{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:46:50Z","timestamp":1782949610534,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698554","type":"print"},{"value":"9789819698561","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9856-1_9","type":"book-chapter","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T12:38:24Z","timestamp":1753187904000},"page":"96-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LBA: Multi-Scale Video Segment Sampling for Open-Ended Video Question Answering"],"prefix":"10.1007","author":[{"given":"Jin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"9_CR1","unstructured":"Li, D., et al.: Aria: An open multimodal native mixture-of-experts model. CoRR abs\/2410.05993 (2024)"},{"key":"9_CR2","unstructured":"Li, K., He, Y., Wang, Y., Li, Y., Wang, W., Ping, L., et al.: Videochat: Chat-centric video understanding. CoRR abs\/2305.06355 (2023)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Activitynet-qa: a dataset for understanding complex web videos via question answering. In: AAAI, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Liang, T., Tan, C., Xia, B., Zheng, W.S., Hu, J.F.: Ranking distillation for open-ended video question answering with insufficient labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13161\u201313170 (2024)","DOI":"10.1109\/CVPR52733.2024.01250"},{"key":"9_CR6","unstructured":"He, X., Chen, S., Ma, F., Huang, Z., Jin, X., Liu, Z., et al.: VLAB: enhancing video language pre-training by feature adapting and blending. CoRR abs\/2305.13167 (2023)"},{"key":"9_CR7","unstructured":"Cheng, Z., et al.: Videollama 2: advancing spatial-temporal modeling and audio understanding in video-llms. CoRR abs\/2406.07476 (2024)"},{"key":"9_CR8","unstructured":"Wang, Z., et al.: Videotree: adaptive tree-based video representation for LLM reasoning on long videos. CoRR abs\/2405.19209 (2024)"},{"key":"9_CR9","unstructured":"Park, J., Ranasinghe, K., Kahatapitiya, K., Ryoo, W., Kim, D., Ryoo, M.S.: Too many frames, not all useful: Efficient strategies for long-form video QA. CoRR abs\/2406.09396 (2024)"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"He, B., et al.: Ma-lmm: Memory-augmented large multimodal model for long-term video understanding. In: CVPR, pp. 13504\u201313514 (2024)","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, B., Chen, Y., Cheng, M., Shi, X.: Multi: efficient video-and-language understanding with text-guided multiway-sampler and multiple choice modeling, pp. 6297\u20136305. AAAI Press (2024)","DOI":"10.1609\/aaai.v38i6.28448"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Peng, M., Liu, L., Li, Z., Shi, Y., Zhou, X.: Multi-semantic alignment co-reasoning network for video question answering. In: ICIP, pp. 2090\u20132094 (2023)","DOI":"10.1109\/ICIP49359.2023.10222262"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S., Wang, W., Zhang, C., Huang, H.: Heterogeneous memory enhanced multi-modal attention model for video question answering. In: CVPR, pp. 1999\u20132007 (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Sohn, K.: Bridge to answer: Structure-aware graph interaction network for video question answering. In: CVPR, pp. 15526\u201315535 (2021)","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Unmasked teacher: Towards training-efficient video foundation models. In: ICCV, pp. 19948\u201319960 (2023)","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Valor: Vision-audio-language omni-perception pretraining model and dataset. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, S., Chu, J., Choi, M., Kim, H.J.: VID-TLDR: Training free token merging for light-weight video transformer. In: CVPR, pp. 18771\u201318781 (2024)","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Atrey, P.K., Kumar, V., Kumar, A., Kankanhalli, M.S.: Experiential sampling based foreground\/background segmentation for video surveillance. In: ICME, pp. 1809\u20131812 (2006)","DOI":"10.1109\/ICME.2006.262904"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Karsch, K., Liu, C., Kang, S.B.: Depth extraction from video using non-parametric sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) Computer Vision \u2013 ECCV 2012. ECCV 2012. LNCS, vol. 7576. Springer, Berlin, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_56","DOI":"10.1007\/978-3-642-33715-4_56"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: Scsampler: sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: Clipbert for video-and-language learning via sparse sampling. In: CVPR, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-llava: learning united visual representation by alignment before projection. In: EMNLP, pp. 5971\u20135984. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"9_CR23","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. CoRR abs\/2307.09288 (2023)"},{"key":"9_CR24","unstructured":"Abdin, M.I., et al.: Phi-3 technical report: a highly capable language model locally on your phone. CoRR abs\/2404.14219 (2024)"},{"key":"9_CR25","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00d716 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"9_CR26","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for CLIP at scale. CoRR abs\/2303.15389 (2023)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Dai, W., Li, J., Li, D.,Tiong, A.M.H., et al.: Instructblip: Towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-2142"},{"key":"9_CR28","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"9_CR29","unstructured":"Kuo, W., et al.: Mammut: a simple architecture for joint learning for multimodal tasks. Trans. Mach. Learn. Res. 2023 (2023)"},{"key":"9_CR30","unstructured":"Xu, H., et al.: mplug-2: A modularized multi-modal foundation model across text,image and video. In: ICML, pp. 38728\u201338748 (2023)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, H., Wang, Q., Zhao, Z., Sun, M., et al.: VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset. In: NeurIPS (2023)","DOI":"10.52202\/075280-3185"},{"key":"9_CR32","unstructured":"Chen, S., He, X., Li, H., Jin, X., Feng, J., Liu, J.: COSA: concatenated sample pretrained vision-language foundation model. In: ICLR. OpenReview.net (2024)"},{"key":"9_CR33","unstructured":"Ollama: GitHub repository. https:\/\/github.com\/ollama\/ollama. Accessed\u202f10\u202fApr\u202f2025"}],"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\/978-981-96-9856-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:40:48Z","timestamp":1782949248000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9856-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698554","9789819698561"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9856-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 July 2025","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":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}