@article{bb198000, 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#TT193387"} @article{bb198001, 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#TT193388"} @article{bb198002, 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#TT193389"} @article{bb198003, 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#TT193390"} @article{bb198004, AUTHOR = "Li, Q. and Zu, G. and Xu, H. and Kong, J. and Zhang, Y. and Wang, J.Z.", TITLE = "An Adaptive Dual Selective Transformer for Temporal Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "7398-7412", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193391"} @article{bb198005, AUTHOR = "Yang, S. and Wu, X.X. and Shang, Z. and Luo, J.B.", TITLE = "Dynamic Pathway for Query-Aware Feature Learning in Language-Driven Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "7451-7461", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193392"} @article{bb198006, AUTHOR = "Mokari, M. and Sadeghi, K.H.", TITLE = "Enhancing temporal action localization in an end-to-end network through estimation error incorporation", JOURNAL = IVC, VOLUME = "145", YEAR = "2024", PAGES = "104994", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193393"} @article{bb198007, AUTHOR = "Cao, C.Q. and Wang, Y.Z. and Zhang, Y. and Lu, Y. and Zhang, X. and Zhang, Y.N.", TITLE = "Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization", JOURNAL = CirSysVideo, VOLUME = "34", YEAR = "2024", NUMBER = "5", MONTH = "May", PAGES = "3327-3339", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193394"} @article{bb198008, AUTHOR = "Hu, X.J. and Wang, S.J. and Li, M. and Li, Y. and Du, S.", TITLE = "Time-attentive fusion network: An efficient model for online detection of action start", JOURNAL = IET-IPR, VOLUME = "18", YEAR = "2024", NUMBER = "7", PAGES = "1892-1902", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193395"} @article{bb198009, AUTHOR = "Yang, J. and Wei, P. and Zheng, N.N.", TITLE = "Cross Time-Frequency Transformer for Temporal Action Localization", JOURNAL = CirSysVideo, VOLUME = "34", YEAR = "2024", NUMBER = "6", MONTH = "June", PAGES = "4625-4638", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193396"} @article{bb198010, 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-f742aloct1.html#TT193397"} @article{bb198011, AUTHOR = "Tang, Y.P. and Wang, W.N. and Zhang, C.J. and Liu, J. and Zhao, Y.", TITLE = "Learnable Feature Augmentation Framework for Temporal Action Localization", JOURNAL = IP, VOLUME = "33", YEAR = "2024", PAGES = "4002-4015", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193398"} @article{bb198012, 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-f742aloct1.html#TT193399"} @article{bb198013, AUTHOR = "Vahdani, E. and Tian, Y.L.", TITLE = "POTLoc: Pseudo-label Oriented Transformer for point-supervised temporal Action Localization", JOURNAL = CVIU, VOLUME = "246", YEAR = "2024", PAGES = "104044", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193400"} @article{bb198014, AUTHOR = "Zhang, T.Y. and Li, R. and Feng, P.M. and Zhang, R.", TITLE = "Integration of Global and Local Knowledge for Foreground Enhancing in Weakly Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "8476-8487", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193401"} @article{bb198015, AUTHOR = "Chen, Z.M. and Jin, X. and Chan, S.X.", TITLE = "SiSe: Simultaneous and Sequential Transformers for multi-label activity recognition", JOURNAL = PR, VOLUME = "156", YEAR = "2024", PAGES = "110844", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193402"} @article{bb198016, AUTHOR = "Chen, L. and Zhang, J. and Zhang, Y.F. and Kang, J.P. and Zhuo, L.", TITLE = "MKP-Net: Memory knowledge propagation network for point-supervised temporal action localization in livestreaming", JOURNAL = CVIU, VOLUME = "248", YEAR = "2024", PAGES = "104109", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193403"} @article{bb198017, AUTHOR = "Wang, Y. and Zhao, S.J. and Chen, S.W.", TITLE = "Action-Semantic Consistent Knowledge for Weakly-Supervised Action Localization", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "10279-10289", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193404"} @inproceedings{bb198018, AUTHOR = "Helvaci, H.I. and Chuah, C.N. and Ozonoff, S. and Cheung, S.C.S.", TITLE = "Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder", BOOKTITLE = ICIP24, YEAR = "2024", PAGES = "3841-3847", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193405"} @article{bb198019, AUTHOR = "Raza, A. and Yang, B. and Zou, Y.X.", TITLE = "Zero-Shot Temporal Action Detection by Learning Multimodal Prompts and Text-Enhanced Actionness", JOURNAL = CirSysVideo, VOLUME = "34", YEAR = "2024", NUMBER = "11", MONTH = "November", PAGES = "11000-11012", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193406"} @article{bb198020, AUTHOR = "Wang, Y. and Zhao, S.J. and Chen, S.W.", TITLE = "SQL-Net: Semantic Query Learning for Point-Supervised Temporal Action Localization", JOURNAL = MultMed, VOLUME = "27", YEAR = "2025", PAGES = "84-94", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193407"} @article{bb198021, AUTHOR = "Du, J.R. and Feng, J.C. and Lin, K.Y. and Hong, F.T. and Qi, Z.A. and Shan, Y. and Hu, J.F. and Zheng, W.S.", TITLE = "Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning", JOURNAL = CirSysVideo, VOLUME = "35", YEAR = "2025", NUMBER = "1", MONTH = "January", PAGES = "938-952", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193408"} @article{bb198022, AUTHOR = "Liu, Y.Y. and Zhou, N. and Huang, Y.X. and Liu, S.Y. and Liu, L.Y. and Zhou, W. and Tang, C. and Wang, K.", TITLE = "Beyond boundaries: Hierarchical-contrast unsupervised temporal action localization with high-coupling feature