{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T21:54:08Z","timestamp":1763330048530,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":65,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609710"},{"type":"electronic","value":"9789819609727"}],"license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0972-7_6","type":"book-chapter","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T08:10:29Z","timestamp":1733731829000},"page":"90-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MonoDSSMs: Efficient Monocular 3D Object Detection with\u00a0Depth-Aware State Space Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0964-8134","authenticated-orcid":false,"given":"Kiet Dang","family":"Vu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1422-9685","authenticated-orcid":false,"given":"Trung Thai","family":"Tran","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7321-7401","authenticated-orcid":false,"given":"Duc Dung","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Arora, C.: Depthformer: Multiscale vision transformer for monocular depth estimation with global local information fusion. In: 2022 IEEE International Conference on Image Processing (ICIP). pp. 3873\u20133877 (2022)","DOI":"10.1109\/ICIP46576.2022.9897187"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3d object detection in monocular video. In: Computer Vision \u2013 ECCV 2020. pp. 135\u2013152. Springer International Publishing, Cham (2020)","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bui, M.Q.V., Ngo, D.T., Pham, H.A., Nguyen, D.D.: Gac3d: improving monocular 3d object detection with ground-guide model and adaptive convolution. PeerJ Computer Science 7 (2021)","DOI":"10.7717\/peerj-cs.686"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., Li, B., Jiao, Z., Li, H., Zeng, X., Wang, X.: Monocular 3d object detection with decoupled structured polygon estimation and height-guided depth estimation. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6618"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Huang, Y., Tian, W., Gao, Z., Xiong, L.: Monorun: Monocular 3d object detection by reconstruction and uncertainty propagation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10374\u201310383 (2021)","DOI":"10.1109\/CVPR46437.2021.01024"},{"key":"6_CR6","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. ArXiv (2017)"},{"key":"6_CR7","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A.G., Ma, H., Fidler, S., Urtasun, R.: 3d object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems. vol.\u00a028. Curran Associates, Inc. (2015)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: Monopair: Monocular 3d object detection using pairwise spatial relationships. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12090\u201312099 (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"6_CR9","unstructured":"Dao, T., Fu, D.Y., Saab, K.K., Thomas, A.W., Rudra, A., R\u00e9, C.: Hungry hungry hippos: Towards language modeling with state space models. ArXiv (2022)"},{"key":"6_CR10","unstructured":"Dao, T., Gu, A.: Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. In: Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 10041\u201310071. PMLR (21\u201327 Jul 2024)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Ding, M., Huo, Y., Yi, H., Wang, Z., Shi, J., Lu, Z., Luo, P.: Learning depth-guided convolutions for monocular 3d object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 11669\u201311678 (2020)","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"6_CR12","unstructured":"Dong, Z., Ji, H., Huang, X., Zhang, W., Zhan, X., Chen, J.: Pep: a point enhanced painting method for unified point cloud tasks. CoRR (2023)"},{"key":"6_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR (2021)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6_CR16","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. ArXiv (2023)"},{"key":"6_CR17","unstructured":"Gu, A., Goel, K., R\u2019e, C.: Efficiently modeling long sequences with structured state spaces. ArXiv (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.S., Zhang, L.: Structure aware single-stage 3d object detection from point cloud. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 11870\u201311879 (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Hu, V.T., Baumann, S.A., Gui, M., Grebenkova, O., Ma, P., Fischer, J., Ommer, B.: Zigma: A dit-style zigzag mamba diffusion model. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"6_CR20","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. ArXiv (2021)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Huang, K., Wu, T., Su, H., Hsu, W.H.: Monodtr: Monocular 3d object detection with depth-aware transformer. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4002\u20134011 (2022)","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"6_CR22","unstructured":"Huang, T., Pei, X., You, S., Wang, F., Qian, C., Xu, C.: Localmamba: Visual state space model with windowed selective scan. ArXiv (2024)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Kumar, A., Brazil, G., Corona, E., Parchami, A., Liu, X.: DEVIANT: depth equivariant network for monocular 3d object detection. In: Computer Vision - ECCV 2022 - 17th European Conference, Proceedings, Part IX. Lecture Notes in Computer Science, vol. 13669, pp. 664\u2013683. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_39"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: Fast encoders for object detection from point clouds. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12689\u201312697 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., Qiao, Y.: Videomamba: State space model for efficient video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3d detection from object keypoints for autonomous driving. In: Computer Vision - ECCV 2020 - 16th European Conference, Proceedings, Part III. Lecture Notes in Computer Science, vol. 12348, pp. 644\u2013660. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Yu, Q., Dai, J.: Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. ArXiv (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Li, Z., Qu, Z., Zhou, Y., Liu, J., Wang, H., Jiang, L.: Diversity matters: Fully exploiting depth clues for reliable monocular 3d object detection. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2781\u20132790 (2022)","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"6_CR29","unstructured":"Liang, D., Zhou, X., Wang, X., Zhu, X., Xu, W., Zou, Z., Ye, X., Bai, X.: Pointmamba: A simple state space model for point cloud analysis. ArXiv (2024)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In: Computer Vision \u2013 ECCV 2016. pp. 21\u201337. Springer International Publishing, Cham (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Liu, X., Xue, N., Wu, T.: Learning auxiliary monocular contexts helps monocular 3d object detection. In: AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for multi-view 3d object detection. ArXiv (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"6_CR33","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Liu, Y.: Vmamba: Visual state space model. ArXiV (2024)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u2019oth, R.: Smoke: Single-stage monocular 3d object detection via keypoint estimation. