{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:05:18Z","timestamp":1790201118869,"version":"4.1.0"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134668","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:17:31Z","timestamp":1785338251000},"page":"134668","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-VLM collaborated adaptive sampling for enhanced data pruning"],"prefix":"10.1016","volume":"702","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3580-8284","authenticated-orcid":false,"given":"Changfan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-0416","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huahui","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8136-9816","authenticated-orcid":false,"given":"Kang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-8548","authenticated-orcid":false,"given":"Qicheng","family":"Lao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134668_bib0005","author":"Yin"},{"issue":"10","key":"10.1016\/j.neucom.2026.134668_bib0010","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: a survey","volume":"63","author":"Qiu","year":"2020","journal-title":"Sci. China Technol. Sci."},{"key":"10.1016\/j.neucom.2026.134668_bib0015","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134668_bib0020","series-title":"ICLR","article-title":"Moderate coreset: a universal method of data selection for real-world data-efficient deep learning","author":"Xia","year":"2023"},{"key":"10.1016\/j.neucom.2026.134668_bib0025","author":"Coleman"},{"key":"10.1016\/j.neucom.2026.134668_bib0030","author":"Zheng"},{"key":"10.1016\/j.neucom.2026.134668_bib0035","first-page":"20596","article-title":"Deep learning on a data diet: finding important examples early in training","volume":"34","author":"Paul","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0040","first-page":"14488","article-title":"Retrieve: coreset selection for efficient and robust semi-supervised learning","volume":"34","author":"Killamsetty","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0045","author":"Abbas"},{"key":"10.1016\/j.neucom.2026.134668_bib0050","doi-asserted-by":"crossref","first-page":"19523","DOI":"10.52202\/068431-1419","article-title":"Beyond neural scaling laws: beating power law scaling via data pruning","volume":"35","author":"Sorscher","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0055","series-title":"International Conference on Machine Learning","first-page":"1050","article-title":"Dropout as a Bayesian approximation: representing model uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"10.1016\/j.neucom.2026.134668_bib0060","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1266","article-title":"Scail: classifier weights scaling for class incremental learning","author":"Belouadah","year":"2020"},{"key":"10.1016\/j.neucom.2026.134668_bib0065","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"233","article-title":"End-to-end incremental learning","author":"Castro","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0070","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8179","article-title":"Scaling up influence functions","volume":"vol. 36","author":"Schioppa","year":"2022"},{"key":"10.1016\/j.neucom.2026.134668_bib0075","author":"Toneva"},{"key":"10.1016\/j.neucom.2026.134668_bib0080","series-title":"International Conference on Machine Learning","first-page":"5464","article-title":"Grad-match: gradient matching based data subset selection for efficient deep model training","author":"Killamsetty","year":"2021"},{"key":"10.1016\/j.neucom.2026.134668_bib0085","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0090","author":"Kaplan"},{"key":"10.1016\/j.neucom.2026.134668_bib0095","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7151","article-title":"Context encoding for semantic segmentation","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0100","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"593","article-title":"Asymmetric non-local neural networks for semantic segmentation","author":"Zhu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134668_bib0105","author":"Yuan"},{"key":"10.1016\/j.neucom.2026.134668_bib0110","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3435710","article-title":"Multi-level collaborative learning for multi-target domain adaptive semantic segmentation","volume":"34","author":"Ding","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134668_bib0115","article-title":"Cross-modality image interpretation via concept decomposition vector of visual-language models","volume":"35","author":"Fang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134668_bib0120","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3529923","article-title":"Variational adapter: improving CLIP in data-imbalanced scenarios","volume":"35","author":"Lu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134668_bib0125","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"5014","article-title":"VG4D: vision-language model goes 4D video recognition","author":"Deng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134668_bib0130","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3528108","article-title":"PLOVAD: prompting vision-language models for open vocabulary video anomaly detection","volume":"35","author":"Xu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134668_bib0135","article-title":"GPT4Ego: unleashing the potential of pre-trained models for zero-shot egocentric action recognition","volume":"27","author":"Dai","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134668_bib0140","series-title":"International Conference on Machine Learning","first-page":"31292","article-title":"Upop: unified and progressive pruning for compressing vision-language transformers","author":"Shi","year":"2023"},{"key":"10.1016\/j.neucom.2026.134668_bib0145","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134668_bib0150","series-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021"},{"issue":"9","key":"10.1016\/j.neucom.2026.134668_bib0155","first-page":"1","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134668_bib0160","author":"Achiam"},{"key":"10.1016\/j.neucom.2026.134668_bib0165","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134668_bib0170","author":"Grattafiori"},{"key":"10.1016\/j.neucom.2026.134668_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"23849","article-title":"Out-of-distributed