{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T18:38:23Z","timestamp":1792521503216,"version":"4.5.0"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","award":["Major Program MP202404"],"award-info":[{"award-number":["Major Program MP202404"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436002"],"award-info":[{"award-number":["62436002"]}],"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":["62276061"],"award-info":[{"award-number":["62276061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109615","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:15:29Z","timestamp":1788948929000},"page":"109615","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["VLG-RMOT: Calibration-before-control for end-to-end referring multi-object tracking"],"prefix":"10.1016","volume":"205","author":[{"given":"Hongshen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-0035","authenticated-orcid":false,"given":"Ming","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2733-2393","authenticated-orcid":false,"given":"Fei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuncong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109615_bib0001","series-title":"European conference on computer vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.109615_bib0002","first-page":"1","article-title":"Multigranularity localization transformer with collaborative understanding for referring multiobject tracking","volume":"74","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109615_bib0003","doi-asserted-by":"crossref","first-page":"2618","DOI":"10.1609\/aaai.v39i3.32265","article-title":"Multi-task visual grounding with coarse-to-fine consistency constraints","volume":"39","author":"Dai","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109615_bib0004","doi-asserted-by":"crossref","first-page":"121670","DOI":"10.52202\/079017-3867","article-title":"Simvg: A simple framework for visual grounding with decoupled multi-modal fusion","volume":"37","author":"Dai","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0005","doi-asserted-by":"crossref","first-page":"7900","DOI":"10.1109\/TPAMI.2022.3217852","article-title":"Vlt: Vision-language transformer and query generation for referring segmentation","volume":"45","author":"Ding","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109615_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19135","article-title":"Ikun: Speak to trackers without retraining","author":"Du","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0007","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.52202\/068431-0321","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0008","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109615_bib0009","series-title":"Ieee international conference on acoustics, speech and signal processing","first-page":"6310","article-title":"Visual-linguistic representation learning with deep cross-modality fusion for referring multi-object tracking","author":"He","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0010","series-title":"Ieee international conference on acoustics, speech and signal processing","first-page":"10332","article-title":"Tell me what to track: Infusing robust language guidance for enhanced referring multi-object tracking","author":"Huang","year":"2026"},{"key":"10.1016\/j.neunet.2026.109615_bib0011","first-page":"8646","article-title":"Language-aware spatial-temporal collaboration for referring video segmentation","volume":"45","author":"Hui","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109615_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13619","article-title":"Dn-detr: Accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109615_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"23626","article-title":"Language decoupling with fine-grained knowledge guidance for referring multi-object tracking","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109615_bib0014","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107606","article-title":"Recognizing human\u2013object interactions in videos with the supervision of natural language","volume":"190","author":"Li","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109615_bib0016","unstructured":"Li, W., Du, Y., Yin, Q., Zhao, Z., & Su, F. (2025c). Cpany: Couple with any encoder to refer multi-object tracking. arXiv: 2503.07516v1."},{"key":"10.1016\/j.neunet.2026.109615_bib0017","series-title":"2025\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"6816","article-title":"Lamot: Language-guided multi-object tracking","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109615_bib0018","doi-asserted-by":"crossref","first-page":"10055","DOI":"10.1109\/TPAMI.2023.3262578","article-title":"Local-global context aware transformer for language-guided video segmentation","volume":"45","author":"Liang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109615_bib0019","doi-asserted-by":"crossref","first-page":"3182","DOI":"10.1109\/TIP.2022.3165376","article-title":"Rethinking the competition between detection and reid in multiobject tracking","volume":"31","author":"Liang","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109615_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103349","article-title":"Cognitive disentanglement for referring multi-object tracking","author":"Liang","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109615_bib0021","doi-asserted-by":"crossref","first-page":"18964","DOI":"10.1109\/TITS.2024.3437645","article-title":"Echotrack: Auditory referring multi-object tracking for autonomous driving","volume":"25","author":"Lin","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0022","series-title":"Computer vision\u2013ECCV 2014: 13th european conference, zurich, switzerland, september 6\u201312, 2014, proceedings, part v 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109615_bib0023","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4673","article-title":"Learning to assemble neural module tree networks for visual grounding","author":"Liu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109615_bib0024","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","volume":"32","author":"Liu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0025","series-title":"European conference on computer vision","first-page":"38","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0026","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019c). RoBERTa: A robustly optimized BERT pretraining approach. arXiv: 1907.11692."},{"key":"10.1016\/j.neunet.2026.109615_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107673","article-title":"LaTP: LiDAR-aided multimodal token pruning for efficient trajectory prediction of autonomous driving","volume":"190","author":"Lu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109615_bib0028","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","article-title":"Hota: A higher order metric for evaluating multi-object tracking","volume":"129","author":"Luiten","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109615_bib0029","unstructured":"Ma, Z., Yang, S., Cui, Z., Zhao, Z., Su, F., Liu, D., & Wang, J. (2024). Mls-track: Multilevel semantic interaction in rmot. arXiv: 2404.12031."