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 4289\u20134298 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Lu, Y., Ma, X., Yang, L., Zhang, T., Liu, Y., Chu, Q., Yan, J., Ouyang, W.: Geometry uncertainty projection network for monocular 3d object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 3091\u20133101 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, Y., Xu, D., Zhou, D., Yi, S., Li, H., Ouyang, W.: Delving into localization errors for monocular 3d object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4719\u20134728 (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"6_CR38","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. CoRR (2022)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Qin, Z., Li, X.: Monoground: Detecting monocular 3d objects from the ground. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3783\u20133792 (2022)","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3d object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 8551\u20138560 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 779\u2013788 (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Sagar, A.: Monocular depth estimation using multi scale neural network and feature fusion. 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) pp. 656\u2013662 (2020)","DOI":"10.1109\/WACVW54805.2022.00072"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10526\u201310535 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 770\u2013779 (2018)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., Kim, T.K.: Geometry-based distance decomposition for monocular 3d object detection. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 15152\u201315161 (2021)","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3d object detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"6_CR47","unstructured":"Smith, J., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. ArXiv (2022)"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E.G., Kautz, J.: Pixel-adaptive convolutional neural networks. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 11158\u201311167 (2019)","DOI":"10.1109\/CVPR.2019.01142"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Tang, Y., Dorn, S., Savani, C.: Center3d: Center-based monocular 3d object detection with joint depth understanding. In: Pattern Recognition. pp. 289\u2013302. Springer International Publishing, Cham (2021)","DOI":"10.1007\/978-3-030-71278-5_21"},{"key":"6_CR50","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10347\u201310357. PMLR (2021)"},{"key":"6_CR51","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Wang, L., Du, L., Ye, X., Fu, Y., Guo, G., Xue, X., Feng, J., Zhang, L.: Depth-conditioned dynamic message propagation for monocular 3d object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 454\u2013463 (2021)","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"6_CR53","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Probabilistic and geometric depth: Detecting objects in perspective. In: Conference on Robot Learning (2021)"},{"key":"6_CR54","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. ArXiv (2021)"},{"issue":"11","key":"6_CR55","doi-asserted-by":"publisher","first-page":"7464","DOI":"10.1109\/LRA.2023.3313053","volume":"8","author":"K Xiong","year":"2023","unstructured":"Xiong, K., Zhang, D., Liang, D., Liu, Z., Yang, H., Dikubab, W., Cheng, J., Bai, X.: You only look bottom-up for monocular 3d object detection. IEEE Robotics and Automation Letters 8(11), 7464\u20137471 (2023)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"6_CR56","doi-asserted-by":"crossref","unstructured":"Yang, C., Chen, Y., Tian, H., Tao, C., Zhu, X., Zhang, Z., Huang, G., Li, H., Qiao, Y., Lu, L., Zhou, J., Dai, J.: Bevformer v2: Adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 17830\u201317839 (2022)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"6_CR57","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Center-based 3d object detection and tracking. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 11779\u201311788 (2020)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"6_CR58","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Darrell, T.: Deep layer aggregation. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 2403\u20132412 (2017)","DOI":"10.1109\/CVPR.2018.00255"},{"key":"6_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, F., Chen, Y., Li, Z., Hong, Z., Liu, J., Ma, F., Han, J., Ding, E.: Acfnet: Attentional class feature network for semantic segmentation. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 6797\u20136806 (2019)","DOI":"10.1109\/ICCV.2019.00690"},{"key":"6_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, R., Qiu, H., Wang, T., Guo, Z., Cui, Z., Xu, X., Qiao, Y.J., Gao, P., Li, H.: Monodetr: Depth-guided transformer for monocular 3d object detection. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 9121\u20139132 (2022)","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"6_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: Flexible monocular 3d object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3288\u20133297 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"6_CR62","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. ArXiv (2019)"},{"key":"6_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4490\u20134499. IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"6_CR64","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: Efficient visual representation learning with bidirectional state space model. ArXiv (2024)"},{"key":"6_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, M., Ge, L., Wang, P., Peng, H.: Monoedge: Monocular 3d object detection using local perspectives. 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) pp. 643\u2013652 (2023)","DOI":"10.1109\/WACV56688.2023.00071"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0972-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T09:05:50Z","timestamp":1733735150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0972-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"ISBN":["9789819609710","9789819609727"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0972-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"10 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}