semantic pruning for robust semi-supervised learning","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134668_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129690","article-title":"An active learning model based on image similarity for skin lesion segmentation","volume":"630","author":"Shu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134668_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2594","article-title":"Semantic-aware domain generalized segmentation","author":"Peng","year":"2022"},{"key":"10.1016\/j.neucom.2026.134668_bib0190","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"960","article-title":"CAP: context-aware pruning for semantic segmentation","author":"He","year":"2021"},{"issue":"1","key":"10.1016\/j.neucom.2026.134668_bib0195","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1080\/00401706.1990.10484593","article-title":"Assessing influence on predictions from generalized linear models","volume":"32","author":"Thomas","year":"1990","journal-title":"Technometrics"},{"issue":"2","key":"10.1016\/j.neucom.2026.134668_bib0200","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1111\/j.2517-6161.1986.tb01398.x","article-title":"Assessment of local influence","volume":"48","author":"Cook","year":"1986","journal-title":"J. R. Stat. Soc. B Stat. Methodol."},{"key":"10.1016\/j.neucom.2026.134668_bib0205","article-title":"Gradient based sample selection for online continual learning","volume":"32","author":"Aljundi","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0210","author":"Guo"},{"key":"10.1016\/j.neucom.2026.134668_bib0215","author":"Han"},{"key":"10.1016\/j.neucom.2026.134668_bib0220","series-title":"Proceedings of the 26th Annual International Conference on Machine Learning","first-page":"1121","article-title":"Herding dynamical weights to learn","author":"Welling","year":"2009"},{"key":"10.1016\/j.neucom.2026.134668_bib0225","first-page":"19920","article-title":"Estimating training data influence by tracing gradient descent","volume":"33","author":"Pruthi","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0230","series-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0235","author":"Alexey"},{"key":"10.1016\/j.neucom.2026.134668_bib0240","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16","first-page":"491","article-title":"Big transfer (bit): general visual representation learning","author":"Kolesnikov","year":"2020"},{"key":"10.1016\/j.neucom.2026.134668_bib0245","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Active learning for convolutional neural networks: a core-set approach","author":"Sener","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131519","article-title":"A rate-dependent coreset selector for continual learning on time-varying data distributions","author":"Luo","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134668_bib0255","first-page":"1","article-title":"M3amba: CLIP-driven Mamba model for multi-modal remote sensing classification","author":"Cao","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"99","key":"10.1016\/j.neucom.2026.134668_bib0260","first-page":"1","article-title":"Mv-clip: multi-view clip for zero-shot 3D shape recognition","author":"Song","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134668_bib0265","series-title":"Advances in Neural Information Processing Systems","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"Kendall","year":"2017"},{"key":"10.1016\/j.neucom.2026.134668_bib0270","series-title":"6th International Conference on Learning Representations, ICLR 2018","article-title":"Active learning for convolutional neural networks: a core-set approach","author":"Sener","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0275","series-title":"International Conference on Machine Learning","first-page":"1954","article-title":"Submodularity in data subset selection and active learning","author":"Wei","year":"2015"},{"key":"10.1016\/j.neucom.2026.134668_bib0280","author":"Hou"},{"key":"10.1016\/j.neucom.2026.134668_bib0285","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109883","article-title":"Semantic similarity distance: towards better text-image consistency metric in text-to-image generation","volume":"144","author":"Tan","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134668_bib0290","series-title":"Advances in Neural Information Processing Systems","article-title":"Matching networks for one shot learning","volume":"vol. 29","author":"Vinyals","year":"2016"},{"key":"10.1016\/j.neucom.2026.134668_bib0295","series-title":"Invariant Feature Learning for Generalized Long-Tailed Classification","author":"Tang","year":"2023"},{"issue":"4","key":"10.1016\/j.neucom.2026.134668_bib0300","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"Fei-Fei","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134668_bib0305","series-title":"CVPR09","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2026.134668_bib0310","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.neucom.2026.134668_bib0315","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6848","article-title":"Shufflenet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134668_bib0320","series-title":"BLIP: Bootstrapping Language-Image Pre-Training for Unified Vision-Language Understanding and Generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134668_bib0325","first-page":"9694","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134668_bib0330","series-title":"Microsoft COCO Captions: Data Collection and Evaluation Server","author":"Chen","year":"2015"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020667?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020667?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:16:39Z","timestamp":1790198199000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226020667"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":66,"alternative-id":["S0925231226020667"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134668","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-VLM collaborated adaptive sampling for enhanced data pruning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134668","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":"134668"}}