},{"key":"10.1016\/j.neunet.2026.109615_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8844","article-title":"Trackformer: Multi-object tracking with transformers","author":"Meinhardt","year":"2022"},{"key":"10.1016\/j.neunet.2026.109615_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107202","article-title":"Sample-efficient and occlusion-robust reinforcement learning for robotic manipulation via multimodal fusion dualization and representation normalization","volume":"185","author":"Noh","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109615_bib0032","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109615_bib0033","series-title":"The thirteenth international conference on learning representations","first-page":"1","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2025"},{"key":"10.1016\/j.neunet.2026.109615_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10417","article-title":"Video object grounding using semantic roles in language description","author":"Sadhu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109615_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19208","article-title":"Context-aware integration of language and visual references for natural language tracking","author":"Shao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1346","article-title":"Co-grounding networks with semantic attention for referring expression comprehension in videos","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.109615_bib0037","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., & Luo, P. (2021). Transtrack: Multiple object tracking with transformer. arXiv: 2012.15460."},{"key":"10.1016\/j.neunet.2026.109615_bib0038","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109615_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19175","article-title":"Image as a foreign language: Beit pretraining for vision and vision-language tasks","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109615_bib0040","series-title":"2017\u202fIEEE International conference on image processing (ICIP)","first-page":"3645","article-title":"Simple online and realtime tracking with a deep association metric","author":"Wojke","year":"2017"},{"key":"10.1016\/j.neunet.2026.109615_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14633","article-title":"Referring multi-object tracking","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109615_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4974","article-title":"Language as queries for referring video object segmentation","author":"Wu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109615_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4818","article-title":"Florence-2: Advancing a unified representation for a variety of vision tasks","author":"Xiao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0044","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.1109\/TCSVT.2025.3615851","article-title":"Temporal-enhanced multimodal transformer for referring multi-object tracking and segmentation","volume":"36","author":"Xiao","year":"2026","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109615_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19113","article-title":"Diffusiontrack: Point set diffusion model for visual object tracking","author":"Xie","year":"2024"},{"key":"10.1016\/j.neunet.2026.109615_bib0046","doi-asserted-by":"crossref","first-page":"10681","DOI":"10.1109\/TPAMI.2024.3448254","article-title":"Correlation-embedded transformer tracking: A single-branch framework","volume":"46","author":"Xie","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109615_bib0047","article-title":"Enhancing referring multi-object tracking via language guidance and temporal representation","author":"Xu","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109615_bib0048","unstructured":"Yan, F., Luo, W., Zhong, Y., Gan, Y., & Ma, L. (2023). Bridging the gap between end-to-end and non-end-to-end multi-object tracking. arXiv: 2305.12724."},{"key":"10.1016\/j.neunet.2026.109615_bib0049","series-title":"European conference on computer vision","first-page":"659","article-title":"Motr: End-to-end multiple-object tracking with transformer","author":"Zeng","year":"2022"},{"key":"10.1016\/j.neunet.2026.109615_bib0050","series-title":"International conference on learning representations","first-page":"1","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109615_bib0051","series-title":"European conference on computer vision","first-page":"1","article-title":"Bytetrack: Multi-object tracking by associating every detection box","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109615_bib0052","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","article-title":"Fairmot: On the fairness of detection and re-identification in multiple object tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109615_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22056","article-title":"Motrv2: Bootstrapping end-to-end multi-object tracking by pretrained object detectors","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109615_bib0054","unstructured":"Zhang, Y., Wu, D., Han, W., & Dong, X. (2025). Bootstrapping referring multi-object tracking. arXiv: 2406.05039."},{"key":"10.1016\/j.neunet.2026.109615_bib0055","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10528","article-title":"Hff-tracker: A hierarchical fine-grained fusion tracker for referring multi-object tracking","author":"Zhao","year":"2025"},{"key":"10.1016\/j.neunet.2026.109615_bib0056","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23151","article-title":"Joint visual grounding and tracking with natural language specification","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109615_bib0057","series-title":"International conference on learning representations","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109615_bib0058","doi-asserted-by":"crossref","first-page":"11337","DOI":"10.1109\/TCSVT.2025.3576341","article-title":"Cgatracker: Correlation-aware graph alignment for referring multi-object tracking","volume":"35","author":"Zhuang","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010725?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010725?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:39:10Z","timestamp":1792517950000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026010725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":58,"alternative-id":["S0893608026010725"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109615","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VLG-RMOT: Calibration-before-control for end-to-end referring multi-object tracking","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109615","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109615"}}