@article{bb206400,
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#TT201728"}
@article{bb206401,
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#TT201729"}
@article{bb206402,
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#TT201730"}
@article{bb206403,
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#TT201731"}
@article{bb206404,
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#TT201732"}
@article{bb206405,
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#TT201733"}
@article{bb206406,
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#TT201734"}
@article{bb206407,
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#TT201735"}
@article{bb206408,
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#TT201736"}
@article{bb206409,
AUTHOR = "Sun, C. and Chen, M. and Zhu, C.B. and Zhang, S. and Lu, P. and Chen, J.C.",
TITLE = "Listen With Seeing: Cross-Modal Contrastive Learning for Audio-Visual
Event Localization",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2650-2665",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201737"}
@article{bb206410,
AUTHOR = "Liu, Y. and Wu, Q. and Zeng, M. and Liu, Y. and Pan, Y.Y.",
TITLE = "FASTEN: Video Event Localization Based on Audio-Visual Feature
Alignment and Multi-Scale Temporal Enhancement",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2010-2014",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201738"}
@article{bb206411,
AUTHOR = "Zhang, L. and Song, P.P. and Duan, Z.L. and Wang, S. and Chang, X.J. and Yang, X.",
TITLE = "Video Corpus Moment Retrieval With Query-Specific Context Learning
and Progressive Localization",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "6",
MONTH = "June",
PAGES = "5659-5670",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201739"}
@article{bb206412,
AUTHOR = "Zhou, W. and Lin, K. and Hu, W.P. and Xie, C. and Su, T. and Hu, H.F. and Tan, Y.P.",
TITLE = "Snippet-Inter Difference Attention Network for Weakly-Supervised
Temporal Action Localization",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "3610-3624",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201740"}
@article{bb206413,
AUTHOR = "Li, J.X. and Ma, T.C. and Yang, X.H. and Yang, L.J. and Zheng, C.",
TITLE = "Video Complicated-Information Extraction and Filtering Network for
Weakly-Supervised Temporal Action Localization",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2334-2338",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201741"}
@article{bb206414,
AUTHOR = "Gao, Z.L. and Wang, Q.L. and Zhang, B.B. and Hu, Q.H. and Li, P.H.",
TITLE = "A^2M^2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action
Recognition",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5363-5378",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201742"}
@article{bb206415,
AUTHOR = "Liu, H.M. and Li, X. and Fan, B. and Xu, J.L.",
TITLE = "BRTAL: Boundary Refinement Temporal Action Localization via
Offset-Driven Diffusion Models",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "8174-8186",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201743"}
@article{bb206416,
AUTHOR = "Zhang, P. and Shi, P. and He, X.",
TITLE = "Audio-Visual Event Localization With Cross Co-Attention and Dynamic
Audio-Object Semantic Alignment",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3152-3156",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201744"}
@article{bb206417,
AUTHOR = "Zhang, J. and Yu, Y. and Mao, Y. and Ren, Y.G.",
TITLE = "Event-level multimodal feature fusion for audio-visual event
localization",
JOURNAL = IVC,
VOLUME = "161",
YEAR = "2025",
PAGES = "105610",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201745"}
@article{bb206418,
AUTHOR = "Geng, T.T. and Wang, T. and Duan, J.M. and Zhang, Y. and Guan, W. and Zheng, F. and Shao, L.",
TITLE = "UniAV: Unified Audio-Visual Perception for Multi-Task Video Event
Localization",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "10280-10294",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201746"}
@article{bb206419,
AUTHOR = "Feng, Q. and Li, W. and Lin, T. and Chen, X.H.",
TITLE = "Full-Stage Pseudo Label Quality Enhancement for Weakly-Supervised
Temporal Action Localization",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11144-11157",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201747"}
@article{bb206420,
AUTHOR = "Gao, J. and Zhou, S.P. and Yu, H. and Li, C.Y. and Hu, X.X.",
TITLE = "SCESS-Net: Semantic consistency enhancement and segment selection
network for audio-visual event localization",
JOURNAL = CVIU,
VOLUME = "262",
YEAR = "2025",
PAGES = "104551",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201748"}
@article{bb206421,
AUTHOR = "Xu, J.L. and Zhang, Y.Q. and Zhou, W.H. and Liu, H.M.",
TITLE = "BFSTAL: Bidirectional Feature Splitting With Cross-Layer Fusion for
Temporal Action Localization",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "12707-12718",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201749"}
@inproceedings{bb206422,
AUTHOR = "Chen, X.Y. and Guo, Y. and Liang, J.M. and Zhuang, S.T. and Zeng, R. and Hu, X.P.",
TITLE = "Temporal Action Detection Model Compression by Progressive Block Drop",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29225-29236",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201750"}
