{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:06:24Z","timestamp":1784534784307,"version":"3.55.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key Research and Development Program of Shaanxi Province","award":["2025SF-YBXM-548"],"award-info":[{"award-number":["2025SF-YBXM-548"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302379"],"award-info":[{"award-number":["62302379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s10044-026-01732-w","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:42:02Z","timestamp":1784533322000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effi-TAD: efficient temporal action detection via temporal interaction and boundary-aware modeling"],"prefix":"10.1007","volume":"29","author":[{"given":"Jiayi","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongfang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"1732_CR1","doi-asserted-by":"publisher","unstructured":"Heilbron FC, Escorcia V, Ghanem B, Niebles JC (2015) ActivityNet: A large-scale video benchmark for human activity understanding. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 961\u2013 970. https:\/\/doi.org\/10.1109\/CVPR.2015.7298698","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"1732_CR2","unstructured":"Jiang Y.-G, Liu J, Zamir A.R, Toderici G, Laptev I, Shah M (2014) THUMOS challenge: action recognition with a large number of classes. Technical Report http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"1732_CR3","doi-asserted-by":"publisher","unstructured":"Yeung S, Russakovsky O, Andriluka JN, Mori M, Fei-Fei GL (2018) Every moment counts: dense detailed labeling of actions in complex videos. Int J Comput Vis 126:375\u2013389. https:\/\/doi.org\/10.1007\/s11263-017-1013-y","DOI":"10.1007\/s11263-017-1013-y"},{"key":"1732_CR4","doi-asserted-by":"publisher","unstructured":"Sigurdsson GA, Varol G, Wang X, Farhadi A, Laptev I, Gupta A (2016) Hollywood in homes: crowdsourcing data collection for activity understanding. In: Proc. Eur. Conf. Comput. Vis., pp. 510\u2013 526. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"1732_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130006","volume":"637","author":"Y Hu","year":"2025","unstructured":"Hu Y, Xia Z, Chen Z, Tsering T, Cheng J, Nyima T (2025) CITAL: counterfactual intervention for temporal action localization with point-level annotation. Neurocomputing 637:130006","journal-title":"Neurocomputing"},{"key":"1732_CR6","unstructured":"Singla G, Cook DJ, Schmitter-Edgecombe M (2008) Incorporating temporal reasoning into activity recognition for smart home residents. AAAI Workshop on Spatial and Temporal Reasoning, pp. 53\u201361"},{"key":"1732_CR7","doi-asserted-by":"publisher","unstructured":"Alyahya M, Alghannam S, Alhussan T (2022) Temporal driver action localization using action classification methods. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn. Workshops, pp. 3319\u2013 3326. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00375","DOI":"10.1109\/CVPRW56347.2022.00375"},{"key":"1732_CR8","doi-asserted-by":"publisher","unstructured":"Xu H, Das A, Saenko K (2017) R-C3D: Region convolutional 3d network for temporal activity detection. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 5783\u2013 5792. https:\/\/doi.org\/10.1109\/ICCV.2017.617","DOI":"10.1109\/ICCV.2017.617"},{"key":"1732_CR9","doi-asserted-by":"publisher","unstructured":"Zhao Y, Xiong Y, Wang L, Wu Z, Tang X, Lin D (2017) Temporal action detection with structured segment networks. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 2914\u2013 2923. https:\/\/doi.org\/10.1109\/ICCV.2017.317","DOI":"10.1109\/ICCV.2017.317"},{"key":"1732_CR10","doi-asserted-by":"crossref","unstructured":"Lin C, Xu C, Luo D, Wang Y, Tai Y.-W, Wang C, Li J, Huang F, Fu Y (2021) Learning salient boundary feature for anchor-free temporal action localization. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 3320\u2013 3329","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"1732_CR11","doi-asserted-by":"publisher","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S (2019) BMN: Boundary-matching network for temporal action proposal generation. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 3889\u2013 3898. https:\/\/doi.org\/10.1109\/ICCV.2019.00399","DOI":"10.1109\/ICCV.2019.00399"},{"key":"1732_CR12","doi-asserted-by":"publisher","unstructured":"Hou R, Chen C, Shah M (2017) Tube convolutional neural network (t-cnn) for action detection in videos. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 5822\u2013 5831. https:\/\/doi.org\/10.1109\/ICCV.2017.620","DOI":"10.1109\/ICCV.2017.620"},{"key":"1732_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C (2020) X3D: Expanding architectures for efficient video recognition. