{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:01:36Z","timestamp":1740132096720,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["KQTD20210811090149095"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3454647","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:48:15Z","timestamp":1725472095000},"page":"11287-11297","source":"Crossref","is-referenced-by-count":2,"title":["TagCLIP: Improving Discrimination Ability of Zero-Shot Semantic Segmentation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5121-1153","authenticated-orcid":false,"given":"Jingyao","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1746-5127","authenticated-orcid":false,"given":"Pengguang","family":"Chen","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3386-0336","authenticated-orcid":false,"given":"Shengju","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-9270","authenticated-orcid":false,"given":"Shu","family":"Liu","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-553X","authenticated-orcid":false,"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01114"},{"article-title":"Motcoder: Elevating large language models with modular of thought for challenging programming tasks","year":"2023","author":"Li","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3412004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3345844"},{"article-title":"Combined scaling for open-vocabulary image classification","year":"2021","author":"Pham","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00682"},{"article-title":"A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model","year":"2021","author":"Xu","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01075"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"article-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","year":"2014","author":"Chen","key":"ref13"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref14"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"article-title":"Unsupervised attention-based sentence-level meta-embeddings from contextualised language models","year":"2022","author":"Takahashi","key":"ref17"},{"key":"ref18","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. naacL-HLT","volume":"1","author":"Kenton","year":"2019"},{"key":"ref19","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"},{"article-title":"VisualBERT: A simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref20"},{"article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","year":"2019","author":"Su","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"article-title":"Finetuning pretrained vision-language models with correlation information bottleneck for robust visual question answering","year":"2022","author":"Jiang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"article-title":"DenseCLIP: Extract free dense labels from clip","year":"2021","author":"Zhou","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref30","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref34","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref35","first-page":"4971","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref37","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bucher"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413593"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00942"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00940"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00303"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"article-title":"Distributed representations of words and phrases and their compositionality","year":"2013","author":"Mikolov","key":"ref44"},{"article-title":"Fasttext.zip: Compressing text classification models","year":"2016","author":"Joulin","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10666015.pdf?arnumber=10666015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:33:53Z","timestamp":1732667633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10666015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":46,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3454647","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":[[2024,12]]}}}