@inproceedings{bb206423,
AUTHOR = "Khosla, S. and V, S.T. and Schwing, A. and Hoiem, D.",
TITLE = "Relocate: A Simple Training-Free Baseline for Visual Query
Localization Using Region-Based Representations",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3697-3706",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201751"}
@inproceedings{bb206424,
AUTHOR = "Zhang, Q. and Fang, J. and Yuan, R. and Tang, X. and Qi, Y.X. and Zhang, K. and Yuan, C.",
TITLE = "Weakly Supervised Temporal Action Localization via Dual-Prior
Collaborative Learning Guided by Multimodal Large Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24139-24148",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201752"}
@inproceedings{bb206425,
AUTHOR = "Liu, L. and Li, S. and Zhu, Y.Q.",
TITLE = "Audio-Visual Semantic Graph Network for Audio-Visual Event
Localization",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23957-23966",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201753"}
@inproceedings{bb206426,
AUTHOR = "Liu, M. and Wang, L. and Zhou, S.P. and Xia, K. and Sun, X.L. and Hua, G.",
TITLE = "Boosting Point-Supervised Temporal Action Localization through
Integrating Query Reformation and Optimal Transport",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13865-13875",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201754"}
@inproceedings{bb206427,
AUTHOR = "Zhang, G. and Fok, M.L.A. and Ma, J. and Xia, Y. and Cremers, D. and Torr, P. and Tresp, V. and Gu, J.D.",
TITLE = "Localizing Events in Videos with Multimodal Queries",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3339-3351",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201755"}
@inproceedings{bb206428,
AUTHOR = "Zhou, J.X. and Guo, D. and Guo, R. and Mao, Y.X. and Hu, J.J. and Zhong, Y.R. and Chang, X.J. and Wang, M.",
TITLE = "Towards Open-Vocabulary Audio-Visual Event Localization",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8362-8371",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201756"}
@inproceedings{bb206429,
AUTHOR = "Liu, Z. and Liu, Y.",
TITLE = "Bridge the Gap: From Weak to Full Supervision for Temporal Action
Localization with PseudoFormer",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8711-8720",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201757"}
@inproceedings{bb206430,
AUTHOR = "Diko, A. and Wang, T. and Swaileh, W. and Sun, S.Y. and Patras, I.",
TITLE = "ReWind: Understanding Long Videos with Instructed Learnable Memory",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13734-13743",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201758"}
@inproceedings{bb206431,
AUTHOR = "Hyun, J. and Han, S.H. and Kang, H. and Lee, J.Y. and Kim, S.J.",
TITLE = "Exploring Scalability of Self-Training for Open-Vocabulary Temporal
Action Localization",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9406-9415",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201759"}
@inproceedings{bb206432,
AUTHOR = "Bao, W.T. and Li, K. and Chen, Y.X. and Patel, D. and Min, M.R.Q. and Kong, Y.",
TITLE = "Exploiting VLM Localizability and Semantics for Open Vocabulary
Action Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8291-8301",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201760"}
@inproceedings{bb206433,
AUTHOR = "Gupta, A. and Mittal, G. and Magooda, A. and Yu, Y. and Taylor, G.W. and Chen, M.",
TITLE = "LoSA: Long-Short-Range Adapter for Scaling End-to-End Temporal Action
Localization",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "2092-2102",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201761"}
@inproceedings{bb206434,
AUTHOR = "Pujol Perich, D. and Clapes, A. and Escalera, S.",
TITLE = "SADA: Semantic Adversarial Unsupervised Domain Adaptation for
Temporal Action Localization",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9237-9247",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201762"}
@inproceedings{bb206435,
AUTHOR = "Abdullah, H.M. and Liu, T. and Wei, K. and Kong, S. and Huang, R.",
TITLE = "UAL-Bench: The First Comprehensive Unusual Activity Localization
Benchmark",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5801-5811",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201763"}
@inproceedings{bb206436,
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#TT201764"}
@inproceedings{bb206437,
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#TT201765"}
@inproceedings{bb206438,
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#TT201766"}
@inproceedings{bb206439,
AUTHOR = "Kwon, D. and Kim, I.H. and Kwak, S.",
TITLE = "Boosting Semi-Supervised Video Action Detection with Temporal Context",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "847-858",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201767"}
@inproceedings{bb206440,
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#TT201768"}
@inproceedings{bb206441,
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#TT201769"}
@inproceedings{bb206442,
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#TT201770"}
@inproceedings{bb206443,
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#TT201771"}
@inproceedings{bb206444,
