{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:14:39Z","timestamp":1783523679686,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819224791","type":"print"},{"value":"9789819224807","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-2480-7_29","type":"book-chapter","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:21:38Z","timestamp":1783520498000},"page":"464-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Instruction Tuning for\u00a0Video Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8861-4001","authenticated-orcid":false,"given":"Weipeng","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anlin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiancai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edith C. H.","family":"Ngai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"29_CR1","unstructured":"Bai, J., et al.: Qwen technical report (2023). https:\/\/arxiv.org\/abs\/2309.16609"},{"key":"29_CR2","unstructured":"Bi, J., Nguyen, N.M., Vosoughi, A., Xu, C.: Misar: A multimodal instructional system with augmented reality (2023). arXiv:2310.11699 arXiv preprint"},{"key":"29_CR3","unstructured":"Cai, M., et al.: Temporalbench: Benchmarking fine-grained temporal understanding for multimodal video models (2024). https:\/\/arxiv.org\/abs\/2410.10818"},{"key":"29_CR4","unstructured":"Castellano, B.: Pyscenedetect. https:\/\/scenedetect.com\/en\/latest\/"},{"key":"29_CR5","unstructured":"Cheang, C.L., et\u00a0al.: Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation. arXiv preprint arXiv:2410.06158 (2024)"},{"key":"29_CR6","unstructured":"Chen, G.H., et al.: Allava: harnessing gpt4v-synthesized data for lite vision-language models (2024). https:\/\/arxiv.org\/abs\/2402.11684"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: Improving large multi-modal models with better captions (2023). https:\/\/arxiv.org\/abs\/2311.12793","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"29_CR8","unstructured":"Cheng, Z., et al.: Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms (2024). https:\/\/arxiv.org\/abs\/2406.07476"},{"key":"29_CR9","unstructured":"Fu, C., et al.: Mme: a comprehensive evaluation benchmark for multimodal large language models (2024). https:\/\/arxiv.org\/abs\/2306.13394"},{"key":"29_CR10","unstructured":"Fu, C., et al.: Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis (2024). https:\/\/arxiv.org\/abs\/2405.21075"},{"key":"29_CR11","unstructured":"Hurst, A., et al.: Gpt-4o system card (2024). arXiv:2410.21276 arXiv preprint"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Kim, W., Choi, C., Lee, W., Rhee, W.: An image grid can be worth a video: Zero-shot video question answering using a vlm (2024). https:\/\/arxiv.org\/abs\/2403.18406","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"29_CR13","unstructured":"Li, B., et al.: Llava-onevision: Easy visual task transfer (2024). https:\/\/arxiv.org\/abs\/2408.03326"},{"key":"29_CR14","unstructured":"Li, Y., et al.: Mini-gemini: mining the potential of multi-modality vision language models (2024). https:\/\/arxiv.org\/abs\/2403.18814"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"29_CR16","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., Lee, Y.J.: Llava-next: improved reasoning, ocr, and world knowledge, January 2024. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Mmbench: Is your multi-modal model an all-around player? (2024). https:\/\/arxiv.org\/abs\/2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Tempcompass: Do video llms really understand videos? (2024). https:\/\/arxiv.org\/abs\/2403.00476","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Ocrbench: On the hidden mystery of ocr in large multimodal models (2024). https:\/\/arxiv.org\/abs\/2305.07895","DOI":"10.1007\/s11432-024-4235-6"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: Multimodal reasoning via thought chains for science question answering (2022). https:\/\/arxiv.org\/abs\/2209.09513","DOI":"10.52202\/068431-0182"},{"key":"29_CR22","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 (2024). https:\/\/arxiv.org\/abs\/2306.05424","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"29_CR23","unstructured":"OpenAI: Gpt-4 technical report (2024). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"29_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Song, E., et al.: Moviechat: from dense token to sparse memory for long video understanding (2024). https:\/\/arxiv.org\/abs\/2307.16449","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"29_CR26","unstructured":"Tang, Y., et al.: Video understanding with large language models: A survey (2024). https:\/\/arxiv.org\/abs\/2312.17432"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Tong, S., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal llms. ArXiv abs\/2406.16860 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270703300","DOI":"10.52202\/079017-2771"},{"key":"29_CR28","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models (2023). https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"29_CR29","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023). https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"29_CR30","unstructured":"Wang, P., et al.: Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution (2024). https:\/\/arxiv.org\/abs\/2409.12191"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Gpt4video: a unified multimodal large language model for lnstruction-followed understanding and safety-aware generation (2024). https:\/\/arxiv.org\/abs\/2311.16511","DOI":"10.1145\/3664647.3681464"},{"key":"29_CR32","unstructured":"Wu, H., et al.: Unleashing large-scale video generative pre-training for visual robot manipulation. arXiv preprint arXiv:2312.13139 (2023)"},{"key":"29_CR33","unstructured":"Wu, W.: Freeva: Offline mllm as training-free video assistant (2024). https:\/\/arxiv.org\/abs\/2405.07798"},{"key":"29_CR34","unstructured":"Xu, L., Zhao, Y., Zhou, D., Lin, Z., Ng, S.K., Feng, J.: Pllava : Parameter-free llava extension from images to videos for video dense captioning (2024). https:\/\/arxiv.org\/abs\/2404.16994"},{"key":"29_CR35","unstructured":"Yang, A., et al.: Qwen2 technical report (2024). https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training (2023). https:\/\/arxiv.org\/abs\/2303.15343","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"29_CR37","unstructured":"Zhang, Y., et al.: Llava-next: A strong zero-shot video understanding model, April 2024. https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"29_CR38","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data (2024). https:\/\/arxiv.org\/abs\/2410.02713"},{"key":"29_CR39","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models (2023). https:\/\/arxiv.org\/abs\/2304.10592"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Engineering for Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2480-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:21:43Z","timestamp":1783520503000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2480-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"ISBN":["9789819224791","9789819224807"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2480-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"assertion":[{"value":"9 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"During the preparation of this manuscript, we used large language models only for grammar checking and writing refinement.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Usage of Large Language Models"}},{"value":"FLINS-ISKE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Systems and Knowledge Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","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":"iske2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.flins.cc","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}