{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:56:29Z","timestamp":1778082989216,"version":"3.51.4"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032144942","type":"print"},{"value":"9783032144959","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-14495-9_4","type":"book-chapter","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:22:58Z","timestamp":1768576978000},"page":"47-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatial-ViLT: Enhancing Visual Spatial Reasoning Through Multi-task Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4048-5784","authenticated-orcid":false,"given":"Chashi Mahiul","family":"Islam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0865-0019","authenticated-orcid":false,"given":"Oteo","family":"Mamo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0948-4234","authenticated-orcid":false,"given":"Samuel Jacob","family":"Chacko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9320-3872","authenticated-orcid":false,"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8754-0311","authenticated-orcid":false,"given":"Weikuan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.neunet.2023.11.031","volume":"170","author":"G Azkune","year":"2024","unstructured":"Azkune, G., Salaberria, A., Agirre, E.: Grounding spatial relations in text-only language models. Neural Netw. 170, 215\u2013226 (2024)","journal-title":"Neural Netw."},{"key":"4_CR2","unstructured":"Balazevic, I., Steiner, D., Parthasarathy, N., Arandjelovi\u0107, R., Henaff, O.: Towards in-context scene understanding. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR3","doi-asserted-by":"publisher","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(6), 679\u2013698 (1986). https:\/\/doi.org\/10.1109\/TPAMI.1986.4767851","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. arXiv preprint arXiv:2401.12168 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"4_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102897","volume":"192","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Tian, Y., He, M.: Monocular human pose estimation: a survey of deep learning-based methods. Comput. Vis. Image Underst. 192, 102897 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: Spatialrgpt: Grounded spatial reasoning in vision language model. arXiv preprint arXiv:2406.01584 (2024)","DOI":"10.52202\/079017-4293"},{"key":"4_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, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"4_CR8","unstructured":"Dang, L.H., Le, T.M., Le, V., Phuong, T.M., Tran, T.: Sadl: An effective in-context learning method for compositional visual QA (2024). https:\/\/arxiv.org\/abs\/2407.01983"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kamath, A., Hessel, J., Chang, K.W.: What\u2019s up with vision-language models? Investigating their struggle with spatial reasoning. arXiv preprint arXiv:2310.19785 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"4_CR11","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, C., Zhou, H., Collier, N., Korhonen, A., Vuli\u0107, I.: Topviewrs: Vision-language models as top-view spatial reasoners. arXiv preprint arXiv:2406.02537 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.106"},{"key":"4_CR13","unstructured":"Li, F., Hogg, D., Cohn, A.G.: 1. reframing spatial reasoning evaluation in language models: A real-world simulation benchmark for qualitative reasoning (2024)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Huang, J., Jin, P., Song, G., Wu, Q., Chen, J.: Toward 3D spatial reasoning for human-like text-based visual question answering. arXiv preprint arXiv:2209.10326 (2022)","DOI":"10.1109\/TIP.2023.3276570"},{"key":"4_CR15","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"issue":"4","key":"4_CR16","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s40484-020-0226-1","volume":"8","author":"Y Li","year":"2020","unstructured":"Li, Y., Luo, Y.: Performance-weighted-voting model: An ensemble machine learning method for cancer type classification using whole-exome sequencing mutation. Quan. Biol. 8(4), 347\u2013358 (2020)","journal-title":"Quan. Biol."},{"key":"4_CR17","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1162\/tacl_a_00566","volume":"11","author":"F Liu","year":"2023","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguis. 11, 635\u2013651 (2023)","journal-title":"Trans. Assoc. Comput. Linguis."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"issue":"6","key":"4_CR19","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1111\/tgis.12815","volume":"25","author":"CK Marchi Fagundes","year":"2021","unstructured":"Marchi Fagundes, C.K., Stock, K., Delazari, L.S.: A cross-linguistic study of spatial location descriptions in new Zealand English and Brazilian Portuguese natural language. Trans. GIS 25(6), 3159\u20133187 (2021)","journal-title":"Trans. GIS"},{"key":"4_CR20","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"4_CR21","unstructured":"Rajabi, N., Kosecka, J.: Towards grounded visual spatial reasoning in multi-modal vision language models. ArXiv abs\/2308.09778 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261048680"},{"issue":"3","key":"4_CR22","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: Spatial and visual perspective-taking via view rotation and relation reasoning for embodied reference understanding. In: European Conference on Computer Vision, pp. 201\u2013218. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_12"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Singh, Y., Biswas, A., Bora, A., Malakar, D., Chakraborty, S., Bera, S.: Design perspectives of multi-task deep-learning models and applications. Machine Learning Algorithms for Signal and Image Processing, pp. 45\u201363 (2022)","DOI":"10.1002\/9781119861850.ch4"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"4_CR26","unstructured":"Yi, K., et al.: Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019)"},{"key":"4_CR27","unstructured":"Zhou, Q.Y., Park, J., Koltun, V.: Open3d: A modern library for 3d data processing. arXiv preprint arXiv:1801.09847 (2018)"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-14495-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:23:03Z","timestamp":1768576983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-14495-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032144942","9783032144959"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-14495-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Vegas, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}