{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:26:19Z","timestamp":1785511579940,"version":"3.56.0"},"publisher-location":"Cham","reference-count":86,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732461","type":"print"},{"value":"9783031732478","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73247-8_13","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"213-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with\u00a0Spatial Relation Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8125-1308","authenticated-orcid":false,"given":"Meng","family":"Chu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2434-9050","authenticated-orcid":false,"given":"Zhedong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-9768","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4169-1595","authenticated-orcid":false,"given":"Tingyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Berton, G., et al.: Deep visual geo-localization benchmark. In: CVPR, pp. 5396\u20135407 (2022)","DOI":"10.1109\/CVPR52688.2022.00532"},{"key":"13_CR3","unstructured":"Blukis, V., Terme, Y., Niklasson, E., Knepper, R.A., Artzi, Y.: Learning to map natural language instructions to physical quadcopter control using simulated flight. In: CoRL, pp. 1415\u20131438 (2020)"},{"key":"13_CR4","unstructured":"Borisov, V., Sessler, K., Leemann, T., Pawelczyk, M., Kasneci, G.: Language models are realistic tabular data generators. In: ICLR (2023)"},{"key":"13_CR5","unstructured":"Brunsting, S., De\u00a0Sterck, H., Dolman, R., van Sprundel, T.: Geotexttagger: high-precision location tagging of textual documents using a natural language processing approach. arXiv (2016)"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chandarana, M., Meszaros, E.L., Trujillo, A., Allen, B.D.: \u2019Fly like this\u2019: natural language interface for UAV mission planning. In: ACHI (2017)","DOI":"10.1177\/1541931213601483"},{"key":"13_CR7","unstructured":"Chen, D., et al.: MLLM-as-a-judge: assessing multimodal LLM-as-a-judge with vision-language benchmark. In: ICML (2024)"},{"issue":"9","key":"13_CR8","doi-asserted-by":"publisher","first-page":"4552","DOI":"10.1109\/TCSVT.2023.3281557","volume":"33","author":"G Chen","year":"2023","unstructured":"Chen, G., Zhu, P., Cao, B., Wang, X., Hu, Q.: Cross-drone transformer network for robust single object tracking. IEEE Trans. Circuits Syst. Video Technol. 33(9), 4552\u20134563 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"13_CR9","unstructured":"Chen, G.H., et al.: Allava: harnessing gpt4v-synthesized data for a lite vision-language model. arXiv (2024)"},{"key":"13_CR10","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv (2015)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: Uniter: universal image-text representation learning. In: ECCV, pp. 104\u2013120 (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"issue":"7","key":"13_CR12","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TCSVT.2021.3135013","volume":"32","author":"M Dai","year":"2021","unstructured":"Dai, M., Hu, J., Zhuang, J., Zheng, E.: A transformer-based feature segmentation and region alignment method for UAV-view geo-localization. IEEE Trans. Circuits Syst. Video Technol. 32(7), 4376\u20134389 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"13_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Dhakal, A., Ahmad, A., Khanal, S., Sastry, S., Jacobs, N.: Sat2cap: mapping fine-grained textual descriptions from satellite images. In: CVPR Workshops, pp. 533\u2013542 (2024)","DOI":"10.1109\/CVPRW63382.2024.00058"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"13_CR16","unstructured":"Doh, S., Choi, K., Lee, J., Nam, J.: LP-musiccaps: LLM-based pseudo music captioning. In: ISMIR (2023)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et al.: An empirical study of training end-to-end vision-and-language transformers. In: CVPR, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"13_CR18","unstructured":"Fang, Y., Zhang, N., Chen, Z., Guo, L., Fan, X., Chen, H.: Domain-agnostic molecular generation with self-feedback. In: ICLR (2023)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Georgakis, G., et al.: Cross-modal map learning for vision-and-language navigation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01502"},{"issue":"30","key":"13_CR20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120","volume":"120","author":"F Gilardi","year":"2023","unstructured":"Gilardi, F., Alizadeh, M., Kubli, M.: Chatgpt outperforms crowd workers for text-annotation tasks. Proc. Natl. Acad. Sci. 120(30), e2305016120 (2023)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"H\u00e4m\u00e4l\u00e4inen, P., Tavast, M., Kunnari, A.: Evaluating large language models in generating synthetic HCI research data: a case study. In: CHI, pp. 1\u201319 (2023)","DOI":"10.1145\/3544548.3580688"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Hong, Y., Rodriguez-Opazo, C., Wu, Q., Gould, S.: VLN-BERT: a recurrent vision-and-language BERT for navigation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Hu, W., et al.: Beyond geo-localization: fine-grained orientation of street-view images by cross-view matching with satellite imagery. In: ACM MM, pp. 6155\u20136164 (2022)","DOI":"10.1145\/3503161.3548102"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Hu, X., Hu, Y., Resch, B., Kersten, J.: Geographic information extraction from texts (GeoExT). In: ECCV, pp. 398\u2013404 (2023)","DOI":"10.1007\/978-3-031-28241-6_44"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Huang, B., Bayazit, D., Ullman, D., Gopalan, N., Tellex, S.: Flight, camera, action! using natural language and mixed reality to control a drone. In: ICRA, pp. 6949\u20136956 (2019)","DOI":"10.1109\/ICRA.2019.8794200"},{"key":"13_CR27","unstructured":"Ikezogwo, W., et al.: Quilt-1m: one million image-text pairs for histopathology. In: NeurIPS, vol.\u00a036 (2024)"},{"key":"13_CR28","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Jin\u00a0Kim, H., Dunn, E., Frahm, J.M.: Learned contextual feature reweighting for image geo-localization. In: CVPR, pp. 2136\u20132145 (2017)","DOI":"10.1109\/CVPR.2017.346"},{"key":"13_CR30","unstructured":"Kuzman, T., Mozetic, I., Ljube\u0161ic, N.: Chatgpt: beginning of an end of manual linguistic data annotation. arXiv (2023)"},{"key":"13_CR31","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"13_CR32","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS, vol.\u00a034, pp. 9694\u20139705 (2021)"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: ICCV, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: ECCV, pp. 121\u2013137 (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Stablellava: enhanced visual instruction tuning with synthesized image-dialogue data. arXiv (2023)","DOI":"10.18653\/v1\/2024.findings-acl.864"},{"key":"13_CR36","doi-asserted-by":"publisher","first-page":"3780","DOI":"10.1109\/TIP.2022.3175601","volume":"31","author":"J Lin","year":"2022","unstructured":"Lin, J., et al.: Joint representation learning and keypoint detection for cross-view geo-localization. IEEE Trans. Image Process. 31, 3780\u20133792 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H.: Lending orientation to neural networks for cross-view geo-localization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00577"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Liu, S., Hussain, A.S., Sun, C., Shan, Y.: Music understanding llama: advancing text-to-music generation with question answering and captioning. In: ICASSP, pp. 286\u2013290 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"13_CR41","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatgpt: towards detailed video understanding via large vision and language models. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Majumdar, A., Shrivastava, A., Lee, S., Anderson, P., Parikh, D., Batra, D.: Improving vision-and-language navigation with image-text pairs from the web. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Meguro, J.I., Ishikawa, K., Hasizume, T., Takiguchi, J.I., Noda, I., Hatayama, M.: Disaster information collection into geographic information system using rescue robots. In: IROS, pp. 3514\u20133520 (2006)","DOI":"10.1109\/IROS.2006.281636"},{"key":"13_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2022.102558","volume":"53","author":"A Mehbodniya","year":"2022","unstructured":"Mehbodniya, A., Webber, J.L., Karupusamy, S., et al.: Improving the geo-drone-based route for effective communication and connection stability improvement in the emergency area ad-hoc network. Sustainable Energy Technol. Assess. 53, 102558 (2022)","journal-title":"Sustainable Energy Technol. Assess."