learning", JOURNAL = PR, VOLUME = "162", YEAR = "2025", PAGES = "111421", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193409"} @article{bb198023, 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-f742aloct1.html#TT193410"} @article{bb198024, 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-f742aloct1.html#TT193411"} @article{bb198025, AUTHOR = "Sheng, J.R. and Li, A. and Ge, Y.X.", TITLE = "Summarized knowledge guidance for single-frame temporal action localization", JOURNAL = PRL, VOLUME = "191", YEAR = "2025", PAGES = "31-36", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193412"} @inproceedings{bb198026, AUTHOR = "Yang, L. and Zheng, Z.W. and Han, Y.Z. and Cheng, H. and Song, S. and Huang, G. and Li, F.", TITLE = "Dyfadet: Dynamic Feature Aggregation for Temporal Action Detection", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "XLVI: 305-322", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193413"} @inproceedings{bb198027, AUTHOR = "Zeng, Y.S. and Zhong, Y.J. and Feng, C.J. and Ma, L.", TITLE = "Unimd: Towards Unifying Moment Retrieval and Temporal Action Detection", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "XLVI: 286-304", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193414"} @inproceedings{bb198028, AUTHOR = "Liu, M.N. and Wang, L. and Zhou, S.P. and Xia, K. and Wu, Q. and Zhang, Q. and Hua, G.", TITLE = "Stepwise Multi-grained Boundary Detector for Point-supervised Temporal Action Localization", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "VII: 333-349", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193415"} @inproceedings{bb198029, AUTHOR = "Lee, J. and Kim, T. and Lee, I. and Shim, M.H. and Wee, D.Y. and Cho, M. and Kwak, S.", TITLE = "Classification Matters: Improving Video Action Detection with Class-specific Attention", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "XX: 450-467", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193416"} @inproceedings{bb198030, AUTHOR = "Song, Y.K. and Kim, D.K. and Cho, M. and Kwak, S.", TITLE = "Online Temporal Action Localization with Memory-augmented Transformer", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "XIX: 74-91", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193417"} @inproceedings{bb198031, AUTHOR = "Reza, S. and Zhang, Y.X. and Moghaddam, M. and Camps, O.", TITLE = "Hat: History-augmented Anchor Transformer for Online Temporal Action Localization", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "XXI: 205-222", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193418"} @inproceedings{bb198032, AUTHOR = "Zhou, F.X. and Williams, B. and Rahmani, H.", TITLE = "Towards Adaptive Pseudo-label Learning for Semi-supervised Temporal Action Localization", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "LXII: 320-338", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193419"} @inproceedings{bb198033, AUTHOR = "Huang, D.A. and Liao, S. and Radhakrishnan, S. and Yin, H.X. and Molchanov, P. and Yu, Z. and Kautz, J.", TITLE = "Lita: Language Instructed Temporal-localization Assistant", BOOKTITLE = ECCV24, YEAR = "2024", PAGES = "LXIV: 202-218", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193420"} @inproceedings{bb198034, AUTHOR = "Rahman, M.S. and Shihab, I.F. and Chu, L. and Sharma, A.", TITLE = "DeepLocalization: Using change point detection for Temporal Action Localization", BOOKTITLE = AICity24, YEAR = "2024", PAGES = "7252-7260", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193421"} @inproceedings{bb198035, AUTHOR = "Xia, Z. and Cheng, J. and Liul, S. and Hu, Y.X. and Wang, S.G. and Zhang, Y.J. and Dang, L.", TITLE = "Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization", BOOKTITLE = CVPR24, YEAR = "2024", PAGES = "18440-18450", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193422"} @inproceedings{bb198036, AUTHOR = "Liberatori, B. and Conti, A. and Rota, P. and Wang, Y.M. and Ricci, E.", TITLE = "Test-Time Zero-Shot Temporal Action Localization", BOOKTITLE = CVPR24, YEAR = "2024", PAGES = "18720-18729", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193423"} @inproceedings{bb198037, AUTHOR = "Ntinoutl, I. and Sanchez, E. and Tzimiropoulos, G.", TITLE = "Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-Stage Action Localization", BOOKTITLE = CVPR24, YEAR = "2024", PAGES = "18827-18836", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193424"} @inproceedings{bb198038, AUTHOR = "Hu, X. and Li, K. and Patel, D. and Kruus, E. and Min, M.R. and Ding, Z.M.", TITLE = "Weakly-Supervised Temporal Action Localization with Multi-Modal Plateau Transformers", BOOKTITLE = L3D-IVU24, YEAR = "2024", PAGES = "2704-2713", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193425"} @inproceedings{bb198039, AUTHOR = "Gritsenko, A.A. and Xiong, X. and Djolonga, J. and Dehghani, M. and Sun, C. and Lucic, M. and Schmid, C. and Arnab, A.", TITLE = "End-to-End Spatio-Temporal Action Localisation with Video Transformers", BOOKTITLE = CVPR24, YEAR = "2024", PAGES = "18373-18383", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193426"} @inproceedings{bb198040, AUTHOR = "Yang, A. and Miech, A. and Sivic, J. and Laptev, I. and Schmid, C.", TITLE = "TubeDETR: Spatio-Temporal Video Grounding with Transformers", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "16421-16432", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193427"} @inproceedings{bb198041, AUTHOR = "Zhang, Z.J. and Palmero, C. and Escalera, S.", TITLE = "DualH: A Dual Hierarchical Model for Temporal Action Localization", BOOKTITLE = FG24, YEAR = "2024", PAGES = "1-10", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193428"} @inproceedings{bb198042, 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-f742aloct1.html#TT193429"} @inproceedings{bb198043, AUTHOR = "Denize, J. and Liashuha, M. and Rabarisoa, J. and Orcesi, A. and Herault, R.", TITLE = "COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting Using Transformers", BOOKTITLE = Pretrain24, YEAR = "2024", PAGES = "518-528", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193430"} @inproceedings{bb198044, 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-f742aloct1.html#TT193431"} @inproceedings{bb198045, AUTHOR = "Rahman, M.A. and Laganiere, R.", TITLE = "Spatio-Temporal Activity Detection via Joint Optimization of Spatial and Temporal Localization", BOOKTITLE = RWSurvil24, YEAR = "2024", PAGES = "242-250", BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT193432"} @inproceedings{bb198046, 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#TT193433"} @inproceedings{bb198047, 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#TT193434"} @inproceedings{bb198048, 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#TT193435"} @inproceedings{bb198049, 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#TT193436"} @inproceedings{bb198050, 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#TT193437"} @inproceedings{bb198051, 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#TT193438"} @inproceedings{bb198052, 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#TT193439"} @inproceedings{bb198053, AUTHOR = "Liu, Q.Y. and Wang, Z. and Rong, S.H. 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#TT193440"} @inproceedings{bb198054, 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#TT193441"} @inproceedings{bb198055, 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#TT193442"} @inproceedings{bb198056, 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#TT193443"} @inproceedings{bb198057, AUTHOR = "Geng, T.T. and Wang, T. and Duan, J.M. and Cong, R.M. 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#TT193444"} @inproceedings{bb198058, 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#TT193445"} @inproceedings{bb198059, 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#TT193446"} @inproceedings{bb198060, 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#TT193447"} @inproceedings{bb198061, 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#TT193448"} @inproceedings{bb198062, 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#TT193449"} @inproceedings{bb198063, 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#TT193450"} @inproceedings{bb198064, 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#TT193451"} @inproceedings{bb198065, 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#TT193452"} @inproceedings{bb198066, 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#TT193453"} @inproceedings{bb198067, 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#TT193454"} @inproceedings{bb198068, 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#TT193455"} @inproceedings{bb198069, 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#TT193456"} @inproceedings{bb198070, 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#TT193457"} @inproceedings{bb198071, 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#TT193458"} @inproceedings{bb198072, 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#TT193459"} @inproceedings{bb198073, 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#TT193460"} @inproceedings{bb198074, 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#TT193461"} @inproceedings{bb198075, 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#TT193462"} @inproceedings{bb198076, 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#TT193463"} @inproceedings{bb198077, 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#TT193464"} @inproceedings{bb198078, 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#TT193465"} @inproceedings{bb198079, 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#TT193466"} @inproceedings{bb198080, 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#TT193467"} @inproceedings{bb198081, 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#TT193468"} @inproceedings{bb198082, 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#TT193469"} @inproceedings{bb198083, 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#TT193470"} @inproceedings{bb198084, 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#TT193471"} @inproceedings{bb198085, 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#TT193472"} @inproceedings{bb198086, 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#TT193473"} @inproceedings{bb198087, 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#TT193474"} @inproceedings{bb198088, 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#TT193475"} @inproceedings{bb198089, 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#TT193476"} @inproceedings{bb198090, 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#TT193477"} @inproceedings{bb198091, 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#TT193478"} @inproceedings{bb198092, 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#TT193479"} @inproceedings{bb198093, AUTHOR = "He, B. and Yang, X.T. and Kang, L. and Cheng, Z.Y. 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#TT193480"} @inproceedings{bb198094, 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#TT193481"} @inproceedings{bb198095, 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#TT193482"} @inproceedings{bb198096, 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#TT193483"} @inproceedings{bb198097, 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#TT193484"} @inproceedings{bb198098, 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#TT193485"} @inproceedings{bb198099, 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#TT193486"}