{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:02:43Z","timestamp":1784361763513,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234288","type":"print"},{"value":"9789819234295","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3429-5_19","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T07:07:25Z","timestamp":1784358445000},"page":"225-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SparseVision-Drive: Hierarchical Sparse Multi-view Visual Aggregation for Autonomous-Driving VLMs"],"prefix":"10.1007","author":[{"given":"Huilin","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senmao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Watzenig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Sima, C., et al.: Drivelm: driving with graph visual question answering. In: European Conference on Computer Vision, pp. 256\u2013274. Springer (2024)","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"19_CR2","unstructured":"Li, Y., et al.: Recogdrive: a reinforced cognitive framework for end-to-end autonomous driving. arXiv preprint. https:\/\/arxiv.org\/abs\/2506.08052 (2025)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Huang, Y., Sansom, J., Ma, Z., Gervits, F., Chai, J.: Drivlme: enhancing LLM-based autonomous driving agents with embodied and social experiences. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3153\u20133160. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10802555"},{"key":"19_CR4","unstructured":"Zhang, J., Yang, X., Wang, T., Yao, Y., Petiushko, A., Li, B.: Safeauto: knowledge-enhanced safe autonomous driving with multimodal foundation models. arXiv preprint. https:\/\/arxiv.org\/abs\/2503.00211 (2025)"},{"key":"19_CR5","unstructured":"Gopalkrishnan, A., Greer, R., Trivedi, M.: Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving. arXiv preprint. https:\/\/arxiv.org\/abs\/2403.19838 (2024)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Opera: alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13418\u201313427 (2024)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, E., Dai, X., Huang, M., Lv, Y., Miao, Q.: Minidrive: more efficient vision-language models with multi-level 2d features as text tokens for autonomous driving. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 255\u2013269. Springer (2025)","DOI":"10.1007\/978-981-95-5740-0_18"},{"key":"19_CR8","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"J-B Alayrac","year":"2022","unstructured":"Alayrac, J.-B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural Inf. Proces. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"19_CR9","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.-J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. Adv. Neural Inf. Proces. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"19_CR10","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. arXiv preprint. https:\/\/arxiv.org\/abs\/2202.07800 (2022)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"19_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint. https:\/\/arxiv.org\/abs\/2010.11929 (2020)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"19_CR14","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"19_CR15","unstructured":"Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: UniRepLKNet: a Universal perception large-kernel convnet for audio video point cloud time-series and image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5513\u20135524 (2024)","DOI":"10.1109\/CVPR52733.2024.00527"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3429-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T07:07:29Z","timestamp":1784358449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3429-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234288","9789819234295"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3429-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}