{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:24:11Z","timestamp":1763191451800,"version":"3.45.0"},"reference-count":127,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227753","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Video Moment Retrieval: A Survey"],"prefix":"10.1109","author":[{"given":"Wenwen","family":"Su","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxing","family":"Ren","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenghua","family":"Gao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitao","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haobin","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Movie gen: A cast of media foundation models","year":"2024","author":"Polyak","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3532626"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395778"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_20"},{"article-title":"A survey on natural language video localization","year":"2021","author":"Liu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref19","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00767-6_32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00225"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01248"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.733"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_34"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413975"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113791"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428369"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"article-title":"Excl: Extractive clip localization using natural language descriptions","year":"2019","author":"Ghosh","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463616"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3441577"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_36"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3110713"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00112"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref71","first-page":"28 442","article-title":"End-to-end multi-modal video temporal grounding","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"author":"Lei","key":"ref72","article-title":"Qvhighlights: Detecting moments and highlights in videos via natural language queries.(2021)"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref75","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023","journal-title":"CoRR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"article-title":"Qd-vmr: Query debiasing with contextual understanding enhancement for video moment retrieval","year":"2024","author":"Gao","key":"ref77"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413841"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3478025"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413840"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.135"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086591"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1157"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_10"},{"article-title":"Logan: Latent optimisation for generative adversarial networks","year":"2019","author":"Wu","key":"ref89"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475278"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413967"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058614"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412712"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413862"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"article-title":"Bert: a review of applications in natural language processing and understanding","year":"2021","author":"Koroteev","key":"ref99"},{"key":"ref100","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref101","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"article-title":"Videogpt: Video generation using vq-vae and transformers","year":"2021","author":"Yan","key":"ref102"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.156"},{"article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","year":"2024","author":"Qian","key":"ref105"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27832"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3390\/app14051894"},{"key":"ref108","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3340103"},{"article-title":"Hawkeye: Training video-text llms for grounding text in videos","year":"2024","author":"Wang","key":"ref110"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01332"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3581797"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681024"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"article-title":"The surprising effectiveness of multimodal large language models for video moment retrieval","year":"2024","author":"Meinardus","key":"ref118"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681115"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111670"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3521758"},{"article-title":"Trace: Temporal grounding video llm via causal event modeling","year":"2024","author":"Guo","key":"ref122"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227753.pdf?arnumber=11227753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:22:19Z","timestamp":1763191339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":127,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227753","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}