@inproceedings{bb214300,
        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#TT209598"}

@inproceedings{bb214301,
        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#TT209599"}

@inproceedings{bb214302,
        AUTHOR = "Liberatori, B. and Conti, A. and Vaquero, L. and Rota, P. and Wang, Y.M. and Ricci, E.",
        TITLE = "Zero-Shot Temporal Action Localization Through Textual Guidance",
        BOOKTITLE = FG26,
        YEAR = "2026",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209600"}

@inproceedings{bb214303,
        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#TT209601"}

@inproceedings{bb214304,
        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#TT209602"}

@inproceedings{bb214305,
        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#TT209603"}

@inproceedings{bb214306,
        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#TT209604"}

@inproceedings{bb214307,
        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#TT209605"}

@inproceedings{bb214308,
        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#TT209606"}

@inproceedings{bb214309,
        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#TT209607"}

@inproceedings{bb214310,
        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#TT209608"}

@inproceedings{bb214311,
        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#TT209609"}

@inproceedings{bb214312,
        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#TT209610"}

@inproceedings{bb214313,
        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#TT209611"}

@inproceedings{bb214314,
        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#TT209612"}

@inproceedings{bb214315,
        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#TT209613"}

@inproceedings{bb214316,
        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#TT209614"}

@inproceedings{bb214317,
        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#TT209615"}

@inproceedings{bb214318,
        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#TT209616"}

@inproceedings{bb214319,
        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#TT209617"}

@inproceedings{bb214320,
        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#TT209618"}

@inproceedings{bb214321,
        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#TT209619"}

@inproceedings{bb214322,
        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#TT209620"}

@inproceedings{bb214323,
        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#TT209621"}

@inproceedings{bb214324,
        AUTHOR = "Kang, H. and Kim, H. and An, J.B. 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#TT209622"}

@inproceedings{bb214325,
        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#TT209623"}

@inproceedings{bb214326,
        AUTHOR = "Niu, Y.R. 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#TT209624"}

@inproceedings{bb214327,
        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#TT209625"}

@inproceedings{bb214328,
        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#TT209626"}

@inproceedings{bb214329,
        AUTHOR = "Kim, H.J. and Lee, Y. and Hong, J.H. and Lee, S.W.",
        TITLE = "DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region
Integrated Decoder for Temporal Action Detection Transformer",
        BOOKTITLE = CVPR25,
        YEAR = "2025",
        PAGES = "24286-24296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209627"}

@inproceedings{bb214330,
        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#TT209628"}

@inproceedings{bb214331,
        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#TT209629"}

@inproceedings{bb214332,
        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#TT209630"}

@inproceedings{bb214333,
        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#TT209631"}

@inproceedings{bb214334,
        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#TT209632"}

@inproceedings{bb214335,
        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#TT209633"}

@inproceedings{bb214336,
        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#TT209634"}

@inproceedings{bb214337,
        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#TT209635"}

@inproceedings{bb214338,
        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#TT209636"}

@inproceedings{bb214339,
        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#TT209637"}

@inproceedings{bb214340,
        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#TT209638"}

@inproceedings{bb214341,
        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#TT209639"}

@inproceedings{bb214342,
        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#TT209640"}

@inproceedings{bb214343,
        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#TT209641"}

@inproceedings{bb214344,
        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#TT209642"}

@inproceedings{bb214345,
        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#TT209643"}

@inproceedings{bb214346,
        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#TT209644"}

@inproceedings{bb214347,
        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#TT209645"}

@inproceedings{bb214348,
        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#TT209646"}

@inproceedings{bb214349,
        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#TT209647"}

@inproceedings{bb214350,
        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#TT209648"}

@inproceedings{bb214351,
        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#TT209649"}

@inproceedings{bb214352,
        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#TT209650"}

@inproceedings{bb214353,
        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#TT209651"}

@inproceedings{bb214354,
        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#TT209652"}

@inproceedings{bb214355,
        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#TT209653"}

@inproceedings{bb214356,
        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#TT209654"}

@inproceedings{bb214357,
        AUTHOR = "Kim, H. and Jain, M. and Lee, J.T. and Yun, S. and Porikli, F.M.",
        TITLE = "Efficient Action Recognition via Dynamic Knowledge Propagation",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "13699-13708",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209655"}

