{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:57:03Z","timestamp":1781326623064,"version":"3.54.1"},"reference-count":41,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["2022015"],"award-info":[{"award-number":["2022015"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Multi-object tracking and segmentation (MOTS) aims to jointly perform pixel-level instance segmentation and temporal identity association for multiple objects in video sequences. Existing online decoupled MOTS methods face several challenges in complex scenarios, including limited front-end mask quality, corruption of memory representations under prolonged occlusion, and unstable data association and trajectory recovery. To address these limitations, we propose TrackRefine, a plug-and-play decoupled enhancement framework. TrackRefine enhances overall performance through back-end refinement without modifying the architecture of the front-end instance segmenter or relying on additional end-to-end joint training. Specifically, we introduce a lightweight Fast GrabCut-based mask refinement module to optimize mask boundaries, a multimodal long-short-term memory bank that integrates appearance, semantic, and shape cues for identity modeling, and a progressive three-stage association strategy for stable matching and long-term trajectory recovery. Experimental results on MOTS20 show that TrackRefine achieves 69.4 sMOTSA, 82.7 MOTSA, and 478 Frag. Experimental results on KITTI MOTS show that it achieves 62.4\/73.7 sMOTSA and 78.0\/85.4 MOTSA for pedestrians and cars, respectively. Extensive experiments with different front-end instance segmenters verify its plug-and-play flexibility and decoupled design, while ablation studies confirm the effectiveness of each core module. These results show that TrackRefine provides an efficient and practical solution for online MOTS in complex scenarios.<\/jats:p>","DOI":"10.3390\/s26123696","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:59:31Z","timestamp":1781146771000},"page":"3696","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TrackRefine: A Plug-and-Play Decoupled Enhancement Framework for Online Multi-Object Tracking and Segmentation"],"prefix":"10.3390","volume":"26","author":[{"given":"Longfei","family":"Qie","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlei","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Bi","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqi","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-1044","authenticated-orcid":false,"given":"Jiakui","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1109\/TPAMI.2024.3485644","article-title":"OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Qian, H., Wang, M., Zhu, M., and Wang, H. (2025). A Review of Multi-Sensor Fusion in Autonomous Driving. Sensors, 25.","DOI":"10.3390\/s25196033"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mirzaei, B., Nezamabadi-Pour, H., Raoof, A., and Derakhshani, R. (2023). Small Object Detection and Tracking: A Comprehensive Review. Sensors, 23.","DOI":"10.3390\/s23156887"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, R., Ye, Z., and Li, Y. (2026). Robot Object Detection and Tracking Based on Image-Point Cloud Instance Matching. Sensors, 26.","DOI":"10.3390\/s26020718"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B.B.G., Geiger, A., and Leibe, B. (2019, January 15\u201320). MOTS: Multi-Object Tracking and Segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, L., Zhou, S., Fu, P., Hua, G., and Tang, W. (2024, January 17\u201321). Towards Generalizable Multi-Object Tracking. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01797"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, S., Ke, L., Danelljan, M., Piccinelli, L., Segu, M., Van Gool, L., and Yu, F. (2024, January 17\u201321). Matching Anything by Segmenting Anything. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01794"},{"key":"ref_8","unstructured":"Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., and Gustafson, L. (2025, January 24\u201328). SAM 2: Segment Anything in Images and Videos. Proceedings of the International Conference on Learning Representations, Singapore."},{"key":"ref_9","first-page":"5388","article-title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","volume":"40","author":"Jiang","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_10","first-page":"12762","article-title":"Tracking and Segmenting Anything in Any Modality","volume":"40","author":"Zhang","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gao, R., and Wang, L. (2023, January 2\u20136). MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Oh, S.W., Price, B., Schwing, A., and Lee, J.Y. (2024, January 17\u201321). Putting the Object Back into Video Object Segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yang, M., Han, G., Yan, B., Zhang, W., Qi, J., Lu, H., and Wang, D. (2024, January 20\u201327). Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i7.28471"},{"key":"ref_14","unstructured":"Segu, M., Piccinelli, L., Li, S., Yang, Y.-H., Van Gool, L., and Schiele, B. (2025, January 24\u201328). Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking. Proceedings of the International Conference on Learning Representations, Singapore."},{"key":"ref_15","unstructured":"Luo, W., Yan, F., Zhong, Y., Gan, Y., and Ma, L. (2025, January 24\u201328). CO-MOT: Boosting End-to-End Transformer-Based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets. Proceedings of the International Conference on Learning Representations, Singapore."