{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:10:02Z","timestamp":1771600202007,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032151339","type":"print"},{"value":"9783032151346","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\/978-3-032-15134-6_2","type":"book-chapter","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T14:23:09Z","timestamp":1771597389000},"page":"19-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CommuteQA: Visual Question Answering for\u00a0Bus Transport"],"prefix":"10.1007","author":[{"given":"Anwar","family":"Shaikh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prakrit","family":"Garg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahisha","family":"Ramesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ritwik","family":"Kashyap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghava","family":"Mutharaju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajiv Ratn","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2_CR2","unstructured":"Jocher, G., Wightman, R., Bochkovskiy, A.: YOLOv5: An Incremental Improvement. arXiv preprint arXiv:2107.08430 (2021). https:\/\/arxiv.org\/abs\/2107.08430"},{"key":"2_CR3","unstructured":"Bochkovskiy, A., Liao, H.Y.M.: YOLOv5-P6: Faster, Better YOLOv5 in Production. arXiv preprint arXiv:2104.13963 (2021). https:\/\/arxiv.org\/abs\/2104.13963"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-vqa: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"2_CR5","unstructured":"Open Transit Data. https:\/\/otd.delhi.gov.in\/"},{"key":"2_CR6","unstructured":"National Transit Map Data. https:\/\/www.bts.dot.gov\/newsroom\/national-transit-map-data"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"2_CR8","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":"2_CR9","unstructured":"Chen, X., et al.: Pali: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"2_CR10","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning for enhanced multimodal interaction. In: Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (2023)"},{"key":"2_CR11","unstructured":"Huerta, E.A., Kumar, S., Gormley, M.: Low-rank adaptation of large language models (LoRA): streamlining model tuning. In: Proceedings of the International Conference on Learning Representations (ICLR 2021) (2021)"},{"key":"2_CR12","unstructured":"Zhang, J., Chen, P., Xiao, L.: Parameter-efficient transfer learning for NLP. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020) (2020)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019) (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ding, Y., Yu, J., Liu, B., Hu, Y., Cui, M., Wu, Q.: Mukea: multimodal knowledge extraction and accumulation for knowledge-based visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5089\u20135098 (2022)","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: Uniter: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"2_CR17","unstructured":"Devlin, J., Chang, MW., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Ma\u00f1as, O., Krojer, B., Agrawal, A.: Improving automatic VQA evaluation using large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4171\u20134179. (2024)","DOI":"10.1609\/aaai.v38i5.28212"},{"key":"2_CR19","unstructured":"llava-1.5-7b (Vicuna) Model. https:\/\/huggingface.co\/liuhaotian\/llava-v1.5-7b. Accessed 18 Aug 2024"},{"key":"2_CR20","unstructured":"llava-1.6-7b-vicuna Model. https:\/\/huggingface.co\/liuhaotian\/llava-v1.6-vicuna-7b. Accessed 18 Aug 2024"},{"key":"2_CR21","unstructured":"llava-1.6-7b-mistral Model. https:\/\/huggingface.co\/liuhaotian\/llava-v1.6-mistral-7b. Accessed 18 Aug 2024"},{"key":"2_CR22","unstructured":"BakLLaVA model. https:\/\/huggingface.co\/SkunkworksAI\/BakLLaVA-1. Accessed 18 Aug 2024"},{"key":"2_CR23","unstructured":"paligemma-3b-pt-224 Model. https:\/\/huggingface.co\/google\/paligemma-3b-pt-224. Accessed 18 Aug 2024"}],"container-title":["Lecture Notes in Computer Science","Big Data and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-15134-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T14:23:19Z","timestamp":1771597399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-15134-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032151339","9783032151346"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-15134-6_2","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":"21 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BDA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangalore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bigda2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bda2025.iiitb.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}