{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:31:50Z","timestamp":1777307510060,"version":"3.51.4"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008869","name":"Wuhan Institute of Technology","doi-asserted-by":"publisher","award":["24QD07"],"award-info":[{"award-number":["24QD07"]}],"id":[{"id":"10.13039\/501100008869","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008869","name":"Wuhan Institute of Technology","doi-asserted-by":"publisher","award":["24QD057"],"award-info":[{"award-number":["24QD057"]}],"id":[{"id":"10.13039\/501100008869","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2025AFB218"],"award-info":[{"award-number":["2025AFB218"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012554","name":"Hubei Provincial Department of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012554","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011431","name":"Hubei Provincial Key Laboratory of Intelligent Robot","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011431","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.inffus.2026.104344","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:53:27Z","timestamp":1775231607000},"page":"104344","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Wavelet-guided geometric feature enhancement and multimodal fusion for category-level object pose estimation"],"prefix":"10.1016","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2619-3475","authenticated-orcid":false,"given":"Lu","family":"Zou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1475-8894","authenticated-orcid":false,"given":"Zhangjin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104344_bib0001","doi-asserted-by":"crossref","unstructured":"Y. Xiang, T. Schmidt, V. Narayanan, D. Fox, PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes, arXiv preprint arXiv: 1711.00199(2017).","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"10.1016\/j.inffus.2026.104344_bib0002","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"683","article-title":"Deepim: deep iterative matching for 6D pose estimation","author":"Li","year":"2018"},{"key":"10.1016\/j.inffus.2026.104344_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3003","article-title":"FFB6D: a full flow bidirectional fusion network for 6D pose estimation","author":"He","year":"2021"},{"key":"10.1016\/j.inffus.2026.104344_bib0004","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3343","article-title":"Densefusion: 6D object pose estimation by iterative dense fusion","author":"Wang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104344_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4561","article-title":"PVNET: pixel-wise voting network for 6DoF pose estimation","author":"Peng","year":"2019"},{"key":"10.1016\/j.inffus.2026.104344_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11632","article-title":"PVN3D: a deep point-wise 3D keypoints voting network for 6DoF pose estimation","author":"He","year":"2020"},{"key":"10.1016\/j.inffus.2026.104344_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10710","article-title":"Latentfusion: end-to-end differentiable reconstruction and rendering for unseen object pose estimation","author":"Park","year":"2020"},{"key":"10.1016\/j.inffus.2026.104344_bib0008","series-title":"European Conference on Computer Vision","first-page":"108","article-title":"Self6D: self-supervised monocular 6D object pose estimation","author":"Wang","year":"2020"},{"issue":"4","key":"10.1016\/j.inffus.2026.104344_bib0009","doi-asserted-by":"crossref","first-page":"8575","DOI":"10.1109\/LRA.2021.3110538","article-title":"Category-level metric scale object shape and pose estimation","volume":"6","author":"Lee","year":"2021","journal-title":"IEEE Rob. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104344_bib0010","series-title":"European Conference on Computer Vision","first-page":"139","article-title":"Category level object pose estimation via neural analysis-by-synthesis","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104344_bib0011","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2036","article-title":"RGB-based category-level object pose estimation via decoupled metric scale recovery","author":"Wei","year":"2024"},{"key":"10.1016\/j.inffus.2026.104344_bib0012","series-title":"European Conference on Computer Vision","first-page":"467","article-title":"Lapose: Laplacian mixture shape modeling for RGB-based category-level object pose estimation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104344_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1581","article-title":"FS-Net: fast shape-based network for category-level 6D object pose estimation with decoupled rotation mechanism","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104344_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6707","article-title":"SAR-Net: shape alignment and recovery network for category-level 6D object pose and size estimation","author":"Lin","year":"2022"},{"key":"10.1016\/j.inffus.2026.104344_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6781","article-title":"GPV-pose: category-level object pose estimation via geometry-guided point-wise voting","author":"Di","year":"2022"},{"key":"10.1016\/j.inffus.2026.104344_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17163","article-title":"HS-pose: hybrid scope feature extraction for category-level object pose estimation","author":"Zheng","year":"2023"},{"key":"10.1016\/j.inffus.2026.104344_bib0017","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"14055","article-title":"Query6DoF: learning sparse queries as implicit shape prior for category-level 6DoF pose estimation","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104344_bib0018","series-title":"European Conference on Computer Vision","first-page":"530","article-title":"Shape prior deformation for categorical 6D object pose and size estimation","author":"Tian","year":"2020"},{"key":"10.1016\/j.inffus.2026.104344_bib0019","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2773","article-title":"SGPA: structure-guided prior adaptation for category-level 6D object pose estimation","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104344_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2642","article-title":"Normalized object coordinate space for category-level 6D object pose and size estimation","author":"Wang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104344_bib0021","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3560","article-title":"Dualposenet: category-level 6D object pose and size estimation using dual pose network with refined learning of pose consistency","author":"Lin","year":"2021"},{"issue":"12","key":"10.1016\/j.inffus.2026.104344_bib0022","doi-asserted-by":"crossref","first-page":"2763","DOI":"10.1007\/s11263-020-01309-y","article-title":"CR-Net: a deep classification-regression network for multimodal apparent personality analysis","volume":"128","author":"Li","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104344_bib0023","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13978","article-title":"IST-Net: prior-free category-level pose estimation with implicit space transformation","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104344_bib0024","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6808","article-title":"Catformer: category-level 6D object pose estimation with transformer","author":"Yu","year":"2024"},{"issue":"10","key":"10.1016\/j.inffus.2026.104344_bib0025","doi-asserted-by":"crossref","first-page":"9125","DOI":"10.1109\/TCSVT.2024.3397997","article-title":"Clipose: category-level object pose estimation with pre-trained vision-language knowledge","volume":"34","author":"Lin","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104344_bib0026","series-title":"European Conference on Computer Vision","first-page":"19","article-title":"Category-level 6D object pose and size estimation using self-supervised deep prior deformation networks","author":"Lin","year":"2022"},{"key":"10.1016\/j.inffus.2026.104344_bib0027","series-title":"A Wavelet Tour of Signal Processing","author":"Mallat","year":"1999"},{"issue":"6","key":"10.1016\/j.inffus.2026.104344_bib0028","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"},{"key":"10.1016\/j.inffus.2026.104344_bib0029","unstructured":"D.P. Kingma, M. Welling, Auto-encoding variational bayes, arXiv preprint arXiv: 1312.6114(2013)."},{"key":"10.1016\/j.inffus.2026.104344_bib0030","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"773","article-title":"Multi-level wavelet-CNN for image restoration","author":"Liu","year":"2018"},{"key":"10.1016\/j.inffus.2026.104344_bib0031","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.inffus.2026.104344_bib0032","series-title":"European Conference on Computer Vision","first-page":"363","article-title":"Wavelet convolutions for large receptive fields","author":"Finder","year":"2024"},{"issue":"3","key":"10.1016\/j.inffus.2026.104344_bib0033","doi-asserted-by":"crossref","first-page":"6084","DOI":"10.1109\/TCE.2024.3435032","article-title":"RLGC: reconstruction learning fusing gradient and content features for efficient deepfake detection","volume":"70","author":"Xu","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"10","key":"10.1016\/j.inffus.2026.104344_bib0034","doi-asserted-by":"crossref","first-page":"4746","DOI":"10.1007\/s11263-024-02116-5","article-title":"Watcher: wavelet-guided texture-content hierarchical relation learning for deepfake detection","volume":"132","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104344_bib0035","series-title":"International Conference on Learning Representations","article-title":"Adaptive wavelet transformer network for 3D shape representation learning","author":"Huang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104344_bib0036","series-title":"Ten Lectures on Wavelets","author":"Daubechies","year":"1992"},{"issue":"7","key":"10.1016\/j.inffus.2026.104344_bib0037","doi-asserted-by":"crossref","first-page":"2104","DOI":"10.1117\/12.172247","article-title":"Orthogonal multiwavelets with vanishing moments","volume":"33","author":"Strang","year":"1994","journal-title":"Opt. Eng."},{"key":"10.1016\/j.inffus.2026.104344_bib0038","series-title":"Zur Theorie der Orthogonalen Funktionensysteme","author":"Haar","year":"1909"},{"key":"10.1016\/j.inffus.2026.104344_bib0039","series-title":"Dritter Band: Analysis\u00b7 Grundlagen der Mathematik\u00b7 Physik Verschiedenes: Nebst Einer Lebensgeschichte","author":"Hilbert","year":"2013"},{"key":"10.1016\/j.inffus.2026.104344_bib0040","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.inffus.2026.104344_bib0041","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2881","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"10.1016\/j.inffus.2026.104344_bib0042","series-title":"Advances in Neural Information Processing Systems","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","author":"Ruizhongtai","year":"2017"},{"key":"10.1016\/j.inffus.2026.104344_bib0043","series-title":"European Conference on Computer Vision","first-page":"124","article-title":"Agent attention: on the integration of softmax and linear attention","author":"Han","year":"2024"},{"key":"10.1016\/j.inffus.2026.104344_bib0044","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.inffus.2026.104344_bib0045","series-title":"International Conference on Learning Representations (ICLR)","article-title":"A method for stochastic optimization","author":"Kinga","year":"2015"},{"key":"10.1016\/j.inffus.2026.104344_bib0046","series-title":"2017 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"464","article-title":"Cyclical learning rates for training neural networks","author":"Smith","year":"2017"},{"key":"10.1016\/j.inffus.2026.104344_bib0047","series-title":"European Conference on Computer Vision","first-page":"655","article-title":"RBP-pose: residual bounding box projection for category-level pose estimation","author":"Zhang","year":"2022"},{"issue":"7","key":"10.1016\/j.inffus.2026.104344_bib0048","doi-asserted-by":"crossref","first-page":"5520","DOI":"10.1109\/TPAMI.2025.3552132","article-title":"Diff9D: diffusion-based domain-generalized category-level 9-DoF object pose estimation","volume":"47","author":"Liu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.inffus.2026.104344_bib0049","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1109\/TNNLS.2023.3330011","article-title":"Category-level 6-D object pose estimation with shape deformation for robotic grasp detection","volume":"36","author":"Yu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104344_bib0050","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2415","article-title":"Learning point cloud representations with pose continuity for depth-based category-level 6D object pose estimation","author":"Li","year":"2025"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600223X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600223X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T15:32:14Z","timestamp":1777303934000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156625352600223X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"alternative-id":["S156625352600223X"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104344","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Wavelet-guided geometric feature enhancement and multimodal fusion for category-level object pose estimation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104344","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104344"}}