{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:59:26Z","timestamp":1782845966243,"version":"3.54.5"},"reference-count":54,"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"}],"funder":[{"DOI":"10.13039\/501100007128","name":"Shaanxi Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114333","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:47:46Z","timestamp":1782431266000},"page":"114333","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Bridging the encoder gap: Stability-aware efficient adaptation of SAM2 for video object segmentation"],"prefix":"10.1016","volume":"180","author":[{"given":"Zhiqiang","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4346-3588","authenticated-orcid":false,"given":"Hao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sugang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114333_b1","unstructured":"H.K. Cheng, Y.-W. Tai, C.-K. Tang, Modular interactive video object segmentation: Interaction-to-mask, propagation and difference-aware fusion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5559\u20135568."},{"issue":"1\u20133","key":"10.1016\/j.patcog.2026.114333_b2","first-page":"1","article-title":"Computer vision for autonomous vehicles: Problems, datasets and state of the art","volume":"12","author":"Janai","year":"2020","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"10.1016\/j.patcog.2026.114333_b3","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"7375","article-title":"Learning object manipulation skills from video via approximate differentiable physics","author":"Petr\u00edk","year":"2022"},{"key":"10.1016\/j.patcog.2026.114333_b4","unstructured":"S.W. Oh, J.-Y. Lee, N. Xu, S.J. Kim, Video object segmentation using space-time memory networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9226\u20139235."},{"key":"10.1016\/j.patcog.2026.114333_b5","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114333_b6","series-title":"European Conference on Computer Vision","first-page":"640","article-title":"XMem: Long-term video object segmentation with an Atkinson-Shiffrin memory model","author":"Cheng","year":"2022"},{"key":"10.1016\/j.patcog.2026.114333_b7","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3151","article-title":"Putting the object back into video object segmentation","author":"Cheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.114333_b8","doi-asserted-by":"crossref","unstructured":"Q. Wu, T. Yang, W. Wu, A.B. Chan, Scalable video object segmentation with simplified framework, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 13879\u201313889.","DOI":"10.1109\/ICCV51070.2023.01276"},{"issue":"7","key":"10.1016\/j.patcog.2026.114333_b9","doi-asserted-by":"crossref","first-page":"6039","DOI":"10.1109\/TPAMI.2025.3557841","article-title":"JointFormer: A unified framework with joint modeling for video object segmentation","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114333_b10","doi-asserted-by":"crossref","unstructured":"J. Wang, D. Chen, Z. Wu, C. Luo, C. Tang, X. Dai, Y. Zhao, Y. Xie, L. Yuan, Y.-G. Jiang, Look before you match: Instance understanding matters in video object segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2268\u20132278.","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"10.1016\/j.patcog.2026.114333_b11","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.114333_b12","series-title":"SAM2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.patcog.2026.114333_b13","doi-asserted-by":"crossref","unstructured":"S. Ding, R. Qian, X. Dong, P. Zhang, Y. Zang, Y. Cao, Y. Guo, D. Lin, J. Wang, SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2025, pp. 13614\u201313624.","DOI":"10.1109\/ICCV51701.2025.01264"},{"key":"10.1016\/j.patcog.2026.114333_b14","doi-asserted-by":"crossref","unstructured":"J. Videnovic, A. Lukezic, M. Kristan, A distractor-aware memory for visual object tracking with SAM2, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 24255\u201324264.","DOI":"10.1109\/CVPR52734.2025.02259"},{"key":"10.1016\/j.patcog.2026.114333_b15","series-title":"Proceedings of the 30th International Conference on Machine Learning","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"Pascanu","year":"2013"},{"key":"10.1016\/j.patcog.2026.114333_b16","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"Xiong","year":"2020"},{"key":"10.1016\/j.patcog.2026.114333_b17","series-title":"SAM2-Adapter: Evaluating & adapting segment anything 2 in downstream tasks: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.114333_b18","series-title":"SAM2-UNet: Segment anything 2 makes strong encoder for natural and medical image segmentation","author":"Xiong","year":"2024"},{"key":"10.1016\/j.patcog.2026.114333_b19","doi-asserted-by":"crossref","unstructured":"M. Li, L. Hu, Z. Xiong, B. Zhang, P. Pan, D. Liu, Recurrent dynamic embedding for video object segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1332\u20131341.","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"10.1016\/j.patcog.2026.114333_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131585","article-title":"Frequency-aware fusion for improved video object segmentation","author":"Hou","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114333_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111428","article-title":"Self-supervised video object segmentation via pseudo label rectification","volume":"163","author":"Guo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114333_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103547","article-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","volume":"102","author":"Wu","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.114333_b23","series-title":"Medsam2: Segment anything in 3d medical images and videos","author":"Ma","year":"2025"},{"key":"10.1016\/j.patcog.2026.114333_b24","series-title":"SAMba-UNet: Synergizing SAM2 and Mamba in UNet with heterogeneous aggregation for cardiac MRI segmentation","author":"Huo","year":"2025"},{"key":"10.1016\/j.patcog.2026.114333_b25","series-title":"Surgical SAM2: Real-time segment anything in surgical video by efficient frame pruning","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114333_b26","series-title":"International Conference on Machine Learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.patcog.2026.114333_b27","series-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114333_b28","doi-asserted-by":"crossref","unstructured":"B. Lester, R. Al-Rfou, N. Constant, The Power of Scale for Parameter-Efficient Prompt Tuning, in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP, 2021, pp. 3045\u20133059.