{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:39:50Z","timestamp":1759937990553,"version":"3.40.3"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031727603"},{"type":"electronic","value":"9783031727610"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72761-0_21","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"367-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Global-Local Collaborative Inference with\u00a0LLM for\u00a0Lidar-Based Open-Vocabulary Detection"],"prefix":"10.1007","author":[{"given":"Xingyu","family":"Peng","sequence":"first","affiliation":[]},{"given":"Yan","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Lirong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Beipeng","family":"Mu","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"21_CR1","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"21_CR2","unstructured":"Cao, Y., Yihan, Z., Xu, H., Xu, D.: CoDA: collaborative novel box discovery and cross-modal alignment for open-vocabulary 3D object detection. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR3","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Sheng, L., Shi, S., Yang, M., Xu, D.: Back-tracing representative points for voting-based 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00885"},{"key":"21_CR6","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/vicunalmsys.org. Accessed 14 Apr 2023"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14084\u201314093 (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Fan, L., Xiong, X., Wang, F., Wang, N., Zhang, Z.: RangeDet: in defense of range view for lidar-based 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2918\u20132927 (2021)","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"21_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-031-20077-9_41","volume-title":"ECCV 2022","author":"C Feng","year":"2022","unstructured":"Feng, C., et al.: PromptDet: towards open-vocabulary detection using uncurated images. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 701\u2013717. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_41"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Eliminating cross-modal conflicts in BEV space for lidar-camera 3D object detection. arXiv preprint arXiv:2403.07372 (2024)","DOI":"10.1109\/ICRA57147.2024.10610230"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Gao, C., Chen, J., Liu, S., Wang, L., Zhang, Q., Wu, Q.: Room-and-object aware knowledge reasoning for remote embodied referring expression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3064\u20133073 (2021)","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, A., Narayan, S., Joseph, K., Khan, S., Khan, F.S., Shah, M.: OW-DETR: open-world detection transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9235\u20139244 (2022)","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"21_CR14","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58555-6_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Huang","year":"2020","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 35\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3"},{"key":"21_CR16","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Advances in Neural Information Processing Systems, vol. 35, pp. 22199\u201322213 (2022)"},{"key":"21_CR17","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar R-CNN: an efficient and universal 3D object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"21_CR20","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning: prompt tuning can be comparable to fine-tuning across scales and tasks. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 61\u201368 (2022)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2949\u20132958 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"21_CR25","unstructured":"Lu, Y., et al.: Open-vocabulary 3D detection via image-level class and debiased cross-modal contrastive learning. arXiv preprint arXiv:2207.01987 (2022)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Open-vocabulary point-cloud object detection without 3D annotation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1190\u20131199 (2023)","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: 3D-SPS: single-stage 3D visual grounding via referred point progressive selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16454\u201316463 (2022)","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4721\u20134730 (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"21_CR29","unstructured":"Ma, Z., et al.: Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14074\u201314083 (2022)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"21_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S., Barnes, N.: Improved visual-semantic alignment for zero-shot object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11932\u201311939 (2020)","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"21_CR35","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1007\/s11263-020-01355-6","volume":"128","author":"S Rahman","year":"2020","unstructured":"Rahman, S., Khan, S.H., Porikli, F.: Zero-shot object detection: joint recognition and localization of novel concepts. Int. J. Comput. Vis. 128, 2979\u20132999 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: RSN: range sparse net for efficient, accurate lidar 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5725\u20135734 (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"21_CR40","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58542-6_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Wang","year":"2020","unstructured":"Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_2"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, Y., Liu, T., Zhao, H., Wang, S.: OV-Uni3DETR: towards unified open-vocabulary 3D object detection via cycle-modality propagation. arXiv preprint arXiv:2403.19580 (2024)","DOI":"10.1007\/978-3-031-72970-6_5"},{"key":"21_CR44","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"21_CR45","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Xie, Q., et al.: VENet: voting enhancement network for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3712\u20133721 (2021)","DOI":"10.1109\/ICCV48922.2021.00369"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Q., et al.: MLCVNet: multi-level context votenet for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10447\u201310456 (2020)","DOI":"10.1109\/CVPR42600.2020.01046"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Wang, T., Chen, Y., Pang, J., Lin, D.: PointLLM: empowering large language models to understand point clouds. arXiv preprint arXiv:2308.16911 (2023)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., Urtasun, R.: PIXOR: real-time 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: DetCLIPv2: scalable open-vocabulary object detection pre-training via word-region alignment (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"21_CR52","unstructured":"Yao, L., et al.: DetCLIP: dictionary-enriched visual-concept paralleled pre-training for open-world detection. In: Advances in Neural Information Processing Systems, vol. 35 (2022)"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"21_CR54","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-031-20077-9_7","volume-title":"ECCV 2022","author":"Y Zang","year":"2022","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C.: Open-vocabulary DETR with conditional matching. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 106\u2013122. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_7"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"21_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: FM-OV3D: foundation model-based cross-modal knowledge blending for open-vocabulary 3D detection. arXiv preprint arXiv:2312.14465 (2023)","DOI":"10.1609\/aaai.v38i15.29612"},{"key":"21_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"21_CR58","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"21_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: OpenSight: a simple open-vocabulary framework for lidar-based object detection. arXiv preprint arXiv:2312.08876 (2023)","DOI":"10.1007\/978-3-031-72907-2_1"},{"key":"21_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58610-2_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3DNet: 3D object detection using hybrid geometric primitives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 311\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_19"},{"key":"21_CR61","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"21_CR62","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-031-20077-9_21","volume-title":"ECCV 2022","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21"},{"key":"21_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72761-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:20:48Z","timestamp":1732828848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72761-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727603","9783031727610"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72761-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}