wang, C. and Liu, Y. and Liu, B. and Yan, D.M.", TITLE = "Dense Modality Interaction Network for Audio-Visual Event Localization", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "2734-2748", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179879"} @article{bb184411, AUTHOR = "Sun, L. and Wang, P. and Wang, L. and Sun, J. and Okatani, T.", TITLE = "Zero-shot temporal event localisation: Label-free, training-free, domain-free", JOURNAL = IET-CV, VOLUME = "17", YEAR = "2023", NUMBER = "5", PAGES = "599-613", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179880"} @article{bb184412, AUTHOR = "Raza, M.A. and Chen, L.F. and Nanbo, L. and Fisher, R.B.", TITLE = "EatSense: Human centric, action recognition and localization dataset for understanding eating behaviors and quality of motion assessment", JOURNAL = IVC, VOLUME = "137", YEAR = "2023", PAGES = "104762", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179881"} @article{bb184413, AUTHOR = "Liu, Y. and Yang, F. and Ginhac, D.", TITLE = "Accumulated micro-motion representations for lightweight online action detection in real-time", JOURNAL = JVCIR, VOLUME = "95", YEAR = "2023", PAGES = "103879", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179882"} @article{bb184414, AUTHOR = "Mettes, P.", TITLE = "Universal Prototype Transport for Zero-Shot Action Recognition and Localization", JOURNAL = IJCV, VOLUME = "131", YEAR = "2023", NUMBER = "1", MONTH = "January", PAGES = "3060-3073", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179883"} @article{bb184415, AUTHOR = "Chen, Z.Y. and Liu, H. and Zhang, L.L. and Liao, X.", TITLE = "Multi-Dimensional Attention With Similarity Constraint for Weakly-Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "4349-4360", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179884"} @article{bb184416, 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-f742aloct1.html#TT179885"} @article{bb184417, 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-f742aloct1.html#TT179886"} @article{bb184418, AUTHOR = "Ju, C. and Zhao, P. and Chen, S. and Zhang, Y. and Zhang, X.Y. and Wang, Y.F. and Tian, Q.", TITLE = "Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "6688-6701", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179887"} @article{bb184419, AUTHOR = "Moniruzzaman, M. and Yin, Z.Z.", TITLE = "Collaborative Foreground, Background, and Action Modeling Network for Weakly Supervised Temporal Action Localization", JOURNAL = CirSysVideo, VOLUME = "33", YEAR = "2023", NUMBER = "11", MONTH = "November", PAGES = "6939-6951", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179888"} @article{bb184420, 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-f742aloct1.html#TT179889"} @article{bb184421, AUTHOR = "Liu, Z. and Yan, D.F. and Cai, Y.Q. and Song, Y.", TITLE = "Spatio-temporal human action localization in indoor surveillances", JOURNAL = PR, VOLUME = "147", YEAR = "2024", PAGES = "110087", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179890"} @article{bb184422, AUTHOR = "Xia, K. and Wang, L. and Shen, Y.C. and Zhou, S. and Hua, G. and Tang, W.", TITLE = "Exploring Action Centers for Temporal Action Localization", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "9425-9436", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179891"} @article{bb184423, AUTHOR = "Wang, S.M. and Yan, R. and Huang, P. and Dai, G.Z. and Song, Y. and Shu, X.B.", TITLE = "Com-STAL: Compositional Spatio-Temporal Action Localization", JOURNAL = CirSysVideo, VOLUME = "33", YEAR = "2023", NUMBER = "12", MONTH = "December", PAGES = "7645-7657", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179892"} @article{bb184424, AUTHOR = "Moniruzzaman, M. and Yin, Z.Z.", TITLE = "Feature Weakening, Contextualization, and Discrimination for Weakly Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "270-283", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179893"} @article{bb184425, AUTHOR = "Sun, Y.Z. and Xu, Y.F. and Xie, Z. and Shu, Y.K. and Du, S.", TITLE = "GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features", JOURNAL = SPLetters, VOLUME = "31", YEAR = "2024", PAGES = "521-525", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179894"} @article{bb184426, AUTHOR = "Chen, T.B. and Wang, W. and Jiang, Z. and Li, R.C. and Wang, B.S.", TITLE = "Cross-Modality Knowledge Calibration Network for Video Corpus Moment Retrieval", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "3799-3813", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179895"} @article{bb184427, AUTHOR = "Gan, M.G. and Zhang, Y.", TITLE = "Content Temporal Relation Network for temporal action proposal generation", JOURNAL = PR, VOLUME = "149", YEAR = "2024", PAGES = "110245", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179896"} @article{bb184428, AUTHOR = "Wang, B. and Zhao, Y.Q. and Yang, L. and Long, T. and Li, X.L.", TITLE = "Temporal Action Localization in the Deep Learning