},{"key":"13_CR46","unstructured":"Meng, Y., Michalski, M., Huang, J., Zhang, Y., Abdelzaher, T., Han, J.: Tuning language models as training data generators for augmentation-enhanced few-shot learning. In: ICML, pp. 24457\u201324477 (2023)"},{"key":"13_CR47","unstructured":"OpenAI: GPT-4 technical report. arXiv (2023)"},{"key":"13_CR48","unstructured":"Pangakis, N., Wolken, S., Fasching, N.: Automated annotation with generative AI requires validation. arXiv (2023)"},{"key":"13_CR49","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1016\/j.csbj.2021.01.015","volume":"19","author":"G Pasquini","year":"2021","unstructured":"Pasquini, G., Arias, J.E.R., Sch\u00e4fer, P., Busskamp, V.: Automated methods for cell type annotation on SCRNA-SEQ data. Comput. Struct. Biotechnol. J. 19, 961\u2013969 (2021)","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Qi, Y., Pan, Z., Zhang, S., van\u00a0den Hengel, A., Wu, Q.: Object-and-room informed sequential BERT for vision-and-language navigation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"13_CR51","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"13_CR52","doi-asserted-by":"crossref","unstructured":"Rashid, M.T., Zhang, D.Y., Wang, D.: Socialdrone: an integrated social media and drone sensing system for reliable disaster response. In: INFOCOM, pp. 218\u2013227 (2020)","DOI":"10.1109\/INFOCOM41043.2020.9155522"},{"key":"13_CR53","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Rodrigues, R., Tani, M.: Are these from the same place? Seeing the unseen in cross-view image geo-localization. In: WACV, pp. 3753\u20133761 (2021)","DOI":"10.1109\/WACV48630.2021.00380"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Rodrigues, R., Tani, M.: Global assists local: effective aerial representations for field of view constrained image geo-localization. In: WACV, pp. 3871\u20133879 (2022)","DOI":"10.1109\/WACV51458.2022.00275"},{"key":"13_CR56","doi-asserted-by":"crossref","unstructured":"Shi, Y., Li, H.: Beyond cross-view image retrieval: Highly accurate vehicle localization using satellite image. In: CVPR, pp. 17010\u201317020 (2022)","DOI":"10.1109\/CVPR52688.2022.01650"},{"key":"13_CR57","unstructured":"Shi, Y., Liu, L., Yu, X., Li, H.: Spatial-aware feature aggregation for image based cross-view geo-localization. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"13_CR58","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., Kukleva, A., Hong, X., Rupprecht, C., Schiele, B., Kuehne, H.: Howtocaption: prompting LLMs to transform video annotations at scale. arXiv (2023)","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"13_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3335418","volume":"61","author":"B Sun","year":"2023","unstructured":"Sun, B., Liu, G., Yuan, Y.: F3-net: multiview scene matching for drone-based geo-localization. IEEE Trans. Geosci. Remote Sens. 61, 1\u201311 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"13_CR60","unstructured":"Thomason, J., Gordon, D., Bisk, Y.: Vision-and-dialog navigation. In: CoRL (2020)"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Trivigno, G., Berton, G., Aragon, J., Caputo, B., Masone, C.: Divide &classify: fine-grained classification for city-wide visual geo-localization. In: ICCV, pp. 11142\u201311152 (2023)","DOI":"10.1109\/ICCV51070.2023.01023"},{"issue":"1","key":"13_CR62","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1038\/s41467-020-17266-6","volume":"11","author":"AC Vaucher","year":"2020","unstructured":"Vaucher, A.C., Zipoli, F., Geluykens, J., Nair, V.H., Schwaller, P., Laino, T.: Automated extraction of chemical synthesis actions from experimental procedures. Nat. Commun. 11(1), 3601 (2020)","journal-title":"Nat. Commun."},{"key":"13_CR63","doi-asserted-by":"crossref","unstructured":"Wang, K., Fu, X., Huang, Y., Cao, C., Shi, G., Zha, Z.J.: Generalized UAV object detection via frequency domain disentanglement. In: CVPR, pp. 1064\u20131073 (2023)","DOI":"10.1109\/CVPR52729.2023.00109"},{"key":"13_CR64","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110363","volume":"152","author":"T Wang","year":"2024","unstructured":"Wang, T., Zheng, Z., Sun, Y., Chua, T.S., Yang, Y., Yan, C.: Multiple-environment self-adaptive network for aerial-view geo-localization. Pattern Recognit. 152, 110363 (2024)","journal-title":"Pattern Recognit."},{"issue":"2","key":"13_CR65","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1109\/TCSVT.2021.3061265","volume":"32","author":"T Wang","year":"2021","unstructured":"Wang, T., et al.: Each part matters: local patterns facilitate cross-view geo-localization. IEEE Trans. Circuits Syst. Video Technol. 