{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:28:27Z","timestamp":1779906507877,"version":"3.53.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00095","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"907-916","source":"Crossref","is-referenced-by-count":1,"title":["Saliency-Guided DETR for Moment Retrieval and Highlight Detection"],"prefix":"10.1109","author":[{"given":"Aleksandr","family":"Gordeev","sequence":"first","affiliation":[{"name":"SALUTEDEV LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Dokholyan","sequence":"additional","affiliation":[{"name":"SALUTEDEV LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irina","family":"Tolstykh","sequence":"additional","affiliation":[{"name":"SALUTEDEV LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maksim","family":"Kuprashevich","sequence":"additional","affiliation":[{"name":"SALUTEDEV LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"ref3","article-title":"The surprising effectiveness of multimodal large language models for video moment retrieval","author":"Boris","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"ref5","article-title":"Align-detr: Improving detr with simple iou-aware bce loss","author":"Cai","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475707"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"ref17","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref20","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref22","article-title":"R2-tuning: Efficient image-to-video transfer learning for video temporal grounding","volume":"abs\/2404.00801","author":"Liu","year":"2024","journal-title":"ArXiv"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref25","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref39","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref40","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref42","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103911"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref45","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref47","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref48","first-page":"4","article-title":"Detrs with collaborative hybrid assignments training. arxiv 2022","author":"Zong","year":"2022"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492119.pdf?arnumber=11492119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:03Z","timestamp":1778047623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00095","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}