{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:06:04Z","timestamp":1779692764060,"version":"3.53.1"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108790","type":"journal-article","created":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T01:22:07Z","timestamp":1772846527000},"page":"108790","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["VISTA-3D : Training-free unfolding for vision-based 3D object detection"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0452-0635","authenticated-orcid":false,"given":"Xiaoyu","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8974-7642","authenticated-orcid":false,"given":"Fang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4196-3064","authenticated-orcid":false,"given":"Ying","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8892-9222","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6355-7354","authenticated-orcid":false,"given":"Yajing","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108790_bib0001","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv: 1607.06450."},{"key":"10.1016\/j.neunet.2026.108790_bib0002","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9287","article-title":"M3d-rpn: Monocular 3d region proposal network for object detection","author":"Brazil","year":"2019"},{"key":"10.1016\/j.neunet.2026.108790_bib0003","unstructured":"Courtois, J., & Miramond, B. (2022). An analytical estimation of spiking neural networks energy efficiency. arXiv: 2210.13107."},{"issue":"1","key":"10.1016\/j.neunet.2026.108790_bib0004","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: A neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"10.1016\/j.neunet.2026.108790_bib0005","series-title":"2015 International joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","author":"Diehl","year":"2015"},{"key":"10.1016\/j.neunet.2026.108790_bib0006","series-title":"CVPR","first-page":"11672","article-title":"Learning depth-guided convolutions for monocular 3d object detection","author":"Ding","year":"2020"},{"key":"10.1016\/j.neunet.2026.108790_bib0007","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2661","article-title":"Incorporating learnable membrane time constant to enhance learning of spiking neural networks","author":"Fang","year":"2021"},{"issue":"5","key":"10.1016\/j.neunet.2026.108790_bib0008","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/JPROC.2014.2304638","article-title":"The spiNNaker project","volume":"102","author":"Furber","year":"2014","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.108790_bib0009","series-title":"2012\u202fIEEE Conference on computer vision and pattern recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.neunet.2026.108790_bib0010","series-title":"2014\u202fIEEE International solid-state circuits conference digest of technical papers (ISSCC)","first-page":"10","article-title":"1.1 Computing\u2019s energy problem (and what we can do about it)","author":"Horowitz","year":"2014"},{"key":"10.1016\/j.neunet.2026.108790_bib0011","unstructured":"Huang, J. et al. (2022a). Bevdet: High-performance multi-camera 3d object detection in bird\u2019s-eye view. arXiv: 2112.11790."},{"key":"10.1016\/j.neunet.2026.108790_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4012","article-title":"Monodtr: Monocular 3d object detection with depth-aware transformer","author":"Huang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108790_bib0013","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.eng.2022.01.012","article-title":"1000\u202f\u00d7\u202f Faster camera and machine vision with ordinary devices","volume":"25","author":"Huang","year":"2023","journal-title":"Engineering"},{"issue":"8","key":"10.1016\/j.neunet.2026.108790_bib0014","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1109\/JPROC.2015.2444094","article-title":"Memory and information processing in neuromorphic systems","volume":"103","author":"Indiveri","year":"2015","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2026.108790_bib0015","series-title":"International conference on machine learning","first-page":"14945","article-title":"A unified optimization framework of ann-snn conversion: Towards optimal mapping from activation values to firing rates","author":"Jiang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108790_bib0016","unstructured":"Kim, S., Park, S., Na, B., & Yoon, S. (2019). Spiking-YOLO: Spiking neural network for energy-efficient object detection. arXiv: 1903.06530."