@inproceedings{bb214358,
        AUTHOR = "Hsieh, H.Y. and Chen, D.J. and Liu, T.L.",
        TITLE = "Contextual Proposal Network for Action Localization",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "766-775",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209656"}

@inproceedings{bb214359,
        AUTHOR = "Li, Z.H. and Yao, L.",
        TITLE = "Three Birds with One Stone: Multi-Task Temporal Action Detection via
Recycling Temporal Annotations",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "4749-4758",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209657"}

@inproceedings{bb214360,
        AUTHOR = "Liu, X.L. and Hu, Y. and Bai, S. and Ding, F. and Bai, X. and Torr, P.H.S.",
        TITLE = "Multi-shot Temporal Event Localization: a Benchmark",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12591-12601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209658"}

@inproceedings{bb214361,
        AUTHOR = "Lin, C.M. and Xu, C.M. and Luo, D.H. and Wang, Y.B. and Tai, Y. and Wang, C.J. and Li, J.L. and Huang, F.Y. and Fu, Y.W.",
        TITLE = "Learning Salient Boundary Feature for Anchor-free Temporal Action
Localization",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "3319-3328",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209659"}

@inproceedings{bb214362,
        AUTHOR = "Tirupattur, P. and Duarte, K. and Rawat, Y.S. and Shah, M.",
        TITLE = "Modeling Multi-Label Action Dependencies for Temporal Action
Localization",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "1460-1470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209660"}

@inproceedings{bb214363,
        AUTHOR = "Lopcz Sastrc, R.J. and Baptista Rios, M. and Rodriguez, F.J. .A. and Martin Martin, P. and Maldonado Bascon, S.",
        TITLE = "Live Video Action Recognition from Unsupervised Action Proposals",
        BOOKTITLE = MVA21,
        YEAR = "2021",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209661"}

@inproceedings{bb214364,
        AUTHOR = "Rodriguez Opazo, C. and Marrese Taylor, E. and Fernando, B. and Li, H.D. and Gould, S.",
        TITLE = "DORi: Discovering Object Relationships for Moment Localization of a
Natural Language Query in a Video",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "1078-1087",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209662"}

@inproceedings{bb214365,
        AUTHOR = "Rotsidis, A. and Lutteroth, C. and Hall, P. and Richardt, C.",
        TITLE = "ExMaps: Long-Term Localization in Dynamic Scenes using Exponential
Decay",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "2866-2875",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209663"}

@inproceedings{bb214366,
        AUTHOR = "Vaudaux Ruth, G. and Tong, A.C.H. and Achard, C.",
        TITLE = "SALAD: Self-Assessment Learning for Action Detection",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "1268-1277",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209664"}

@inproceedings{bb214367,
        AUTHOR = "Vaudaux Ruth, G. and Tong, A.C.H. and Achard, C.",
        TITLE = "ActionSpotter: Deep Reinforcement Learning Framework for Temporal
Action Spotting in Videos",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "631-638",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209665"}

@inproceedings{bb214368,
        AUTHOR = "Lu, C.K. and Li, R.M. and Fu, H. and Fu, B. and Wang, Y.H. and Lo, W.L. and Chi, Z.",
        TITLE = "Precise Temporal Localization for Complete Actions with Quantified
Temporal Structure",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4781-4788",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209666"}

@inproceedings{bb214369,
        AUTHOR = "Lin, Y.B. and Wang, Y.C.A.F.",
        TITLE = "Audiovisual Transformer with Instance Attention for Audio-visual Event
Localization",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "VI:274-290",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209667"}

@inproceedings{bb214370,
        AUTHOR = "Long, F. and Yao, T. and Qiu, Z.F. and Tian, X.M. and Luo, J.B. and Mei, T.",
        TITLE = "Learning to Localize Actions from Moments",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "III:137-154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209668"}

@inproceedings{bb214371,
        AUTHOR = "Aakur, S. and Sarkar, S.",
        TITLE = "Action Localization Through Continual Predictive Learning",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIV:300-317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209669"}

