{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T19:18:28Z","timestamp":1788203908048,"version":"build-2803163510"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2023ZD0121104"],"award-info":[{"award-number":["2023ZD0121104"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62406264"],"award-info":[{"award-number":["62406264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3673542","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:04Z","timestamp":1773347884000},"page":"7414-7424","source":"Crossref","is-referenced-by-count":0,"title":["Sparrow: Data-Efficient Video-LLM With Text-to-Image Augmentation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5356-1800","authenticated-orcid":false,"given":"Shukang","family":"Yin","sequence":"first","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0079-7668","authenticated-orcid":false,"given":"Chaoyou","family":"Fu","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8103-0321","authenticated-orcid":false,"given":"Sirui","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4276-3133","authenticated-orcid":false,"given":"Chunjiang","family":"Ge","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-6612","authenticated-orcid":false,"given":"Yuhan","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongdong","family":"Luo","sequence":"additional","affiliation":[{"name":"Xiamen University","place":["Xiamen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caifeng","family":"Shan","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557620"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557692"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535389"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3581797"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521758"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref14","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref16","article-title":"SlowFast-LLaVA: A strong training-free baseline for video large language models","author":"Xu","year":"2024"},{"key":"ref17","article-title":"Free video-LLM: Prompt-guided visual perception for efficient training-free video LLMs","author":"Han","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref23","article-title":"PLLaVA: Parameter-free LLaVA extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref24","article-title":"LLaVA-next: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref25","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref26","article-title":"Longvila: Scaling long-context visual language models for long videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02620-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref30","article-title":"Keyvideollm: Towards large-scale video keyframe selection","author":"Liang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0185"},{"key":"ref37","article-title":"Temporal reasoning transfer from text to video","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2025"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref41","article-title":"SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023"},{"key":"ref42","article-title":"Sharegemini: Scaling up video caption data for multimodal large language models","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref44","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024"},{"key":"ref45","article-title":"Token merging: Your vit but faster","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bolya","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref47","first-page":"55006","article-title":"LIMA: Less is more for alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.440"},{"key":"ref49","article-title":"Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2025"},{"key":"ref50","article-title":"WildChat: 1m chatGPT interaction logs in the wild","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2024"},{"key":"ref51","article-title":"LongLoRA: Efficient fine-tuning of long-context large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref52","article-title":"LongQLoRA: Efficient and effective method to extend context length of large language models","author":"Yang","year":"2023"},{"key":"ref53","article-title":"GPT-4v(ision) system card"},{"key":"ref54","article-title":"Introducing claude 3.5 sonnet"},{"key":"ref55","article-title":"Hello GPT-4o"},{"key":"ref56","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref57","article-title":"Vita: Towards open-source interactive omni multimodal LLM","author":"Fu","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2529"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0907"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01278"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11433052.pdf?arnumber=11433052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T19:12:05Z","timestamp":1788203525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3673542","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}