{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:37:45Z","timestamp":1780079865031,"version":"3.54.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650232","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet"],"prefix":"10.1109","author":[{"given":"Loris","family":"Giulivi","sequence":"first","affiliation":[{"name":"Politecnico di Milano,DEIB"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Boracchi","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,DEIB"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100645"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref3","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref10","article-title":"Rise: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018"},{"key":"ref11","article-title":"Segdiscover: Visual concept discovery via unsupervised semantic segmentation","author":"Huang","year":"2022"},{"key":"ref12","first-page":"1","article-title":"Perception visualization: Seeing through the eyes of a dnn","volume-title":"Proceedings of BMVC 2021","author":"Giulivi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00265-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref17","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Open-set recog-nition: A good closed-set classifier is all you need?","author":"Vaze","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"ref25","first-page":"2219","article-title":"Attention-based dropout layer for weakly super-vised object localization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Choe"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref27","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377519"},{"key":"ref29","article-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.491"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650232.pdf?arnumber=10650232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:11:14Z","timestamp":1725945074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650232","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}