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"10.1016\/j.patcog.2026.114333_b29","unstructured":"X.L. Li, P. Liang, Prefix-Tuning: Optimizing Continuous Prompts for Generation, in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, ACL, 2021, pp. 4582\u20134597."},{"key":"10.1016\/j.patcog.2026.114333_b30","unstructured":"S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, in: International Conference on Machine Learning, 2015, pp. 448\u2013456."},{"key":"10.1016\/j.patcog.2026.114333_b31","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.patcog.2026.114333_b32","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114333_b33","article-title":"Individual time series and composite forecasting of the Chinese stock index","volume":"5","author":"Xu","year":"2021","journal-title":"Mach. Learn. Appl."},{"issue":"4","key":"10.1016\/j.patcog.2026.114333_b34","article-title":"High-frequency CSI300 spot and futures price predictions via the neural network","volume":"18","author":"Jin","year":"2025","journal-title":"J. Uncertain Syst."},{"key":"10.1016\/j.patcog.2026.114333_b35","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.patcog.2026.114333_b36","volume":"vol. 208","author":"Coles","year":"2001"},{"key":"10.1016\/j.patcog.2026.114333_b37","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, Squeeze-and-Excitation Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.patcog.2026.114333_b38","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"issue":"4","key":"10.1016\/j.patcog.2026.114333_b39","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1109\/TPAMI.2015.2465960","article-title":"Hierarchical image saliency detection on extended CSSD","volume":"38","author":"Shi","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114333_b40","doi-asserted-by":"crossref","unstructured":"L. Wang, H. Lu, Y. Wang, M. Feng, D. Wang, B. Yin, X. Ruan, Learning to Detect Salient Objects With Image-Level Supervision, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017.","DOI":"10.1109\/CVPR.2017.404"},{"key":"10.1016\/j.patcog.2026.114333_b41","doi-asserted-by":"crossref","unstructured":"X. Li, T. Wei, Y.P. Chen, Y.-W. Tai, C.-K. Tang, FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"10.1016\/j.patcog.2026.114333_b42","doi-asserted-by":"crossref","unstructured":"Y. Zeng, P. Zhang, J. Zhang, Z. Lin, H. Lu, Towards High-Resolution Salient Object Detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2019.","DOI":"10.1109\/ICCV.2019.00733"},{"key":"10.1016\/j.patcog.2026.114333_b43","doi-asserted-by":"crossref","unstructured":"H.K. Cheng, J. Chung, Y.-W. Tai, C.-K. Tang, CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"10.1016\/j.patcog.2026.114333_b44","doi-asserted-by":"crossref","unstructured":"F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross, A. Sorkine-Hornung, A benchmark dataset and evaluation methodology for video object segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 724\u2013732.","DOI":"10.1109\/CVPR.2016.85"},{"key":"10.1016\/j.patcog.2026.114333_b45","series-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"10.1016\/j.patcog.2026.114333_b46","series-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018"},{"key":"10.1016\/j.patcog.2026.114333_b47","doi-asserted-by":"crossref","unstructured":"H. Ding, C. Liu, S. He, X. Jiang, P.H. Torr, S. Bai, MOSE: A new dataset for video object segmentation in complex scenes, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 20224\u201320234.","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"10.1016\/j.patcog.2026.114333_b48","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114333_b49","doi-asserted-by":"crossref","first-page":"36324","DOI":"10.52202\/068431-2632","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114333_b50","doi-asserted-by":"crossref","unstructured":"H.K. Cheng, S.W. Oh, B. Price, A. Schwing, J.-Y. Lee, Tracking anything with decoupled video segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 1316\u20131326.","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"10.1016\/j.patcog.2026.114333_b51","first-page":"6586","article-title":"Holistic correction with object prototype for video object segmentation","volume":"vol. 39","author":"Qiao","year":"2025"},{"issue":"10","key":"10.1016\/j.patcog.2026.114333_b52","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.patcog.2026.114333_b53","series-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.patcog.2026.114333_b54","doi-asserted-by":"crossref","unstructured":"B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, A. Torralba, Scene parsing through ADE20K dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012987?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012987?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:01:37Z","timestamp":1782842497000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0031320326012987"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114333","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bridging the encoder gap: Stability-aware efficient adaptation of SAM2 for video object segmentation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114333","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":"114333"}}