Era: A Survey", JOURNAL = PAMI, VOLUME = "46", YEAR = "2024", NUMBER = "4", MONTH = "April", PAGES = "2171-2190", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179897"} @article{bb184429, AUTHOR = "Wang, C.X. and Wang, J. and Xu, W.T.", TITLE = "Double branch synergies with modal reinforcement for weakly supervised temporal action detection", JOURNAL = JVCIR, VOLUME = "99", YEAR = "2024", PAGES = "104090", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179898"} @article{bb184430, AUTHOR = "Jiang, Y.Y. and Yin, J.Q. and Dang, Y.H.", TITLE = "Leveraging the Video-Level Semantic Consistency of Event for Audio-Visual Event Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "4617-4627", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179899"} @article{bb184431, 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-f742aloct1.html#TT179900"} @article{bb184432, AUTHOR = "Li, T.T. and Sun, Z.X. and Xiao, X.Y.", TITLE = "Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning", JOURNAL = IP, VOLUME = "33", YEAR = "2024", PAGES = "1911-1922", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179901"} @article{bb184433, AUTHOR = "Li, G.Z. and Cheng, D. and Wang, N.N. and Li, J. and Gao, X.B.", TITLE = "Neighbor-Guided Pseudo-Label Generation and Refinement for Single-Frame Supervised Temporal Action Localization", JOURNAL = IP, VOLUME = "33", YEAR = "2024", PAGES = "2419-2430", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179902"} @article{bb184434, AUTHOR = "Shao, Y.X. and Zhang, F.F. and Xu, C.S.", TITLE = "Snippet-to-Prototype Contrastive Consensus Network for Weakly Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "6717-6729", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179903"} @inproceedings{bb184435, AUTHOR = "Mondal, A. and Nag, S. and Prada, J.M. and Zhu, X.T. and Dutta, A.", TITLE = "Actor-agnostic Multi-label Action Recognition with Multi-modal Query", BOOKTITLE = NIVT23, YEAR = "2023", PAGES = "784-794", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179904"} @inproceedings{bb184436, AUTHOR = "Warchocki, J. and Oprescu, T. and Wang, Y.H. and Damacus, A. and Misterka, P. and Bruintjes, R.J. and Lengyel, A. and Strafforello, O. and van Gemert, J.C.", TITLE = "Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models", BOOKTITLE = CVEU23, YEAR = "2023", PAGES = "3000-3008", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179905"} @inproceedings{bb184437, AUTHOR = "Heigold, G. and Keysers, D. and Minderer, M. and Lucic, M. and Gritsenko, A. and Yu, F. and Bewley, A. and Kipf, T.", TITLE = "Video OWL-ViT: Temporally-consistent open-world localization in video", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "13756-13765", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179906"} @inproceedings{bb184438, AUTHOR = "Shao, J.Y. and Wang, X.H. and Quan, R.J. and Zheng, J.J. and Yang, J. and Yang, Y.", TITLE = "Action Sensitivity Learning for Temporal Action Localization", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "13411-13423", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179907"} @inproceedings{bb184439, AUTHOR = "Barrios, W. and Soldan, M. and Ceballos Arroyo, A.M. and Heilbron, F.C. and Ghanem, B.", TITLE = "Localizing Moments in Long Video Via Multimodal Guidance", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "13621-13632", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179908"} @inproceedings{bb184440, AUTHOR = "Wang, G.Q. and Zhao, P. and Zhao, C. and Yang, S. and Cheng, J. and Leng, L. and Liao, J.X. and Guo, Q.H.", TITLE = "Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10169-10179", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179909"} @inproceedings{bb184441, AUTHOR = "Shah, A. and Lundell, B. and Sawhney, H. and Chellappa, R.", TITLE = "STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10341-10353", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179910"} @inproceedings{bb184442, AUTHOR = "Liu, Q. and Wang, Z. and Rong, S. and Li, J.J. and Zhang, Y.X.", TITLE = "Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10399-10409", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179911"} @inproceedings{bb184443, AUTHOR = "Tang, X.J. and Fan, J.S. and Luo, C.C. and Zhang, Z.X. and Zhang, M. and Yang, Z.Y.", TITLE = "DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "6599-6609", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179912"} @inproceedings{bb184444, AUTHOR = "Croitoru, I. and Bogolin, S.V. and Albanie, S. and Liu, Y. and Wang, Z.W. and Yoon, S.H. and Dernoncourt, F. and Jin, H.L. and Bui, T.", TITLE = "Moment Detection in Long Tutorial Videos", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "2594-2604", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179913"} @inproceedings{bb184445, AUTHOR = "Xia, K. and Wang, L. and Zhou, S.P. and Hua, G. and Tang, W.", TITLE = "Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10126-10135", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179914"} @inproceedings{bb184446, AUTHOR = "Geng, T.T. and Wang, T. and Duan, J.M. and Cong, R. and Zheng, F.", TITLE = "Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "22942-22951", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179915"} @inproceedings{bb184447, AUTHOR = "Zheng, W.R. and Yoshihashi, R. and Kawakami, R. and Sato, I. and Kanezaki, A.", TITLE = "Multi Event Localization by Audio-Visual Fusion with Omnidirectional Camera and Microphone Array", BOOKTITLE = MULA23, YEAR = "2023", PAGES = "2566-2574", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179916"} @inproceedings{bb184448, AUTHOR = "Moon, W.J. and Hyun, S. and Park, S.U. and Park, D. and Heo, J.P.", TITLE = "Query: Dependent Video Representation for Moment Retrieval and Highlight Detection", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "23023-23033", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179917"} @inproceedings{bb184449, AUTHOR = "Luo, D. 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-f742aloct1.html#TT179918"} @inproceedings{bb184450, AUTHOR = "Cao, S.Q. and Luo, W.X. and Wang, B. and Zhang, W. and Ma, L.", TITLE = "E2E-LOAD: End-to-End Long-form Online Action Detection", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10388-10398", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179919"} @inproceedings{bb184451, AUTHOR = "Shi, D.F. and Zhong, Y.J. and Cao, Q. and Ma, L. and Lit, J. and Tao, D.C.", TITLE = "TriDet: Temporal Action Detection with Relative Boundary Modeling", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "18857-18866", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179920"} @inproceedings{bb184452, AUTHOR = "Wang, Y. and Li, Y.D. and Wang, H.B.", TITLE = "Two-Stream Networks for Weakly-Supervised Temporal Action Localization with Semantic-Aware Mechanisms", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "18878-18887", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179921"} @inproceedings{bb184453, AUTHOR = "Zala, A. and Cho, J. and Kottur, S. and Chen, X. and Oguz, B. and Mehdad, Y. and Bansal, M.", TITLE = "Hierarchical Video-Moment Retrieval and Step-Captioning", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "23056-23065", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179922"} @inproceedings{bb184454, AUTHOR = "Ju, C. and Zheng, K. and Liu, J.X. and Zhao, P. and Zhang, Y. and Chang, J.L. and Tian, Q. and Wang, Y.F.", TITLE = "Distilling Vision-Language Pre-Training to Collaborate with Weakly-Supervised Temporal Action Localization", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "14751-14762", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179923"} @inproceedings{bb184455, AUTHOR = "Chi, H.G. and Lee, K. and Agarwal, N. and Xu, Y. and Ramani, K. and Choi, C.", TITLE = "AdamsFormer for Spatial Action Localization in the Future", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "17885-17895", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179924"} @inproceedings{bb184456, AUTHOR = "Rizve, M.N. and Mittal, G. and Yu, Y. and Hall, M. and Sajeev, S. and Shah, M. and Chen, M.", TITLE = "PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "22992-23002", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179925"} @inproceedings{bb184457, AUTHOR = "Zhou, J.Q. and Huang, L. and Wang, L. and Liu, S. and Li, H.S.", TITLE = "Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "23003-23012", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179926"} @inproceedings{bb184458, AUTHOR = "Zhao, C. and Liu, S.M. and Mangalam, K. and Ghanem, B.", TITLE = "Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "10637-10647", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179927"} @inproceedings{bb184459, AUTHOR = "Kang, H. and Kim, H. and An, J. and Cho, M. and Kim, S.J.", TITLE = "Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "6514-6523", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179928"} @inproceedings{bb184460, AUTHOR = "Seol, M. and Kim, J. and Moon, J.", TITLE = "BMRN: Boundary Matching and Refinement Network for Temporal Moment Localization with Natural Language", BOOKTITLE = ODRUM23, YEAR = "2023", PAGES = "5571-5579", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179929"} @inproceedings{bb184461, AUTHOR = "Ren, H. and Yang, W.F. and Zhang, T.Z. and Zhang, Y.D.", TITLE = "Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "2394-2404", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179930"} @inproceedings{bb184462, AUTHOR = "Ren, H.R. and Ren, H. and Lu, H. and Jin, C.", TITLE = "Weakly-Supervised Temporal Action Localization with Regional Similarity Consistency", BOOKTITLE = MMMod23, YEAR = "2023", PAGES = "I: 69-81", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179931"} @inproceedings{bb184463, AUTHOR = "Niu, Y. and Yang, J.Y. and Liang, C. and Huang, B. and Wang, Z.Y.", TITLE = "A Spatio-Temporal