{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T18:50:03Z","timestamp":1782499803995,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570836","type":"print"},{"value":"9789819570843","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\/978-981-95-7084-3_7","type":"book-chapter","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T10:29:50Z","timestamp":1778236190000},"page":"103-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UniAVLM: Unified Large Audio-Visual Language Models for\u00a0Comprehensive Video Understanding"],"prefix":"10.1007","author":[{"given":"Lecheng","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Younes","family":"Samih","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaochen","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"issue":"2","key":"7_CR1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.-P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"7_CR2","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Jeffrey, W., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"7_CR3","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR4","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv e-prints p. arXiv\u20132407 (2024)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer, Heidelberg (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7_CR6","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR7","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"7_CR8","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"7_CR10","unstructured":"Hu, S., et\u00a0al.: Minicpm: unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395 (2024)"},{"key":"7_CR11","unstructured":"Chen, X., et al.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"7_CR12","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"7_CR13","unstructured":"Chu, Y., et\u00a0al.: Qwen2-audio technical report. arXiv preprint arXiv:2407.10759 (2024)"},{"issue":"9","key":"7_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649447","volume":"56","author":"F Zhao","year":"2024","unstructured":"Zhao, F., Zhang, C., Geng, B.: Deep multimodal data fusion. ACM Comput. Surv. 56(9), 1\u201336 (2024)","journal-title":"ACM Comput. Surv."},{"key":"7_CR15","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"7_CR16","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"7_CR17","unstructured":"Yang, Z., et al.: The dawn of lmms: preliminary explorations with gpt-4v (vision), vol. 9, no. 1, p. 1 (2023). arXiv preprint arXiv:2309.17421"},{"key":"7_CR18","unstructured":"Gemini Team, et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"7_CR19","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"7_CR20","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. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Gong, Y., Khurana, S., Karlinsky, L., Glass, J.: Whisper-at: noise-robust automatic speech recognizers are also strong general audio event taggers. arXiv preprint arXiv:2307.03183 (2023)","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"7_CR22","unstructured":"Rubenstein, P.K., et\u00a0al.: Audiopalm: a large language model that can speak and listen. arXiv preprint arXiv:2306.12925 (2023)"},{"key":"7_CR23","unstructured":"Xu, J., et al.: Qwen2.5-omni technical report. arXiv preprint arXiv:2503.20215 (2025)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: a joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"7_CR25","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol. 2, p.\u00a04 (2021)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: Clip4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Li, H., Niebles, J.C., Hoi, S.C.H.: Align and prompt: video-and-language pre-training with entity prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4953\u20134963 (2022)","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"7_CR29","unstructured":"Li, K., et al.: Videochat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatgpt: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 247\u2013263 (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Sung, Y.L., Lei, J., Bansal, M., Bertasius, G.: Vision transformers are parameter-efficient audio-visual learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2299\u20132309 (2023)","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"7_CR33","unstructured":"Luo, R., et al.: Valley: video assistant with large language model enhanced ability. arXiv preprint arXiv:2306.07207 (2023)"},{"key":"7_CR34","unstructured":"Hurst, A., et\u00a0al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"7_CR35","unstructured":"Alamri, H., et\u00a0al.: Audio visual scene-aware dialog (avsd) challenge at dstc7. arXiv preprint arXiv:1806.00525 (2018)"},{"key":"7_CR36","unstructured":"Wang, Y., et\u00a0al.: Internvideo2. 5: empowering video mllms with long and rich context modeling. arXiv preprint arXiv:2501.12386 (2025)"},{"key":"7_CR37","unstructured":"Zhu, J., et\u00a0al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"7_CR38","unstructured":"Yao, Y., et\u00a0al.: Minicpm-v: a gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800 (2024)"},{"key":"7_CR39","unstructured":"Qwen Team. Qwen2.5: A party of foundation models (2024)"},{"key":"7_CR40","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":"7_CR41","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"7_CR42","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7084-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T18:15:19Z","timestamp":1782497719000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7084-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570836","9789819570843"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7084-3_7","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":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"21 November 2025","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":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}