{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:02:49Z","timestamp":1784131369233,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1109\/tpami.2023.3291237","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T17:22:46Z","timestamp":1688145766000},"page":"1-16","source":"Crossref","is-referenced-by-count":5,"title":["Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9519-612X","authenticated-orcid":false,"given":"Xiao","family":"Dong","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Zhuhai Campus, Sun Yat-Sen University, Zhuhai, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunlin","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-5177","authenticated-orcid":false,"given":"Xiaoyong","family":"Wei","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory, Shenzhen, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory, Shenzhen, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minlong","family":"Lu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Zero-shot open set detection by extending clip","author":"esmaeilpour","year":"2021"},{"key":"ref57","article-title":"VIOLET : End-to-end video-language transformers with masked visual-token modeling","author":"fu","year":"2021"},{"key":"ref12","article-title":"Grounded language-image pre-training","author":"li","year":"2021"},{"key":"ref56","article-title":"UNIMO: Towards unified-modal understanding and generation via cross-modal contrastive learning","author":"li","year":"2020"},{"key":"ref15","article-title":"Open-vocabulary detection via vision and language knowledge distillation","author":"gu","year":"2021"},{"key":"ref59","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"yao","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval","author":"luo","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00978"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00604"},{"key":"ref11","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"li","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00342"},{"key":"ref16","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.260"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0391-4"},{"key":"ref46","author":"b\u00fcttcher","year":"2016","journal-title":"Information Retrieval Implementing and Evaluating Search Engines"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123429"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1561\/1500000065"},{"key":"ref42","article-title":"RPC: A large-scale retail product checkout dataset","author":"wei","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540092"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018692"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.266"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266436"},{"key":"ref8","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref9","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347047"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01157"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(15)00449-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3029387.3029420"},{"key":"ref82","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref81","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref80","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref79","article-title":"A revisit of deep hashings for large-scale content based image retrieval","author":"cai","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00360"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2760101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2876822"},{"key":"ref75","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00316"},{"key":"ref74","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","article-title":"ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"sun","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20147"},{"key":"ref32","article-title":"ERNIE: Enhanced representation through knowledge integration","author":"sun","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"radford","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref39","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.384"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125687"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02057"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref68","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics - Hum Lang Technol"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390501"},{"key":"ref67","article-title":"WenLan: Bridging vision and language by large-scale multi-modal pre-training","author":"huo","year":"2021"},{"key":"ref26","first-page":"449","article-title":"Cross-modal retrieval with CNN visual features: A new baseline","volume":"47","author":"wei","year":"2017","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref69","article-title":"Pretrained encyclopedia: Weakly supervised knowledge-pretrained language model","author":"xiong","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532801"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref63","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"wang","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.025"},{"key":"ref66","article-title":"Uni-perceiver: Pre-training unified architecture for generic perception for zero-shot and few-shot tasks","author":"zhu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.034"},{"key":"ref65","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref60","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume":"139","author":"kim","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref62","article-title":"M6: A Chinese multimodal pretrainer","author":"lin","year":"2021"},{"key":"ref61","article-title":"Florence: A new foundation model for computer vision","author":"yuan","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10169110.pdf?arnumber=10169110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:10:41Z","timestamp":1696432241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10169110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3291237","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":[[2023]]}}}