{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:39:59Z","timestamp":1730230799446,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096314","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-based Segmentation Networks"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Barbato","sequence":"first","affiliation":[{"name":"University of Padova,Department of Information Engineering,Padova,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulia","family":"Rizzoli","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Padova,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Zanuttigh","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Padova,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093584"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989540"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref14","first-page":"561","article-title":"Bi-directional cross-modality feature prop-agation with separation-and-aggregation gate for rgb-d semantic segmentation","author":"chen","year":"2020","journal-title":"Proc of ECCV"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2016.0502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"ref10","first-page":"1","article-title":"Indoor semantic segmentation using depth information","author":"couprie","year":"2013","journal-title":"Proc of ICLR"},{"article-title":"Dabnet: Depth-wise asymmetric bottleneck for real-time semantic segmentation","year":"2019","author":"li","key":"ref21"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10357-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011192"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00049"},{"article-title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","year":"2022","author":"liu","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"article-title":"Selma: Semantic large-scale multimodal acquisitions in variable weather, day-time and viewpoints","year":"2022","author":"testolina","key":"ref9"},{"key":"ref4","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Proc of NIPS"},{"key":"ref3","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/technologies10040090"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096314.pdf?arnumber=10096314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:20Z","timestamp":1699883960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096314","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}