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#TT201772"}
@inproceedings{bb206445,
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#TT201773"}
@inproceedings{bb206446,
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#TT201774"}
@inproceedings{bb206447,
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#TT201775"}
@inproceedings{bb206448,
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#TT201776"}
@inproceedings{bb206449,
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#TT201777"}
@inproceedings{bb206450,
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#TT201778"}
@inproceedings{bb206451,
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#TT201779"}
@inproceedings{bb206452,
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#TT201780"}
@inproceedings{bb206453,
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#TT201781"}
@inproceedings{bb206454,
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#TT201782"}
@inproceedings{bb206455,
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#TT201783"}
@inproceedings{bb206456,
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#TT201784"}
@inproceedings{bb206457,
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#TT201785"}
@inproceedings{bb206458,
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#TT201786"}
@inproceedings{bb206459,
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#TT201787"}
@inproceedings{bb206460,
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#TT201788"}
@inproceedings{bb206461,
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#TT201789"}
@inproceedings{bb206462,
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#TT201790"}
@inproceedings{bb206463,
AUTHOR = "Lee, S.B. and Moon, W.J. and Seong, H.S. and Heo, J.P.",
TITLE = "Temporal Alignment-Free Video Matching for Few-Shot Action
Recognition",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "5412-5421",
BIBSOURCE = "http://www.visionbib.com/bibliography/motion-f742aloct1.html#TT201791"}
@inproceedings{bb206464,
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#TT201792"}
@inproceedings{bb206465,
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#TT201793"}
@inproceedings{bb206466,
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#TT201794"}
@inproceedings{bb206467,
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#TT201795"}
@inproceedings{bb206468,
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#TT201796"}
@inproceedings{bb206469,
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#TT201797"}
@inproceedings{bb206470,
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#TT201798"}
@inproceedings{bb206471,
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#TT201799"}
@inproceedings{bb206472,
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#TT201800"}
@inproceedings{bb206473,
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#TT201801"}
@inproceedings{bb206474,
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#TT201802"}
@inproceedings{bb206475,
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#TT201803"}
@inproceedings{bb206476,
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#TT201804"}
@inproceedings{bb206477,
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#TT201805"}
@inproceedings{bb206478,
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#TT201806"}
@inproceedings{bb206479,
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#TT201807"}
@inproceedings{bb206480,
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#TT201808"}
@inproceedings{bb206481,
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#TT201809"}
@inproceedings{bb206482,
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#TT201810"}
@inproceedings{bb206483,
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#TT201811"}
@inproceedings{bb206484,
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#TT201812"}
@inproceedings{bb206485,
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#TT201813"}
@inproceedings{bb206486,
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#TT201814"}
@inproceedings{bb206487,
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#TT201815"}
@inproceedings{bb206488,
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#TT201816"}
@inproceedings{bb206489,
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#TT201817"}
@inproceedings{bb206490,
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#TT201818"}
@inproceedings{bb206491,
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#TT201819"}
@inproceedings{bb206492,
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#TT201820"}
@inproceedings{bb206493,
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#TT201821"}
@inproceedings{bb206494,
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#TT201822"}
@inproceedings{bb206495,
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#TT201823"}
@inproceedings{bb206496,
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#TT201824"}
@inproceedings{bb206497,
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#TT201825"}
@inproceedings{bb206498,
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#TT201826"}
@inproceedings{bb206499,
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#TT201827"}
Last update:Dec 17, 2025 at 15:38:33