{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:06Z","timestamp":1780949226404,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007836","name":"NSFC General Program","doi-asserted-by":"publisher","award":["62576110"],"award-info":[{"award-number":["62576110"]}],"id":[{"id":"10.13039\/100007836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3663658","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:57:15Z","timestamp":1770843435000},"page":"8372-8384","source":"Crossref","is-referenced-by-count":0,"title":["Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5039-7568","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2431-3410","authenticated-orcid":false,"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5700-9326","authenticated-orcid":false,"given":"Xiaolei","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0593-5281","authenticated-orcid":false,"given":"Haotian","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1549-6979","authenticated-orcid":false,"given":"Yi","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3668-6518","authenticated-orcid":false,"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7226-6923","authenticated-orcid":false,"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9633-0033","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4897-9209","authenticated-orcid":false,"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref3","first-page":"18378","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32171"},{"key":"ref5","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref8","article-title":"Tokenpacker: Efficient visual projector for multimodal llm","author":"Li","year":"2024","journal-title":"arXiv:2407.02392"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref10","article-title":"LLaVA-PruMerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv:2403.15388"},{"key":"ref11","article-title":"[CLS] attention is all you need for training-free visual token pruning: Make vlm inference faster","author":"Zhang","year":"2024","journal-title":"arXiv:2412.01818"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref13","article-title":"SparseVLM: Visual token sparsification for efficient vision-language model inference","author":"Zhang","year":"2024","journal-title":"arXiv:2410.04417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02780"},{"key":"ref16","article-title":"SalGAN: Visual saliency prediction with adversarial networks","volume-title":"Proc. CVPR Scene Understand. Workshop (SUNw)","author":"Pan"},{"key":"ref17","article-title":"Global semantic-guided sub-image feature weight allocation in high-resolution large vision-language models","author":"Liang","year":"2025","journal-title":"arXiv:2501.14276"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225865"},{"key":"ref19","article-title":"Grok-1.5 vision preview","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3588892"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3444895"},{"key":"ref22","first-page":"370","article-title":"ShareGPT4V: Improving large multi-modal models with better captions","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Lin"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref24","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3457610"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551084"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref28","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref29","article-title":"PALI-X: On scaling up a multilingual vision and language model","author":"Chen","year":"2023","journal-title":"arXiv:2305.18565"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1348"},{"key":"ref32","first-page":"87874","article-title":"What matters when building vision-language models?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Lauren\u00e7on"},{"key":"ref33","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01360"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34366"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01939"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00877"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref40","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Lu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref45","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref47","first-page":"57730","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111932"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11393550.pdf?arnumber=11393550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:54Z","timestamp":1780948494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":53,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3663658","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}