{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:39:56Z","timestamp":1775284796124,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61625107"],"award-info":[{"award-number":["61625107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702130"],"award-info":[{"award-number":["61702130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Projects of the Ministry of Science and Technology","award":["2020YFC0832500"],"award-info":[{"award-number":["2020YFC0832500"]}]},{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","award":["2020GXNSFAA159137"],"award-info":[{"award-number":["2020GXNSFAA159137"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017530","name":"Major Scientific Research Project of Zhejiang Laboratory","doi-asserted-by":"publisher","award":["2018EC0ZX01"],"award-info":[{"award-number":["2018EC0ZX01"]}],"id":[{"id":"10.13039\/501100017530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3052086","type":"journal-article","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T23:00:39Z","timestamp":1611356439000},"page":"2538-2548","source":"Crossref","is-referenced-by-count":34,"title":["Interaction-Integrated Network for Natural Language Moment Localization"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6682-2224","authenticated-orcid":false,"given":"Ke","family":"Ning","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref72","first-page":"1984","article-title":"Excl: Extractive clip localization using natural language descriptions","volume":"1","author":"ghosh","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref70","first-page":"536","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","author":"yuan","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref39","first-page":"1","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601835"},{"key":"ref37","first-page":"469","article-title":"Question-guided hybrid convolution for visual question answering","author":"gao","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref62","first-page":"552","article-title":"Temporal modular networks for retrieving complex compositional activities in videos","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref61","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2846664"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.08.016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref1","article-title":"YouTube-8M: A large-scale video classification benchmark","volume":"abs 1609 8675","author":"abu-el-haija","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref22","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref21","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref50","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref51","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref58","first-page":"510","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref57","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"abs 1502 3167","author":"ioffe","year":"2015","journal-title":"CoRR"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref54","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref52","article-title":"Hypernetworks","volume":"abs 1609 9106","author":"ha","year":"2016","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601883"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref40","first-page":"6594","article-title":"Modulating early visual processing by language","author":"de vries","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.09.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref18","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"jiang","year":"2014","journal-title":"Proc ECCV Int Workshop Competition Action Recognit Large Number Classes"},{"key":"ref19","article-title":"The kinetics human action video dataset","volume":"abs 1705 6950","author":"kay","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2972108"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref49","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"oord","year":"2016","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09334438.pdf?arnumber=9334438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:03Z","timestamp":1652194203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9334438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3052086","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}