32(2), 867\u2013879 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"13_CR66","unstructured":"Wang, W., Lin, X., Feng, F., He, X., Chua, T.S.: Generative recommendation: towards next-generation recommender paradigm. arXiv (2023)"},{"key":"13_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Camp: cross-modal adaptive message passing for text-image retrieval. In: ICCV, pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"13_CR68","doi-asserted-by":"crossref","unstructured":"Workman, S., Souvenir, R., Jacobs, N.: Wide-area image geolocalization with aerial reference imagery. In: ICCV, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/ICCV.2015.451"},{"key":"13_CR69","unstructured":"Yang, H., Lu, X., Zhu, Y.: Cross-view geo-localization with layer-to-layer transformer. In: NeurIPS, vol.\u00a034, pp. 29009\u201329020 (2021)"},{"key":"13_CR70","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Zheng, Z., Wang, Y., Zhu, L., Wu, Y.: Towards unified text-based person retrieval: a large-scale multi-attribute and language search benchmark. In: ACM MM, pp. 4492\u20134501 (2023)","DOI":"10.1145\/3581783.3611709"},{"key":"13_CR71","unstructured":"Yu, Q., et al.: Building information modeling and classification by visual learning at a city scale. In: NeurIPS, vol. 30 (2019)"},{"key":"13_CR72","unstructured":"Yu, W., et al.: Generate rather than retrieve: large language models are strong context generators. In: ICLR (2023)"},{"key":"13_CR73","unstructured":"Yu, Y., et al.: Large language model as attributed training data generator: a tale of diversity and bias. In: NeurIPS, vol. 36 (2024)"},{"key":"13_CR74","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: aligning texts with visual concepts. In: ICML, pp. 25994\u201326009 (2022)"},{"key":"13_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lei, Z., Zhang, Z., Li, S.Z.: Context-aware attention network for image-text retrieval. In: CVPR, pp. 3536\u20133545 (2020)","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"13_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, Y., Ma, Y., Zhou, M., Zou, L.: Llmaaa: making large language models as active annotators. In: EMNLP, pp. 13088\u201313103 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.872"},{"key":"13_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, X., Sultani, W., Zhou, Y., Wshah, S.: Cross-view geo-localization via learning disentangled geometric layout correspondence. In: AAAI, vol.\u00a037, pp. 3480\u20133488 (2023)","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"13_CR78","unstructured":"Zhao, W.X., et al.: A survey of large language models. arXiv:2303.18223 (2023)"},{"key":"13_CR79","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wei, Y., Yang, Y.: University-1652: a multi-view multi-source benchmark for drone-based geo-localization. In: ACM MM, pp. 1395\u20131403 (2020)","DOI":"10.1145\/3394171.3413896"},{"issue":"2","key":"13_CR80","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng, Z., Zheng, L., Garrett, M., Yang, Y., Xu, M., Shen, Y.D.: Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multimed. Comput. Commun. Appl. 16(2), 1\u201323 (2020)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"13_CR81","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. In: ICLR (2024)"},{"key":"13_CR82","doi-asserted-by":"crossref","unstructured":"Zhu, F., Zhu, Y., Chang, X., Liang, X.: Vision-and-language navigation with self-supervised auxiliary reasoning tasks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01003"},{"issue":"11","key":"13_CR83","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., et al.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, S., Shah, M., Chen, C.: Transgeo: transformer is all you need for cross-view image geo-localization. In: CVPR, pp. 1162\u20131171 (2022)","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"13_CR85","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: Vigor: cross-view image geo-localization beyond one-to-one retrieval. In: CVPR, pp. 3640\u20133649 (2021)","DOI":"10.1109\/CVPR46437.2021.00364"},{"key":"13_CR86","unstructured":"Zhu, W., et al.: Multimodal C4: an open, billion-scale corpus of images interleaved with text. In: NeurIPS, vol. 36 (2024)"}],"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\/978-3-031-73247-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:38:56Z","timestamp":1732981136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":86,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 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"}}]}}