},{"key":"10.1016\/j.neunet.2026.108790_bib0017","series-title":"CVPR","first-page":"8973","article-title":"Groomed-NMS: Grouped mathematically differentiable NMS for monocular 3d object detection","author":"Kumar","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0018","series-title":"CVPR","first-page":"12697","article-title":"Pointpillars: Fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108790_bib0019","series-title":"European conference on computer vision","first-page":"644","article-title":"Rtm3d: Real-time monocular 3d detection from object keypoints for autonomous driving","author":"Li","year":"2020"},{"issue":"7","key":"10.1016\/j.neunet.2026.108790_bib0020","doi-asserted-by":"crossref","first-page":"3516","DOI":"10.1109\/TCSVT.2022.3233042","article-title":"Neuron-based spiking transmission and reasoning network for robust image-text retrieval","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108790_bib0021","series-title":"IEEE international conference on multimedia and expo","first-page":"426","article-title":"Modality-fusion spiking transformer network for audio-visual zero-shot learning","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108790_bib0022","doi-asserted-by":"crossref","first-page":"4840","DOI":"10.1109\/TIP.2024.3430080","article-title":"Spiking tucker fusion transformer for audio-visual zero-shot learning","volume":"33","author":"Li","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108790_bib0023","series-title":"Proceedings of the ACM international conference on multimedia","first-page":"3994","article-title":"Motion-decoupled spiking transformer for audio-visual zero-shot learning","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108790_bib0024","unstructured":"Li, Y., Deng, S., Dong, X., Gu, S. et al. (2022b). Converting artificial neural networks to spiking neural networks via parameter calibration. arXiv: 2205.10121."},{"key":"10.1016\/j.neunet.2026.108790_bib0025","unstructured":"Li, Y., He, X., Dong, Y., Kong, Q., & Zeng, Y. (2022c). Spike calibration: Fast and accurate conversion of spiking neural network for object detection and segmentation. arXiv: 2207.02702."},{"key":"10.1016\/j.neunet.2026.108790_bib0026","series-title":"ECCV","article-title":"Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108790_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3262","article-title":"Petrv2: A unified framework for 3d perception from multi-camera images","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108790_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","first-page":"996","article-title":"Smoke: Single-stage monocular 3d object detection via keypoint estimation","author":"Liu","year":"2020"},{"key":"10.1016\/j.neunet.2026.108790_bib0029","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"15641","article-title":"Autoshape: Real-time shape-aware monocular 3d object detection","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0030","unstructured":"Lv, C., Wang, Y., Han, D., Shen, Y., Zheng, X., Huang, X., & Li, D. (2025). Toward relative positional encoding in spiking transformers. arXiv: 2501.16745."},{"issue":"9","key":"10.1016\/j.neunet.2026.108790_bib0031","doi-asserted-by":"crossref","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of spiking neurons: The third generation of neural network models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Networks"},{"issue":"6197","key":"10.1016\/j.neunet.2026.108790_bib0032","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1126\/science.1254642","article-title":"A million spiking-neuron integrated circuit with a scalable communication network and interface","volume":"345","author":"Merolla","year":"2014","journal-title":"Science"},{"issue":"6","key":"10.1016\/j.neunet.2026.108790_bib0033","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.neunet.2026.108790_bib0034","series-title":"2021\u202fIEEE Workshop on signal processing systems (siPS)","first-page":"254","article-title":"Efficient neuromorphic signal processing with loihi 2","author":"Orchard","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0035","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3142","article-title":"Is pseudo-lidar needed for monocular 3d object detection?","author":"Park","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0036","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"6520","article-title":"Monodgp: Monocular 3d object detection with decoupled-query and geometry-error priors","author":"Pu","year":"2025"},{"key":"10.1016\/j.neunet.2026.108790_bib0037","series-title":"CVPR","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Qi","year":"2017"},{"key":"10.1016\/j.neunet.2026.108790_bib0038","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108790_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"20086","article-title":"Efficient 3d recognition with event-driven spike sparse convolution","volume":"vol. 39","author":"Qiu","year":"2025"},{"issue":"6","key":"10.1016\/j.neunet.2026.108790_bib0040","doi-asserted-by":"crossref","first-page":"3174","DOI":"10.1109\/TNNLS.2021.3111897","article-title":"Diet-snn: A low-latency spiking neural network with direct input encoding and leakage and threshold optimization","volume":"34","author":"Rathi","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108790_bib0041","series-title":"CVPR","first-page":"8555","article-title":"Categorical depth distribution network for monocular 3d object detection","author":"Reading","year":"2021"},{"issue":"7784","key":"10.1016\/j.neunet.2026.108790_bib0042","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108790_bib0043","doi-asserted-by":"crossref","first-page":"682","DOI":"10.3389\/fnins.2017.00682","article-title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","volume":"11","author":"Rueckauer","year":"2017","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2026.108790_bib0044","doi-asserted-by":"crossref","first-page":"95","DOI":"10.3389\/fnins.2019.00095","article-title":"Going deeper in spiking neural networks: VGG and residual architectures","volume":"13","author":"Sengupta","year":"2019","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2026.108790_bib0045","unstructured":"Shapovalov, R., Zabolotskiy, V., Artemov, A., & Burnaev, E. (2021). Imvoxelnet: Image to voxels projection for monocular and multi-view general-purpose 3d detection. arXiv: 2106.01178."