{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:26:54Z","timestamp":1762090014091,"version":"build-2065373602"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100027065","name":"Google Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100027065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Uniandes-DeepMind Scholarships"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3286760","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:27:38Z","timestamp":1687282058000},"page":"12206-12221","source":"Crossref","is-referenced-by-count":6,"title":["PiGLET: Pixel-Level Grounding of Language Expressions With Transformers"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9445-9952","authenticated-orcid":false,"given":"Cristina","family":"Gonz\u00e1lez","sequence":"first","affiliation":[{"name":"Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogotá, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0691-3770","authenticated-orcid":false,"given":"Nicol\u00e1s","family":"Ayobi","sequence":"additional","affiliation":[{"name":"Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogotá, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3539-6696","authenticated-orcid":false,"given":"Isabela","family":"Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogotá, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7133-3724","authenticated-orcid":false,"given":"Jordi","family":"Pont-Tuset","sequence":"additional","affiliation":[{"name":"Google Research, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-2407","authenticated-orcid":false,"given":"Pablo","family":"Arbel\u00e1ez","sequence":"additional","affiliation":[{"name":"Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogotá, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_4"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref15"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930176"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref11","first-page":"1","article-title":"On seeing stuff: The perception of materials by humans and machines","author":"adelson","year":"2001","journal-title":"Proc Hum Vis Electron Imag VI"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61750-7_36"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"article-title":"RoBERTa: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref17"},{"journal-title":"WordNet An Electronic Lexical Database","year":"1998","author":"miller","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref42","article-title":"On the relationship between self-attention and convolutional layers","author":"cordonnier","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2010","author":"dosovitskiy","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"article-title":"Referring expression object segmentation with caption-aware consistency","year":"2019","author":"chen","key":"ref43"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref3","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref82","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref81","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref78","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","author":"zhang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","year":"2019","author":"su","key":"ref31"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01333"},{"article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","year":"2019","author":"lu","key":"ref30"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00140"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"article-title":"Microsoft COCO captions: Data collection and evaluation server","year":"2015","author":"chen","key":"ref1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00719"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548086"},{"key":"ref73","first-page":"17721","article-title":"Solov2: Dynamic and fast instance segmentation","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Maskformer","year":"2021","author":"cheng","key":"ref68"},{"article-title":"Masked-attention mask transformer for universal image segmentation","year":"2021","author":"cheng","key":"ref23"},{"journal-title":"Natural Language Processing with Python Analyzing Text with the Natural Language Toolkit","year":"2009","author":"bird","key":"ref67"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25350"},{"key":"ref20","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref63","first-page":"4761","article-title":"Cross-modal progressive comprehension for referring segmentation","volume":"44","author":"liu","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"article-title":"Panoptic segformer","year":"2021","author":"li","key":"ref22"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.683"},{"article-title":"Per-pixel classification is not all you need for semantic segmentation","year":"2021","author":"cheng","key":"ref21"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"article-title":"VisualBERT: A simple and performant baseline for vision and language","year":"2019","author":"li","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971171"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10158238.pdf?arnumber=10158238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T17:27:51Z","timestamp":1717781271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10158238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":82,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3286760","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}