{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T03:17:08Z","timestamp":1769224628527,"version":"3.49.0"},"reference-count":159,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3552309","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:36:59Z","timestamp":1742603819000},"page":"5690-5707","source":"Crossref","is-referenced-by-count":1,"title":["Impact of Noisy Supervision in Foundation Model Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1960-4803","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Ran","family":"Tao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8973-2843","authenticated-orcid":false,"given":"Hongxin","family":"Wei","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}]},{"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6658-6743","authenticated-orcid":false,"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN, Tokyo, Japan"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-0880","authenticated-orcid":false,"given":"Jindong","family":"Wang","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, VA, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref3","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref4","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref9","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Schuhmann"},{"key":"ref10","article-title":"RedPajama: An open dataset for training large language models","author":"Computer","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref17","first-page":"1","article-title":"ImageNet-21K pretraining for the masses","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ridnik"},{"key":"ref18","article-title":"COYO-700M: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref19","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref24","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref25","article-title":"Gemini: A family of highly capable multimodal models","year":"2023"},{"key":"ref26","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref27","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref28","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref29","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref30","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref31","first-page":"1617","article-title":"Mandoline: Model evaluation under distribution shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref32","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022"},{"key":"ref33","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref34","first-page":"3938","article-title":"USB: A unified semi-supervised learning benchmark","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01868-w"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref39","article-title":"DataComp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2023"},{"key":"ref40","article-title":"The role of pre-training data in transfer learning","author":"Entezari","year":"2023"},{"key":"ref41","article-title":"On the trade-off of intra-\/inter-class diversity for supervised pre-training","author":"Zhang","year":"2023"},{"key":"ref42","first-page":"21455","article-title":"Quality not quantity: On the interaction between dataset design and robustness of clip","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"ref44","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.179"},{"key":"ref46","article-title":"Racial disparity in natural language processing: A case study of social media African-American English","author":"Blodgett","year":"2017"},{"key":"ref47","article-title":"On adversarial bias and the robustness of fair machine learning","author":"Chang","year":"2020"},{"key":"ref48","article-title":"Into the LAIONs Den: Investigating hate in multimodal datasets","author":"Birhane","year":"2023"},{"key":"ref49","article-title":"What\u2019s in my big data?","author":"Elazar","year":"2023"},{"key":"ref50","first-page":"1","article-title":"Quantifying memorization across neural language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Carlini"},{"key":"ref51","article-title":"Identifying and eliminating CSAM in generative ML training data and models","author":"Thiel","year":"2023"},{"key":"ref52","article-title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","author":"Vasudevan","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref54","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref56","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"ref58","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref59","article-title":"Understanding and mitigating the label noise in pre-training on downstream tasks","author":"Chen","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref62","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref63","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref65","article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref67","first-page":"1","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goldberger"},{"key":"ref68","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref69","first-page":"6403","article-title":"Provably end-to-end label-noise learning without anchor points","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref71","first-page":"12501","article-title":"Learning noise transition matrix from only noisy labels via total variation regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref72","first-page":"14153","article-title":"Robust training under label noise by over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref73","first-page":"24137","article-title":"Fine samples for learning with noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref74","article-title":"Imprecise label learning: A unified framework for learning with various imprecise label configurations","author":"Chen","year":"2023"},{"key":"ref75","first-page":"1","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei"},{"key":"ref76","article-title":"Mitigating memorization of noisy labels via regularization between representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheng"},{"key":"ref77","first-page":"1","article-title":"Benign overfitting in classification: Provably counter label noise with larger models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wen"},{"key":"ref78","first-page":"24851","article-title":"Investigating why contrastive learning benefits robustness against label noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xue"},{"key":"ref79","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref80","first-page":"1","article-title":"FreeMatch: Self-adaptive thresholding for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref81","first-page":"1","article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kang"},{"key":"ref82","first-page":"1101","article-title":"Margin calibration for long-tailed visual recognition","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Wang"},{"key":"ref83","first-page":"23589","article-title":"To smooth or not? When label smoothing meets noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref84","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.18"},{"key":"ref86","first-page":"9614","article-title":"Transfer learning without knowing: Reprogramming black-box machine learning models with scarce data and limited resources","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tsai"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"ref89","article-title":"Towards efficient task-driven model reprogramming with foundation models","author":"Xu","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02320"},{"key":"ref91","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref94","first-page":"15696","article-title":"Large language models struggle to learn long-tail knowledge","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kandpal"},{"key":"ref95","article-title":"Gender bias in LLMs","author":"Kotek","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00939-z"},{"key":"ref97","article-title":"Jailbroken: How does LLM safety training fail?","author":"Wei","year":"2023"},{"key":"ref98","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref99","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref100","article-title":"Deep double descent: Where bigger models and more data hurt","volume":"2021","author":"Nakkiran","year":"2019","journal-title":"J. Stat. Mechanics: Theory Experiment"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref102","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref103","first-page":"1","article-title":"RedCaps: Web-curated image-text data created by the people, for the people","volume-title":"Proc. NeurIPS Datasets Benchmarks","author":"Desai"},{"key":"ref104","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref105","article-title":"Are we done with ImageNet?","author":"Beyer","year":"2020"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01619"},{"key":"ref108","first-page":"1","article-title":"Self-supervised learning is more robust to dataset imbalance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref112","article-title":"ResNet strikes back: An improved training procedure in TIMM","author":"Wightman","year":"2021"},{"key":"ref113","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","author":"You","year":"2019"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref116","article-title":"MultiGrain: A unified image embedding for classes and instances","author":"Berman","year":"2019"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref122","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref127","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8519248"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref139","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00952"},{"key":"ref141","first-page":"9448","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Barbu"},{"key":"ref142","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref143","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref144","article-title":"PEFT: State-of-the-art parameter-efficient fine-tuning methods","author":"Mangrulkar","year":"2022"},{"key":"ref145","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref146","article-title":"Generalization guarantees for neural networks via harnessing the low-rank structure of the Jacobian","author":"Oymak","year":"2019"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.76"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref149","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref150","first-page":"1","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bardes"},{"key":"ref151","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref152","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref155","article-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.806"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref159","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10934976.pdf?arnumber=10934976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T17:51:50Z","timestamp":1749577910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10934976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":159,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3552309","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}