{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T12:54:49Z","timestamp":1781528089159,"version":"3.54.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104519","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:34:05Z","timestamp":1780418045000},"page":"104519","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Listen2Track: Plug-and-play audio-visual matching for generic multi-object tracking"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5434-3223","authenticated-orcid":false,"given":"Yeqiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8423-1214","authenticated-orcid":false,"given":"Weiran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4451-1130","authenticated-orcid":false,"given":"Yijie","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7075-9766","authenticated-orcid":false,"given":"Mina","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6772-8525","authenticated-orcid":false,"given":"Fukuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7204-7708","authenticated-orcid":false,"given":"Yining","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7493-1324","authenticated-orcid":false,"given":"Wenxu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2914-1192","authenticated-orcid":false,"given":"Zhenbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104519_bib0001","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.inffus.2026.104519_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9686","article-title":"Observation-centric sort: rethinking sort for robust multi-object tracking","author":"Cao","year":"2023"},{"key":"10.1016\/j.inffus.2026.104519_bib0003","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.inffus.2026.104519_bib0004","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12155","article-title":"AVSegFormer: audio-visual segmentation with transformer","volume":"38","author":"Gao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104519_bib0005","unstructured":"Z. Ge, S. Liu, F. Wang, Z. Li, J. Sun, YOLOX: exceeding YOLO series in 2021, arXiv preprint arXiv: 2107.08430(2021)."},{"key":"10.1016\/j.inffus.2026.104519_bib0006","series-title":"2016 IEEE International Conference on Image Processing (ICIP)","first-page":"3464","article-title":"Simple online and realtime tracking","author":"Bewley","year":"2016"},{"key":"10.1016\/j.inffus.2026.104519_bib0007","series-title":"2017 IEEE 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.inffus.2026.104519_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6768","article-title":"A unified object motion and affinity model for online multi-object tracking","author":"Yin","year":"2020"},{"key":"10.1016\/j.inffus.2026.104519_bib0009","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"27883","article-title":"Multiple object tracking as id prediction","author":"Gao","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0010","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"11687","article-title":"Focusing on tracks for online multi-object tracking","author":"Shim","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0011","unstructured":"L. Jia, Y. Wu, B. Ran, Y. Wang, L. Wang, H. Lu, AR-MOT: autoregressive multi-object tracking, arXiv preprint arXiv: 2601.01925(2026)."},{"key":"10.1016\/j.inffus.2026.104519_bib0012","unstructured":"C. Li, J. Ma, L. Shen, Y. Chen, L. Chen, Occlusion-aware SORT: observing occlusion for robust multi-object tracking, arXiv preprint arXiv: 2603.06034(2026)."},{"key":"10.1016\/j.inffus.2026.104519_bib0013","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"10045","article-title":"Avot: audio-visual object tracking of multiple objects for robotics","author":"Wilson","year":"2020"},{"issue":"11","key":"10.1016\/j.inffus.2026.104519_bib0014","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 Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.inffus.2026.104519_bib0015","series-title":"European Conference on Computer Vision","first-page":"386","article-title":"Audio\u2013visual segmentation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.inffus.2026.104519_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27134","article-title":"Cooperation does matter: exploring multi-order bilateral relations for audio-visual segmentation","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104519_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Robust audio-visual segmentation via audio-guided visual convergent alignment","author":"Liu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Dynamic derivation and elimination: audio visual segmentation with enhanced audio semantics","author":"Liu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0019","unstructured":"Y. Zhu, Y. Wang, Y. Hong, R. Guo, K. Ding, X. Gu, B. Fan, S. Xiang, SeaVIS: sound-enhanced association for online audio-visual instance segmentation, arXiv preprint arXiv: 2603.01431(2026)."},{"key":"10.1016\/j.inffus.2026.104519_bib0020","unstructured":"J. Seo, H. Kwon, K. Kim, J. Lee, K. Sohn, Learning what to hear: boosting sound-source association for robust audiovisual instance segmentation, arXiv preprint arXiv: 2509.22740(2025)."},{"key":"10.1016\/j.inffus.2026.104519_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19067","article-title":"Semantic and sequential alignment for referring video object segmentation","author":"Pan","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0022","series-title":"European Conference on Computer Vision","first-page":"225","article-title":"Unified embedding alignment for open-vocabulary video instance segmentation","author":"Fang","year":"2024"},{"issue":"1","key":"10.1016\/j.inffus.2026.104519_bib0023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2996463","article-title":"Fixation prediction through multimodal analysis","volume":"13","author":"Min","year":"2016","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.inffus.2026.104519_bib0024","doi-asserted-by":"crossref","first-page":"3805","DOI":"10.1109\/TIP.2020.2966082","article-title":"A multimodal saliency model for videos with high audio-visual correspondence","volume":"29","author":"Min","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104519_bib0025","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1109\/TMM.2023.3271022","article-title":"Unified audio-visual saliency model for omnidirectional videos with spatial audio","volume":"26","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.inffus.2026.104519_bib0026","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1109\/TCSVT.2025.3572380","article-title":"Future fixation sequence prediction for