@inproceedings{bb214372,
        AUTHOR = "Chen, S.X. and Jiang, Y.G.",
        TITLE = "Hierarchical Visual-textual Graph for Temporal Activity Localization
via Language",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XX:601-618",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209670"}

@inproceedings{bb214373,
        AUTHOR = "Yang, P.W. and Hu, V.T. and Mettes, P.S. and Snoek, C.G.M.",
        TITLE = "Localizing the Common Action Among a Few Videos",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "VII:505-521",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209671"}

@inproceedings{bb214374,
        AUTHOR = "Toering, M. and Gatopoulos, I. and Stol, M. and Hu, V.T.",
        TITLE = "Self-supervised Video Representation Learning with Cross-Stream
Prototypical Contrasting",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "846-856",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209672"}

@inproceedings{bb214375,
        AUTHOR = "Kanth, R.K. and Ramaswamy, A. and Kumar, A.A. and Gubbi, J. and Balamuralidhar, P.",
        TITLE = "STP-Net: Spatio-Temporal Polarization Network for action recognition
using polarimetric videos",
        BOOKTITLE = ComputationalApp22,
        YEAR = "2022",
        PAGES = "767-776",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209673"}

@inproceedings{bb214376,
        AUTHOR = "Ramaswamy, A. and Seemakurthy, K. and Gubbi, J. and Balamuralidhar, P.",
        TITLE = "Video action re-localization using spatio-temporal correlation",
        BOOKTITLE = Activity22,
        YEAR = "2022",
        PAGES = "192-201",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209674"}

@inproceedings{bb214377,
        AUTHOR = "Ramaswamy, A. and Seemakurthy, K. and Gubbi, J. and Purushothaman, B.",
        TITLE = "Spatio-temporal action detection and localization using a
hierarchical LSTM",
        BOOKTITLE = DeepVision20,
        YEAR = "2020",
        PAGES = "3303-3312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209675"}

@inproceedings{bb214378,
        AUTHOR = "Gong, G.Q. and Wang, X.H. and Mu, Y.D. and Tian, Q.",
        TITLE = "Learning Temporal Co-Attention Models for Unsupervised Video Action
Localization",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9816-9825",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209676"}

@inproceedings{bb214379,
        AUTHOR = "Jain, M. and Ghodrati, A. and Snoek, C.G.M.",
        TITLE = "ActionBytes: Learning From Trimmed Videos to Localize Actions",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "1168-1177",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209677"}

@inproceedings{bb214380,
        AUTHOR = "Eun, H.J. and Moon, J.Y. and Park, J.Y. and Jung, C. and Kim, C.",
        TITLE = "Learning to Discriminate Information for Online Action Detection",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "806-815",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209678"}

@inproceedings{bb214381,
        AUTHOR = "Rodriguez Opazo, C. and Marrese Taylor, E. and Saleh, F.S. and Li, H.D. and Gould, S.",
        TITLE = "Proposal-free Temporal Moment Localization of a Natural-Language
Query in Video using Guided Attention",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "2453-2462",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209679"}

@inproceedings{bb214382,
        AUTHOR = "Wehrmann, J. and Lopes, M.A. and Souza, D. and Barros, R.",
        TITLE = "Language-Agnostic Visual-Semantic Embeddings",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "5803-5812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209680"}

@inproceedings{bb214383,
        AUTHOR = "Pramono, R.R.A. and Chen, Y. and Fang, W.",
        TITLE = "Hierarchical Self-Attention Network for Action Localization in Videos",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "61-70",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209681"}

@inproceedings{bb214384,
        AUTHOR = "Wang, W.N. and Huang, Y. and Wang, L.",
        TITLE = "Language-Driven Temporal Activity Localization:
A Semantic Matching Reinforcement Learning Model",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "334-343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209682"}

@inproceedings{bb214385,
        AUTHOR = "Li, H. and Yang, J. and Zhou, Y. and Li, S.",
        TITLE = "Rethinking Temporal Structure Modeling Method for Temporal Action
Localization",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3676-3680",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209683"}

@inproceedings{bb214386,
        AUTHOR = "Vial, R. and Zhu, H. and Tian, Y. and Lu, S.",
        TITLE = "Search video action proposal with recurrent and static YOLO",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "2035-2039",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209684"}