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 203\u2013 213","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"1732_CR14","doi-asserted-by":"publisher","unstructured":"Liu Z, Ning J, Cao Y, Wei Y, Zhang Z, Lin S, Hu H (2022) Video swin transformer. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 3202\u2013 3211. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00320","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"1732_CR15","doi-asserted-by":"publisher","unstructured":"Tong Z, Song Y, Wang J, Wang L (2022) VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Adv. Neural Inf. Process. Syst., vol. 35, pp. 10078\u2013 10093. https:\/\/doi.org\/10.48550\/arXiv.2203.12602","DOI":"10.48550\/arXiv.2203.12602"},{"key":"1732_CR16","doi-asserted-by":"publisher","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (2021) ViViT: A video vision transformer. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 6836\u2013 6846. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00676","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"1732_CR17","doi-asserted-by":"publisher","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? In: Proc. Int. Conf. Mach. Learn., 139: 1054\u20131064. https:\/\/doi.org\/10.48550\/arXiv.2102.05095","DOI":"10.48550\/arXiv.2102.05095"},{"key":"1732_CR18","doi-asserted-by":"publisher","first-page":"3809","DOI":"10.1007\/s13042-024-02483-y","volume":"16","author":"J Huang","year":"2025","unstructured":"Huang J, Hong C, Xie R, Ran L, Qian J (2025) A simple and efficient channel mlp on token for human pose estimation. Int J Mach Learn Cybern 16:3809\u20133817. https:\/\/doi.org\/10.1007\/s13042-024-02483-y","journal-title":"Int J Mach Learn Cybern"},{"key":"1732_CR19","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s13042-024-02262-9","volume":"16","author":"Y Xie","year":"2025","unstructured":"Xie Y, Hong C, Zhuang W, Liu L, Li J (2025) HOGFormer: high-order graph convolution transformer for 3d human pose estimation. Int J Mach Learn Cybern 16:599\u2013610. https:\/\/doi.org\/10.1007\/s13042-024-02262-9","journal-title":"Int J Mach Learn Cybern"},{"key":"1732_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103224","volume":"208\u2013209","author":"C Hong","year":"2021","unstructured":"Hong C, Chen L, Liang Y (2021) Stacked capsule graph autoencoders for geometry-aware 3d head pose estimation. Comput Vis Image Underst 208\u2013209:103224. https:\/\/doi.org\/10.1016\/j.cviu.2021.103224","journal-title":"Comput Vis Image Underst"},{"key":"1732_CR21","doi-asserted-by":"publisher","unstructured":"Xu M, Zhao C, Rojas D.S, Thabet A, Ghanem B (2020) G-TAD: Sub-graph localization for temporal action detection. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 10156\u2013 10165. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01017","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"1732_CR22","doi-asserted-by":"publisher","unstructured":"Yuan J, Ni B, Yang X, Kassim AA (2016) Temporal action localization with pyramid of score distribution features. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 3093\u2013 3102. https:\/\/doi.org\/10.1109\/CVPR.2016.337","DOI":"10.1109\/CVPR.2016.337"},{"key":"1732_CR23","doi-asserted-by":"publisher","unstructured":"Heilbron F.C, Barrios W, Escorcia V, Ghanem B (2017) SCC: Semantic context cascade for efficient action detection. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 3175\u2013 3184. https:\/\/doi.org\/10.1109\/CVPR.2017.338","DOI":"10.1109\/CVPR.2017.338"},{"key":"1732_CR24","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1109\/LSP.2020.3037796","volume":"27","author":"X Liu","year":"2020","unstructured":"Liu X, Sun Y, Lu J, Yao C, Zhou Y (2020) Self-similarity action proposal. IEEE Signal Process Lett 27:2064\u20132068. https:\/\/doi.org\/10.1109\/LSP.2020.3037796","journal-title":"IEEE Signal Process Lett"},{"key":"1732_CR25","doi-asserted-by":"publisher","unstructured":"Liu X, Hu Y, Bai S, Ding F, Bai X, Torr PHS (2021) Multi-shot temporal event localization: a benchmark. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 12596\u2013 12606. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01241","DOI":"10.1109\/CVPR46437.2021.01241"},{"key":"1732_CR26","doi-asserted-by":"publisher","unstructured":"Chao Y.-W, Vijayanarasimhan S, Seybold B, Ross D.A, Deng J, Sukthankar R (2018) Rethinking the faster r-cnn architecture for temporal action localization. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 1130\u2013 1139. https:\/\/doi.org\/10.1109\/CVPR.2018.00124","DOI":"10.1109\/CVPR.2018.00124"},{"key":"1732_CR27","doi-asserted-by":"publisher","unstructured":"Buch S, Escorcia V, Shen C, Ghanem B, Niebles JC (2017) SST: Single-stream temporal action proposals. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 2911\u2013 2920. https:\/\/doi.org\/10.1109\/CVPR.2017.675","DOI":"10.1109\/CVPR.2017.675"},{"key":"1732_CR28","doi-asserted-by":"publisher","first-page":"9413","DOI":"10.1007\/s13042-025-02761-3","volume":"16","author":"X Lee","year":"2025","unstructured":"Lee X, Hong C, Zhang X, Chen Y (2025) DroFormer: temporal action detection with drop mechanism of attention. Int J Mach Learn Cybern 16:9413\u20139428. https:\/\/doi.org\/10.1007\/s13042-025-02761-3","journal-title":"Int J Mach Learn Cybern"},{"key":"1732_CR29","doi-asserted-by":"publisher","unstructured":"Tang Y, Niu C, Dong M, Ren S, Liang J (2019) AFO-TAD: anchor-free one-stage detector for temporal action detection. arXiv preprint arXiv:1910.08250. https:\/\/doi.org\/10.48550\/arXiv.1910.08250","DOI":"10.48550\/arXiv.1910.08250"},{"key":"1732_CR30","doi-asserted-by":"publisher","unstructured":"Zhang C.-L, Wu J, Li Y (2022) ActionFormer: Localizing moments of actions with transformers. In: Proc. Eur. Conf. Comput. Vis., pp. 492\u2013 510. https:\/\/doi.org\/10.1007\/978-3-031-19772-7_29","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"1732_CR31","doi-asserted-by":"publisher","unstructured":"Shi D, Zhong Y, Cao Q, Ma L, Li J, Tao D (2023) TriDet: temporal action detection with relative boundary modeling. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 18857\u2013 18866. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01808","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"1732_CR32","doi-asserted-by":"publisher","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M (2018) BSN: boundary sensitive network for temporal action proposal generation. In: Proc. Eur. Conf. Comput. Vis., pp. 3\u2013 19. https:\/\/doi.org\/10.48550\/arXiv.1806.02964","DOI":"10.48550\/arXiv.1806.02964"},{"key":"1732_CR33","doi-asserted-by":"publisher","unstructured":"Cheng F, Bertasius G (2022) TallFormer: Temporal action localization with a long-memory transformer. In: Proc. Eur. Conf. Comput. Vis., pp. 503\u2013 521. https:\/\/doi.org\/10.1007\/978-3-031-19830-4_29","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"1732_CR34","doi-asserted-by":"publisher","unstructured":"Zhao C, Liu S, Mangalam K, Ghanem B (2023) $$\\text{Re}^2$$TAL: Rewiring pretrained video backbones for reversible temporal action localization. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 10637\u201310647. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01025","DOI":"10.1109\/CVPR52729.2023.01025"},{"key":"1732_CR35","doi-asserted-by":"publisher","unstructured":"Liu S, Zhang C.-L, Zhao C, Ghanem B (2024) End-to-end temporal action detection with 1b parameters across 1000 frames. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 18591\u2013 18601. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01759","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"1732_CR36","doi-asserted-by":"publisher","unstructured":"Zhao C, Liu S, Mangalam K, Qian G, Zohra F, Alghannam A, Malik J, Ghanem B (2024) $$\\text{ DR}^2$$Net: Dynamic reversible dual-residual networks for memory-efficient finetuning. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 15835\u2013 15844. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01499","DOI":"10.1109\/CVPR52733.2024.01499"},{"key":"1732_CR37","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu X, Wang Q, Hu Y, Tang X, Zhang S, Bai S, Bai X (2022) End-to-end temporal action detection with transformer. IEEE Trans Image Process 31:5427\u20135441","journal-title":"IEEE Trans Image Process"},{"key":"1732_CR38","doi-asserted-by":"publisher","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Soft-NMS: Improving object detection with one line of code. In: Proc. IEEE Int. Conf. Comput. Vis.. https:\/\/doi.org\/10.1109\/ICCV.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"1732_CR39","doi-asserted-by":"publisher","unstructured":"Bai Y, Wang Y, Tong Y, Yang Y, Liu Q, Liu J (2020) Boundary content graph neural network for temporal action proposal generation. In: Proc. Eur. Conf. Comput. Vis., pp. 121\u2013 137. https:\/\/doi.org\/10.48550\/arXiv.2008.01432","DOI":"10.48550\/arXiv.2008.01432"},{"key":"1732_CR40","doi-asserted-by":"publisher","unstructured":"Tan J, Tang J, Wang L, Wu G (2021) Relaxed transformer decoders for direct action proposal generation. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 13526\u2013 13535. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01327","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"1732_CR41","doi-asserted-by":"publisher","unstructured":"Shao J, Wang X, Quan R, Zheng J, Yang J, Yang Y (2023) Action sensitivity learning for temporal action localization. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 13411\u2013 13423. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01238","DOI":"10.1109\/ICCV51070.2023.01238"},{"key":"1732_CR42","doi-asserted-by":"publisher","unstructured":"Wang L, Huang B, Zhao Z, Tong Z, He Y, Wang Y, Wang Y, Qiao Y (2023) VideoMAE V2: Scaling video masked autoencoders with dual masking. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 14549\u2013 14560. https:\/\/doi.org\/10.1109\/ICCV48922.2023.01398","DOI":"10.1109\/ICCV48922.2023.01398"},{"key":"1732_CR43","doi-asserted-by":"publisher","unstructured":"Liu X, Bai S, Bai X (2022) An empirical study of end-to-end temporal action detection. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 20010\u2013 20019. https:\/\/doi.org\/10.48550\/arXiv.2204.02932","DOI":"10.48550\/arXiv.2204.02932"},{"key":"1732_CR44","doi-asserted-by":"publisher","unstructured":"Yang M, Chen G, Zheng Y.-D., Lu T, Wang L (2023) Basic-TAD: An astounding rgb-only baseline for temporal action detection. Comput. Vis. Image Underst. 232, 103692 https:\/\/doi.org\/10.48550\/arXiv.2205.02717","DOI":"10.48550\/arXiv.2205.02717"},{"key":"1732_CR45","doi-asserted-by":"publisher","unstructured":"Yang M, Gao H, Guo P, Wang L. Adapting short-term transformers for action detection in untrimmed videos. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 18570\u2013 18579 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01757","DOI":"10.1109\/CVPR52733.2024.01757"},{"key":"1732_CR46","doi-asserted-by":"publisher","unstructured":"Zeng R, Huang W, Tan M, Rong Y, Zhao P, Huang J, Gan C (2019) Graph convolutional networks for temporal action localization. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 7094\u2013 7103. https:\/\/doi.org\/10.1109\/ICCV.2019.00719","DOI":"10.1109\/ICCV.2019.00719"},{"key":"1732_CR47","doi-asserted-by":"publisher","unstructured":"Zhu Z, Tang W, Wang L, Zheng N, Hua G (2021) Enriching local and global contexts for temporal action localization. In: Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 13516\u2013 13525. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01326","DOI":"10.1109\/ICCV48922.2021.01326"},{"key":"1732_CR48","doi-asserted-by":"publisher","unstructured":"Zhu Y, Zhang G, Tan J, Wu G, Wang L (2024) Dual detrs for multi-label temporal action detection. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 18559\u2013 18569. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01756","DOI":"10.1109\/CVPR52733.2024.01756"},{"key":"1732_CR49","doi-asserted-by":"publisher","unstructured":"Dai R, Das S, Minciullo L, Garattoni L, Francesca G, Br\u00e9mond F (2021) PDAN: pyramid dilated attention network for action detection. In: Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis., pp. 2970\u2013 2979. https:\/\/doi.org\/10.1109\/WACV48630.2021.00301","DOI":"10.1109\/WACV48630.2021.00301"},{"key":"1732_CR50","doi-asserted-by":"publisher","unstructured":"Kahatapitiya K, Ryoo MS (2021) Coarse-fine networks for temporal activity detection in videos. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 8385\u2013 8394. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00828","DOI":"10.1109\/CVPR46437.2021.00828"},{"key":"1732_CR51","doi-asserted-by":"publisher","unstructured":"Dai R, Das S, Kahatapitiya K, Ryoo M.S, Br\u00e9mond F (2022) MS-TCT: Multi-scale temporal convtransformer for action detection. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn., pp. 20041\u201320051. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01941","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"1732_CR52","doi-asserted-by":"crossref","unstructured":"Tan J, Zhao X, Shi X, Kang B, Wang L (2022) PointTAD: Multi-label temporal action detection with learnable query points. Adv Neural Inf Process Syst 35:15268\u201315280. https:\/\/doi.org\/10.48550\/arXiv.2210.11035","DOI":"10.52202\/068431-1111"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01732-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01732-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01732-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:42:06Z","timestamp":1784533326000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01732-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["1732"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01732-w","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"26 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"148"}}