{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:23:18Z","timestamp":1774365798471,"version":"3.50.1"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00051"],"award-info":[{"award-number":["226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372405"],"award-info":[{"award-number":["62372405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tpami.2024.3367952","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T19:34:59Z","timestamp":1708630499000},"page":"5398-5412","source":"Crossref","is-referenced-by-count":70,"title":["Cross-Image Pixel Contrasting for Semantic Segmentation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5475-1473","authenticated-orcid":false,"given":"Tianfei","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence (CCAI), Zhejiang Univeristy, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref4","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref7","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref9","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref16","article-title":"Uncovering prototypical knowledge for weakly open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref17","first-page":"12 077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref19","first-page":"20 787","article-title":"CLUSTSEG: Clustering for universal segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_36"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref23","first-page":"11115","article-title":"Region mutual information loss for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref26","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091066"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.22"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref39","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref41","first-page":"3285","article-title":"Looking beyond single images for contrastive semantic segmentation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00695"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01484"},{"key":"ref47","first-page":"31 360","article-title":"GMMSeg: Gaussian mixture based generative semantic segmentation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00154"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737535"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.539"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102599"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055780"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3332435"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387116"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00381"},{"key":"ref65","article-title":"Towards data-and knowledge-driven artificial intelligence: A survey on neuro-symbolic computing","author":"Wang","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16294"},{"key":"ref68","article-title":"Universal weakly supervised segmentation by pixel-to-segment contrastive learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ke"},{"key":"ref69","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref70","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref72","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref74","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref77","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref78","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref79","first-page":"18 661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref80","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Robinson"},{"key":"ref81","first-page":"21 798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kalantidis"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref83","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20166"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref86","first-page":"12 546","article-title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chaitanya"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01037"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3309979"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref93","article-title":"Semantic instance segmentation via deep metric learning","author":"Fathi","year":"2017"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref95","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref96","first-page":"2406","article-title":"Universal correspondence network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Choy"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.66"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.305"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_31"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00294"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00016"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00728"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6716"},{"key":"ref105","first-page":"1","article-title":"It takes two to tango: Mixup for deep metric learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Venkataramanan"},{"key":"ref106","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref107","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref108","article-title":"$ i$i-Mix: A domain-agnostic strategy for contrastive representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01014"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref112","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"ref114","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pang"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_45"},{"key":"ref116","article-title":"Are all negatives created equal in contrastive instance discrimination?","author":"Frankle","year":"2020"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref120","first-page":"13 927","article-title":"RANet: Region attention network for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref121","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00690"},{"key":"ref124","first-page":"17 864","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":"ref125","article-title":"On mutual information in contrastive learning for visual representations","author":"Wu","year":"2020"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00685"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00909"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00366"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00975"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref134","article-title":"iBOT: Image bert pre-training with online Tokenizer","author":"Zhou","year":"2021"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3239194"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3049156"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00015"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10582780\/10443562.pdf?arnumber=10443562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T04:01:48Z","timestamp":1720152108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10443562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":137,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3367952","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":[[2024,8]]}}}