audio-visual 360deg videos","volume":"36","author":"Zhu","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104519_bib0027","doi-asserted-by":"crossref","first-page":"3447","DOI":"10.1109\/TIP.2025.3567842","article-title":"How does audio influence visual attention in omnidirectional videos? database and model","volume":"34","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104519_bib0028","series-title":"CAAI International Conference on Artificial Intelligence","first-page":"512","article-title":"Perceptual quality assessment of omnidirectional audio-visual signals","author":"Zhu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104519_bib0029","doi-asserted-by":"crossref","first-page":"6054","DOI":"10.1109\/TIP.2020.2988148","article-title":"Study of subjective and objective quality assessment of audio-visual signals","volume":"29","author":"Min","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104519_bib0030","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1109\/TIP.2023.3251695","article-title":"Attention-guided neural networks for full-reference and no-reference audio-visual quality assessment","volume":"32","author":"Cao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104519_bib0031","doi-asserted-by":"crossref","first-page":"3847","DOI":"10.1109\/TIP.2023.3290528","article-title":"Subjective and objective audio-visual quality assessment for user generated content","volume":"32","author":"Cao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.inffus.2026.104519_bib0032","doi-asserted-by":"crossref","first-page":"7778","DOI":"10.1109\/TCSVT.2025.3544659","article-title":"Exploring rich subjective quality information for image quality assessment in the wild","volume":"35","author":"Min","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.inffus.2026.104519_bib0033","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TBC.2018.2816783","article-title":"Blind image quality estimation via distortion aggravation","volume":"64","author":"Min","year":"2018","journal-title":"IEEE Trans. Broadcast."},{"issue":"8","key":"10.1016\/j.inffus.2026.104519_bib0034","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1109\/TMM.2017.2788206","article-title":"Blind quality assessment based on pseudo-reference image","volume":"20","author":"Min","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104519_bib0035","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1109\/TMM.2025.3623560","article-title":"SingingHead: a large-scale 4D dataset for singing head animation","volume":"28","author":"Wu","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104519_bib0036","doi-asserted-by":"crossref","unstructured":"Z. Gao, Y. Li, S. Wu, Y. Zhu, H. Duan, G. Zhai, SFQA: a comprehensive perceptual quality assessment dataset for singing face generation, arXiv preprint arXiv: 2601.20385(2026).","DOI":"10.1109\/ICASSP55912.2026.11461545"},{"key":"10.1016\/j.inffus.2026.104519_bib0037","series-title":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","first-page":"525","article-title":"MVBind: self-supervised music recommendation for videos via embedding space binding","author":"Teng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104519_bib0038","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"13550","article-title":"Audio-visual instance segmentation","author":"Guo","year":"2025"},{"key":"10.1016\/j.inffus.2026.104519_bib0039","unstructured":"C.-I. Lai, Contrastive predictive coding based feature for automatic speaker verification, arXiv preprint arXiv: 1904.01575(2019)."},{"key":"10.1016\/j.inffus.2026.104519_bib0040","series-title":"2023 IEEE International Conference on Image Processing (ICIP)","first-page":"3025","article-title":"Deep OC-sort: multi-pedestrian tracking by adaptive re-identification","author":"Maggiolino","year":"2023"},{"key":"10.1016\/j.inffus.2026.104519_bib0041","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6504","article-title":"Hybrid-sort: weak cues matter for online multi-object tracking","volume":"38","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104519_bib0042","doi-asserted-by":"crossref","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","article-title":"Strongsort: make deepsort great again","volume":"25","author":"Du","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104519_bib0043","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/TIP.2025.3526066","article-title":"TOPIC: a parallel association paradigm for multi-object tracking under complex motions and diverse scenes","volume":"34","author":"Cao","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104519_bib0044","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1282","article-title":"DVIS: decoupled video instance segmentation framework","author":"Zhang","year":"2023"},{"issue":"4","key":"10.1016\/j.inffus.2026.104519_bib0045","doi-asserted-by":"crossref","first-page":"2963","DOI":"10.1109\/TCSVT.2024.3361076","article-title":"Learning better video query with sam for video instance segmentation","volume":"35","author":"Fang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104519_bib0046","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":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.inffus.2026.104519_bib0047","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1007\/s11263-024-02261-x","article-title":"Audio-visual segmentation with semantics","volume":"133","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104519_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18963","article-title":"Matching anything by segmenting anything","author":"Li","year":"2024"},{"key":"10.1016\/j.inffus.2026.104519_bib0049","unstructured":"D. Mendon\u00e7a, T. Barros, C. Premebida, U.J. Nunes, Seg2Track-SAM2: SAM2-based multi-object tracking and segmentation for zero-shot generalization, arXiv preprint arXiv: 2509.11772(2025)."},{"key":"10.1016\/j.inffus.2026.104519_bib0050","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"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003982?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003982?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T12:14:45Z","timestamp":1781525685000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":50,"alternative-id":["S1566253526003982"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104519","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Listen2Track: Plug-and-play audio-visual matching for generic multi-object tracking","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104519","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104519"}}