Identity Verification Method for Person-Action Instance Search in Movies", BOOKTITLE = MMMod23, YEAR = "2023", PAGES = "I: 82-94", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179932"} @inproceedings{bb184464, AUTHOR = "Rai, A.K. and Krishna, T. and Dietlmeier, J. and McGuinness, K. and Smeaton, A.F. and O'Connor, N.E.", TITLE = "Motion Aware Self-Supervision for Generic Event Boundary Detection", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "2727-2738", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179933"} @inproceedings{bb184465, AUTHOR = "Mahmud, T. and Marculescu, D.", TITLE = "AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "5147-5156", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179934"} @inproceedings{bb184466, AUTHOR = "Zhou, J.X. and Wu, Y.", TITLE = "Temporal Feature Enhancement Dilated Convolution Network for Weakly-supervised Temporal Action Localization", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "6017-6026", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179935"} @inproceedings{bb184467, AUTHOR = "Kang, T.K. and Lee, G.H. and Jin, K.M. and Lee, S.W.", TITLE = "Action-aware Masking Network with Group-based Attention for Temporal Action Localization", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "6047-6056", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179936"} @inproceedings{bb184468, AUTHOR = "Cao, M. and Yang, T.Y. and Weng, J.W. and Zhang, C. and Wang, J. and Zou, Y.X.", TITLE = "LocVTP: Video-Text Pre-training for Temporal Localization", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXVI:38-56", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179937"} @inproceedings{bb184469, AUTHOR = "Cheng, F. and Bertasius, G.", TITLE = "TallFormer: Temporal Action Localization with a Long-Memory Transformer", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXIV:503-521", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179938"} @inproceedings{bb184470, AUTHOR = "Kim, Y.H. and Kang, H. and Kim, S.J.", TITLE = "A Sliding Window Scheme for Online Temporal Action Localization", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXIV:653-669", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179939"} @inproceedings{bb184471, AUTHOR = "Rao, V. and Khalil, M.I. and Li, H. and Dai, P. and Lu, J.W.", TITLE = "Dual Perspective Network for Audio-Visual Event Localization", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXIV:689-704", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179940"} @inproceedings{bb184472, AUTHOR = "Huang, J. and Jin, H.L. and Gong, S.G. and Liu, Y.", TITLE = "Video Activity Localisation with Uncertainties in Temporal Boundary", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXIV:724-740", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179941"} @inproceedings{bb184473, AUTHOR = "Aakur, S. and Sarkar, S.", TITLE = "Actor-Centered Representations for Action Localization in Streaming Videos", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXVIII:70-87", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179942"} @inproceedings{bb184474, AUTHOR = "Paul, S. and Mithun, N.C. and Roy Chowdhury, A.K.", TITLE = "Text-Based Temporal Localization of Novel Events", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XIV:567-587", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179943"} @inproceedings{bb184475, AUTHOR = "Zhang, C.L. and Wu, J.X. and Li, Y.", TITLE = "ActionFormer: Localizing Moments of Actions with Transformers", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "IV:492-510", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179944"} @inproceedings{bb184476, 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-f742aloct1.html#TT179945"} @inproceedings{bb184477, AUTHOR = "Zhang, Y.H. and Doughty, H. and Shao, L. and Snoek, C.G.M.", TITLE = "Audio-Adaptive Activity Recognition Across Video Domains", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "13781-13790", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179946"} @inproceedings{bb184478, AUTHOR = "Liu, W.Z. and Tekin, B. and Coskun, H. and Vineet, V. and Fua, P. and Pollefeys, M.", TITLE = "Learning to Align Sequential Actions in the Wild", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "2171-2181", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179947"} @inproceedings{bb184479, AUTHOR = "Li, W. and Chen, S. and Gu, J.Y. and Wang, N. and Chen, C. and Guo, Y.D.", TITLE = "MV-TAL: Mulit-view Temporal Action Localization in Naturalistic Driving", BOOKTITLE = AICity22, YEAR = "2022", PAGES = "3241-3247", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179948"} @inproceedings{bb184480, AUTHOR = "Zhang, C. and Yang, T.Y. and Weng, J. and Cao, M. and Wang, J. and Zou, Y.X.", TITLE = "Unsupervised Pre-training for Temporal Action Localization Tasks", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "14011-14021", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179949"} @inproceedings{bb184481, AUTHOR = "Li, J.J. and Yang, T.Y. and Ji, W. and Wang, J. and Cheng, L.", TITLE = "Exploring Denoised Cross-video Contrast for Weakly-supervised Temporal Action Localization", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "19882-19892", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179950"} @inproceedings{bb184482, AUTHOR = "He, B. and Yang, X. and Kang, L. and Cheng, Z. and Zhou, X. and Shrivastava, A.", TITLE = "ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "13915-13925", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179951"} @inproceedings{bb184483, AUTHOR = "Xia, K. and Wang, L. and Zhou, S.P. and Zheng, N.N. and Tang, W.", TITLE = "Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "13874-13883", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179952"} @inproceedings{bb184484, AUTHOR = "Bao, W.T. and Yu, Q. and Kong, Y.", TITLE = "OpenTAL: Towards Open Set Temporal Action Localization", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "2969-2979", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179953"} @inproceedings{bb184485, AUTHOR = "Sridhar, D. and Quader, N. and Muralidharan, S. and Li, Y.X. and Dai, P. and Lu, J.W.", TITLE = "Class Semantics-based Attention for Action Detection", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13719-13728", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179954"} @inproceedings{bb184486, AUTHOR = "Huang, J. and Liu, Y. and Gong, S.G. and Jin, H.L.", TITLE = "Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "7179-7188", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179955"} @inproceedings{bb184487, AUTHOR = "Xu, M.M. and Perez Rua, J.M. and Escorcia, V. and Martinez, B. and Zhu, X.T. and Zhang, L. and Ghanem, B. and Xiang, T.", TITLE = "Boundary-sensitive Pre-training for Temporal Localization in Videos", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "7200-7210", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179956"} @inproceedings{bb184488, AUTHOR = "Nam, J. and Ahn, D.C. and Kang, D.Y. and Ha, S.J. and Choi, J.H.", TITLE = "Zero-shot Natural Language Video Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "1450-1459", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179957"} @inproceedings{bb184489, AUTHOR = "Wang, Y.X. and Gao, D.F. and Yu, L.C. and Lei, W.X. and Feiszli, M. and Shou, M.Z.", TITLE = "GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXV:709-725", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179958"} @inproceedings{bb184490, AUTHOR = "Shou, M.Z. and Lei, S.W.X. and Wang, W.Y. and Ghadiyaram, D. and Feiszli, M.", TITLE = "Generic Event Boundary Detection: A Benchmark for Event Segmentation", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "8055-8064", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179959"} @inproceedings{bb184491, AUTHOR = "Ju, C. and Zhao, P. and Chen, S. and Zhang, Y. and Wang, Y.F. and Tian, Q.", TITLE = "Divide and Conquer for Single-frame Temporal Action Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13435-13444", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179960"} @inproceedings{bb184492, AUTHOR = "Narayan, S. and Cholakkal, H. and Hayat, M. and Khan, F.S. and Yang, M.H. and Shao, L.", TITLE = "D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13588-13597", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179961"} @inproceedings{bb184493, AUTHOR = "Lee, P. and Byun, H.R.", TITLE = "Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13628-13637", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179962"} @inproceedings{bb184494, AUTHOR = "Zhao, C. and Thabet, A. and Ghanem, B.", TITLE = "Video Self-Stitching Graph Network for Temporal Action Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13638-13647", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179963"} @inproceedings{bb184495, AUTHOR = "Kang, H. and Kim, K. and Ko, Y. and Kim, S.J.", TITLE = "CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "13709-13718", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179964"} @inproceedings{bb184496, 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-f742aloct1.html#TT179965"} @inproceedings{bb184497, AUTHOR = "Trehan, S. and Aakur, S.N.", TITLE = "Towards Active Vision for Action Localization with Reactive Control and Predictive Learning", BOOKTITLE = WACV22, YEAR = "2022", PAGES = "3391-3400", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179966"} @inproceedings{bb184498, AUTHOR = "Lee, J.T. and Jain, M. and Yun, S.", TITLE = "Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "10180-10189", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179967"} @inproceedings{bb184499, AUTHOR = "Lee, J.T. and Yun, S.", TITLE = "Multi-Scale Temporal Feature Fusion for Few-Shot Action Recognition", BOOKTITLE = ICIP23, YEAR = "2023", PAGES = "1785-1789", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT179968"}