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3035","DOI":"10.1007\/s11263-022-01678-6","article-title":"Multi-Object Tracking and Segmentation via Neural Message Passing","volume":"130","author":"Cetintas","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6424","DOI":"10.1109\/TPAMI.2021.3087898","article-title":"Segment as Points for Efficient and Effective Online Multi-Object Tracking and Segmentation","volume":"44","author":"Xu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6083","DOI":"10.1109\/TIP.2022.3203607","article-title":"An Object Point Set Inductive Tracker for Multi-Object Tracking and Segmentation","volume":"31","author":"Gao","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_19","unstructured":"Galoaa, B., Bai, X., Nandi, U., Rangoju, S.S.V.D., Amraee, S., and Ostadabbas, S. (2026, January 23\u201327). UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking. Proceedings of the International Conference on Learning Representations, Rio de Janeiro, Brazil."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.-Y. (2023, January 2\u20136). Segment Anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ding, S., Schuster, R., Lin, W., and Cremers, D. (2025, January 19\u201320). SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Honolulu, HI, USA.","DOI":"10.1109\/ICCV51701.2025.01264"},{"key":"ref_22","unstructured":"Kr\u00e4henb\u00fchl, P., and Koltun, V. (2011, January 12\u201317). Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials. Proceedings of the Advances in Neural Information Processing Systems, Granada, Spain."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","article-title":"\u201cGrabCut\u201d: Interactive Foreground Extraction Using Iterated Graph Cuts","volume":"23","author":"Rother","year":"2004","journal-title":"ACM Trans. Graph."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., and Soatto, S. (2022, January 18\u201324). MeMOT: Multi-Object Tracking with Memory. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., and Paulus, D. (2017, January 17\u201320). Simple Online and Realtime Tracking with a Deep Association Metric. Proceedings of the IEEE International Conference on Image Processing, Beijing, China.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref_26","unstructured":"Li, Y., Li, Q., Wang, H., Ma, X., Yao, J., Dong, S., Fan, H., and Zhang, L. (October, January 29). Beyond MOT: Semantic Multi-Object Tracking. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Sun, P., Cao, J., Jiang, Y., Yuan, Z., Bai, S., Kitani, K., and Luo, P. (2022, January 18\u201324). DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ren, H., Han, S., Ding, H., Zhang, Z., Wang, H., and Wang, F. (2023, January 18\u201322). Focus on Details: Online Multi-Object Tracking with Diverse Fine-Grained Representation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01086"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gao, R., Qi, J., and Wang, L. (2025, January 11\u201315). Multiple Object Tracking as ID Prediction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville TN, USA.","DOI":"10.1109\/CVPR52734.2025.02596"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022, January 23\u201327). ByteTrack: Multi-Object Tracking by Associating Every Detection Box. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_31","unstructured":"Aharon, N., Orfaig, R., and Bobrovsky, B.-Z. (2022). BoT-SORT: Robust Associations Multi-Pedestrian Tracking. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Nie, J., Wu, H., He, Z., and Gao, M. (2022). MSA-MOT: Multi-Stage Association for 3D Multimodality Multi-Object Tracking. Sensors, 22.","DOI":"10.3390\/s22228650"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"22533","DOI":"10.1038\/s41598-025-07276-z","article-title":"Re-Identification Assistance and Multi-Stage Association for Pedestrian Multi-Object Tracking","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_34","unstructured":"Ultralytics (2026, April 29). Ultralytics YOLO26. Available online: https:\/\/www.ultralytics.com\/."},{"key":"ref_35","unstructured":"Ultralytics (2026, April 29). YOLO26 Training Recipe. Available online: https:\/\/docs.ultralytics.com\/guides\/yolo26-training-recipe\/."},{"key":"ref_36","unstructured":"(2026, April 29). MOTSChallenge Dataset. MOTS: Multi-Object Tracking and Segmentation. Available online: https:\/\/www.vision.rwth-aachen.de\/page\/mots."},{"key":"ref_37","unstructured":"(2026, April 29). KITTI MOTS Dataset. Multi-Object Tracking and Segmentation. Available online: https:\/\/www.cvlibs.net\/datasets\/kitti\/eval_mots.php."},{"key":"ref_38","unstructured":"(2026, April 29). Competition 10051. Available online: https:\/\/www.codabench.org\/competitions\/10051\/."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Xu, Z., Meng, A., Shi, Z., Yang, W., Chen, Z., and Huang, L. (2021, January 10\u201317). Continuous Copy-Paste for One-Stage Multi-Object Tracking and Segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01504"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1109\/TCSVT.2022.3202574","article-title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration","volume":"33","author":"Yan","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_41","unstructured":"Mendon\u00e7a, D., Barros, T., Premebida, C., and Nunes, U.J. (2026). Seg2Track-SAM2: SAM2-Based Multi-Object Tracking and Segmentation. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3696\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:25:44Z","timestamp":1781324744000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":41,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123696"],"URL":"https:\/\/doi.org\/10.3390\/s26123696","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}