{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T09:26:12Z","timestamp":1774257972080,"version":"3.50.1"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650009","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Unifying Global and Local Scene Entities Modelling for Precise Action Spotting"],"prefix":"10.1109","author":[{"given":"Kim Hoang","family":"Tran","sequence":"first","affiliation":[{"name":"FPT Software AI Center,Vietnam"}]},{"given":"Phuc","family":"Vuong Do","sequence":"additional","affiliation":[{"name":"Naver Vietnam Dev Center,Vietnam"}]},{"given":"Ngoc Quoc","family":"Ly","sequence":"additional","affiliation":[{"name":"VNUHCM-University of Science,Ho Chi Minh City,Vietnam"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,Department of Computer Science,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_17"},{"key":"ref5","volume":"abs\/2204.02674","author":"Chen","year":"2022","journal-title":"Faster-tad: Towards temporal action detection with proposal generation and classification in a unified network"},{"key":"ref6","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01314"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00511"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"ref10","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00506"},{"key":"ref18","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2022","journal-title":"ICLR"},{"key":"ref19","author":"He","year":"2021","journal-title":"Gta: Global temporal attention for video action understanding"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_3"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICLR","author":"Jia","year":"2021"},{"key":"ref24","volume":"abs\/1705.06950","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref25","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref28","author":"Liu","year":"2023","journal-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref33","author":"Nakkiran","year":"2020","journal-title":"Learning rate annealing can provably help generalization, even for convex problems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","volume":"139","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897256"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref44","author":"Tan","year":"2020","journal-title":"Efficientnet: Rethinking model scaling for convolutional neural networks"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412268"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Aei: Actors-environment interaction with adaptive attention for temporal action proposals generation","author":"Vo","year":"2021","journal-title":"BMVC"},{"key":"ref50","article-title":"Aoe-net: Entities interactions modeling with adaptive attention mechanism for temporal action proposals generation","author":"Vo","year":"2022","journal-title":"IJCV"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25412"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref55","article-title":"Asformer: Transformer for action segmentation","author":"Yi","year":"2021","journal-title":"BMVC"},{"key":"ref56","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018","journal-title":"ICLR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref58","author":"Zhou","year":"2021","journal-title":"Feature combination meets attention: Baidu soccer embeddings and transformer based temporal detection"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3552437.3555693"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650009.pdf?arnumber=10650009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:54:25Z","timestamp":1725944065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650009","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}