{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:45:28Z","timestamp":1782949528666,"version":"3.54.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031936876","type":"print"},{"value":"9783031936883","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"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\/978-3-031-93688-3_31","type":"book-chapter","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T08:06:46Z","timestamp":1752912406000},"page":"431-446","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt2LVideos: Exploring Prompts for\u00a0Understanding Long-Form Multimodal Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3460-9151","authenticated-orcid":false,"given":"Soumya Shamarao","family":"Jahagirdar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0839-1849","authenticated-orcid":false,"given":"Jayasree","family":"Saha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-7057","authenticated-orcid":false,"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Bojanowski, P., Agrawal, N., Sivic, J., Laptev, I., Lacoste-Julien, S.: Unsupervised learning from narrated instruction videos. In: CVPR, pp. 4575\u20134583. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.495"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: ICCV, pp. 4290\u20134300. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"31_CR3","unstructured":"Bulathwela, S., Perez-Ortiz, M., Novak, E., Yilmaz, E., Shawe-Taylor, J.: PEEK: a large dataset of learner engagement with educational videos. CoRR, abs\/2109.03154 (2021)"},{"key":"31_CR4","unstructured":"Bulathwela, S., Perez-Ortiz, M., Yilmaz, E., Shawe-Taylor, J.: Vlengagement: a dataset of scientific video lectures for evaluating population-based engagement. CoRR, abs\/2011.02273 (2020)"},{"key":"31_CR5","unstructured":"Chen, H., Wang, X., Chen, H., Song, Z., Jia, J., Zhu, W.: Grounding-prompter: prompting LLM with multimodal information for temporal sentence grounding in long videos. CoRR, abs\/2312.17117 (2023)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Chou, S.-H., et al.: Multi-modal news understanding with professionally labelled videos (reutersvilnews). CoRR, abs\/2401.12419 (2024)","DOI":"10.21428\/594757db.dd360009"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J.: A thousand frames in just a few words: lingual description of videos through latent topics and sparse object stitching. In: CVPR, pp. 2634\u20132641 (2013)","DOI":"10.1109\/CVPR.2013.340"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Dutta, K., Mathew, M., Krishnan, P., Jawahar, C.V.: Localizing and recognizing text in lecture videos. In: ICFHR, pp. 235\u2013240. IEEE Computer Society (2018)","DOI":"10.1109\/ICFHR-2018.2018.00049"},{"key":"31_CR9","unstructured":"EasyOCR Developers. EasyOCR: A High Accuracy Real-Time OCR Engine (2024). https:\/\/github.com\/JaidedAI\/EasyOCR"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: EMNLP (1), pp. 6769\u20136781. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"31_CR11","unstructured":"Gandhi, A., Biswas, A., Deshmukh, O.: Topic transition in educational videos using visually salient words. In: EDM, pp. 289\u2013296. International Educational Data Mining Society (IEDMS) (2015)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, P., Gupta, M.: Newskvqa: knowledge-aware news video question answering. In: PAKDD (3). Lecture Notes in Computer Science, vol. 13282, pp. 3\u201315. Springer (2022)","DOI":"10.1007\/978-3-031-05981-0_1"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Hegde, S., Jahagirdar, S., Gangisetty, S.: Making the V in text-VQA matter. In: CVPR Workshops, pp. 5580\u20135588. IEEE (2023)","DOI":"10.1109\/CVPRW59228.2023.00590"},{"key":"31_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-86549-8_22","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"S Jahagirdar","year":"2021","unstructured":"Jahagirdar, S., Gangisetty, S., Mishra, A.: Look, read and ask: learning to ask questions by reading text in images. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 335\u2013349. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_22"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Jahagirdar, S., Mathew, M., Karatzas, D., Jawahar, C.V.: Understanding video scenes through text: insights from text-based video question answering. In: ICCV (Workshops), pp. 4648\u20134652. IEEE (2023)","DOI":"10.1109\/ICCVW60793.2023.00500"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Jahagirdar, S., Mathew, M., Karatzas, D., Jawahar, C.V.: Watching the news: towards videoqa models that can read. In: WACV, pp. 4430\u20134439. IEEE (2023)","DOI":"10.1109\/WACV56688.2023.00442"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: ECCV (35). Lecture Notes in Computer Science, vol. 13695, pp. 105\u2013124. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Revealing single frame bias for video-and-language learning. In: ACL (1), pp. 487\u2013507. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: EMNLP (1), pp. 3045\u20133059. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9):195:1\u2013195:35 (2023)","DOI":"10.1145\/3560815"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Mahapatra, D., Mariappan, R., Rajan, V.: Automatic hierarchical table of contents generation for educational videos. In: WWW (Companion Volume), pp. 267\u2013274. ACM (2018)","DOI":"10.1145\/3184558.3186336"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: Docvqa: a dataset for VQA on document images. In: WACV, pp. 2199\u20132208. IEEE (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J. B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV, pp. 2630\u20132640. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"31_CR25","unstructured":"OpenAI. Chatgpt: Large-scale language models. https:\/\/openai.com\/research\/chatgpt"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Papalampidi, P., Keller, F., Lapata, M.: Movie summarization via sparse graph construction. In: AAAI, pp. 13631\u201313639. AAAI Press (2021)","DOI":"10.1609\/aaai.v35i15.17607"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR, pp. 3202\u20133212. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Rouditchenko, A., et al.: Avlnet: learning audio-visual language representations from instructional videos. In: Interspeech, pp. 1584\u20131588. ISCA (2021)","DOI":"10.21437\/Interspeech.2021-1312"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Darshan\u00a0Singh, S., Gupta, A., Jawahar, C.V., Tapaswi, M.: Unsupervised audio-visual lecture segmentation. In: WACV, pp. 5221\u20135230. IEEE (2023)","DOI":"10.1109\/WACV56688.2023.00520"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"31_CR31","unstructured":"Silero Team. Silero models: pre-trained enterprise-grade STT\/TTS models and benchmarks (2021). https:\/\/github.com\/snakers4\/silero-models"},{"key":"31_CR32","unstructured":"Torabi, A., Tandon, N., Sigal, L.: Learning language-visual embedding for movie understanding with natural-language. CoRR, abs\/1609.08124 (2016)"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S., Khan, F.S., Shah, M.: Vita-clip: video and text adaptive CLIP via multimodal prompting. In: CVPR, pp. 23034\u201323044. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"31_CR34","unstructured":"White, J., et al.: A prompt pattern catalog to enhance prompt engineering with chatgpt. CoRR, abs\/2302.11382 (2023)"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR, pp. 5288\u20135296. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, H., Mart\u00edn-Mart\u00edn, R., Kapadia, M., Savarese, S., Niebles, J.C.: Procedure-aware pretraining for instructional video understanding. In: CVPR, pp. 10727\u201310738. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: AAAI, pp. 7590\u20137598. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12342"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-93688-3_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:13:10Z","timestamp":1782947590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-93688-3_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"ISBN":["9783031936876","9783031936883"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-93688-3_31","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"20 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chennai","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cvip2024.iiitdm.ac.in\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}