@inproceedings{bb214387,
        AUTHOR = "Shao, D. and Xiong, Y. and Zhao, Y. and Huang, Q.Q. and Qiao, Y. and Lin, D.",
        TITLE = "Find and Focus: Retrieve and Localize Video Events with Natural
Language Queries",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "IX: 202-218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209685"}

@inproceedings{bb214388,
        AUTHOR = "Yang, J. and Yuan, J.",
        TITLE = "Common Action Discovery and Localization in Unconstrained Videos",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2176-2185",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209686"}

@inproceedings{bb214389,
        AUTHOR = "Sharir, G. and Tuytelaars, T.",
        TITLE = "Action in chains:
A chains model for action localization and classification",
        BOOKTITLE = WACV14,
        YEAR = "2014",
        PAGES = "610-617",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209687"}

@inproceedings{bb214390,
        AUTHOR = "Lan, T. and Wang, Y. and Mori, G.",
        TITLE = "Discriminative figure-centric models for joint action localization and
recognition",
        BOOKTITLE = ICCV11,
        YEAR = "2011",
        PAGES = "2003-2010",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209688"}

@inproceedings{bb214391,
        AUTHOR = "Ta, A.P. and Wolf, C. and Lavoue, G. and Baskurt, A. and Jolion, J.M.",
        TITLE = "Pairwise Features for Human Action Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "3224-3227",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209689"}

@inproceedings{bb214392,
        AUTHOR = "Ta, A.P. and Wolf, C. and Lavoue, G. and Baskurt, A.",
        TITLE = "Recognizing and Localizing Individual Activities through Graph Matching",
        BOOKTITLE = AVSS10,
        YEAR = "2010",
        PAGES = "196-203",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT209690"}

@article{bb214393,
        AUTHOR = "Zeng, R.H. and Gan, C. and Chen, P.H. and Huang, W.B. and Wu, Q.Y. and Tan, M.K.",
        TITLE = "Breaking Winner-Takes-All: Iterative-Winners-Out Networks for Weakly
Supervised Temporal Action Localization",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5797-5808",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209691"}

@article{bb214394,
        AUTHOR = "Kumar, N. and Sukavanam, N.",
        TITLE = "Weakly supervised deep network for spatiotemporal localization and
detection of human actions in wild conditions",
        JOURNAL = VC,
        VOLUME = "36",
        YEAR = "2020",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1809-1821",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209692"}

@article{bb214395,
        AUTHOR = "Qin, X.L. and Ge, Y.X. and Yu, H. and Chen, F.Y. and Yang, D.",
        TITLE = "Spatial Enhancement and Temporal Constraint for Weakly Supervised
Action Localization",
        JOURNAL = SPLetters,
        VOLUME = "27",
        YEAR = "2020",
        PAGES = "1520-1524",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209693"}

@article{bb214396,
        AUTHOR = "Yu, J.R. and Ge, Y.X. and Qin, X.L. and Li, Z.Q. and Huang, S. and Chen, F.Y.",
        TITLE = "Deep feature enhancing and selecting network for weakly supervised
temporal action localization",
        JOURNAL = JVCIR,
        VOLUME = "80",
        YEAR = "2021",
        PAGES = "103276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209694"}

@article{bb214397,
        AUTHOR = "Ge, Y.X. and Qin, X.L. and Yang, D. and Jagersand, M.",
        TITLE = "Deep snippet selective network for weakly supervised temporal action
localization",
        JOURNAL = PR,
        VOLUME = "110",
        YEAR = "2021",
        PAGES = "107686",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209695"}

@article{bb214398,
        AUTHOR = "Zhang, S.W. and Song, L. and Gao, C.X. and Sang, N.",
        TITLE = "GLNet: Global Local Network for Weakly Supervised Action Localization",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2610-2622",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209696"}

@article{bb214399,
        AUTHOR = "Zhang, X.Y. and Shi, H.C. and Li, C.S. and Li, P. and Li, Z.K. and Ren, P.",
        TITLE = "Weakly-supervised action localization via embedding-modeling
iterative optimization",
        JOURNAL = PR,
        VOLUME = "113",
        YEAR = "2021",
        PAGES = "107831",
        BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742wsal3.html#TT209697"}