},{"key":"10.1016\/j.neunet.2026.108790_bib0046","first-page":"1419","article-title":"Slayer: Spike layer error reassignment in time","volume":"31","author":"Shrestha","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6\u20137","key":"10.1016\/j.neunet.2026.108790_bib0047","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/S0893-6080(01)00083-1","article-title":"Spike-based strategies for rapid processing","volume":"14","author":"Thorpe","year":"2001","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108790_bib0048","series-title":"CVPR","first-page":"454","article-title":"Depth-conditioned dynamic message propagation for monocular 3d object detection","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0049","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"913","article-title":"Fcos3d: Fully convolutional one-stage monocular 3d object detection","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108790_bib0050","doi-asserted-by":"crossref","unstructured":"Wu, Y., Deng, L., Li, G., Zhu, J., & Shi, L. (2018). Spatio-temporal backpropagation for training high-performance spiking neural networks. Frontiers in Neuroscience. 12, 331.","DOI":"10.3389\/fnins.2018.00331"},{"key":"10.1016\/j.neunet.2026.108790_bib0051","unstructured":"Xiong, R., Yang, Y., He, D., Zheng, K., Xing, C., Zhang, H., Lan, Y., Wang, L., & Liu, T.-Y. (2020). On layer normalization in the transformer architecture. arXiv: 2002.04745."},{"key":"10.1016\/j.neunet.2026.108790_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10248","article-title":"Monocd: Monocular 3d object detection with complementary depths","author":"Yan","year":"2024"},{"issue":"10","key":"10.1016\/j.neunet.2026.108790_bib0053","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"Second: Sparsely embedded convolutional detection","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.108790_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14905","article-title":"Is-fusion: Instance-scene collaborative fusion for multimodal 3d object detection","author":"Yin","year":"2024"},{"key":"10.1016\/j.neunet.2026.108790_bib0055","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11784","article-title":"Center-based 3d object detection and tracking","author":"Yin","year":"2021"},{"issue":"4","key":"10.1016\/j.neunet.2026.108790_bib0056","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1162\/neco_a_01367","article-title":"The remarkable robustness of surrogate gradient learning for training deep SNNs","volume":"33","author":"Zenke","year":"2021","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.108790_bib0057","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9155","article-title":"MonoDETR: Depth-guided transformer for monocular 3d object detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108790_bib0058","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3289","article-title":"Objects are different: Flexible monocular 3d object detection","author":"Zhang","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2026.108790_bib0059","doi-asserted-by":"crossref","first-page":"5207","DOI":"10.1109\/TCSVT.2023.3326294","article-title":"Spike camera image reconstruction using deep spiking neural networks","volume":"34","author":"Zhao","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.108790_bib0060","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.neunet.2020.03.003","article-title":"Probabilistic inference of binary markov random fields in spiking neural networks through mean-field approximation","volume":"126","author":"Zheng","year":"2020","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108790_bib0061","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1109\/TIP.2022.3228168","article-title":"Spike-based motion estimation for object tracking through bio-inspired unsupervised learning","volume":"32","author":"Zheng","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108790_bib0062","series-title":"CVPR","first-page":"4490","article-title":"Voxelnet: End-to-end learning for point cloud based 3d object detection","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neunet.2026.108790_bib0063","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv: 2010.04159."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002522?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002522?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:48:54Z","timestamp":1779691734000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":63,"alternative-id":["S0893608026002522"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108790","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VISTA-3D : Training-free unfolding for vision-based 3D object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108790","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108790"}}