{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:51:54Z","timestamp":1791355914632,"version":"4.3.1"},"reference-count":51,"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":[{"name":"National Key R&D Program of China","award":["2023YFB4704900"],"award-info":[{"award-number":["2023YFB4704900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3736818","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:09:02Z","timestamp":1790708942000},"page":"10433-10448","source":"Crossref","is-referenced-by-count":0,"title":["AdaCompVL: Adaptive Compression of Spatiotemporal and Cross-Modal Redundancy for Efficient Video\u2013Language Learning"],"prefix":"10.1109","volume":"35","author":[{"given":"Jianxin","family":"Ma","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shibo","family":"Jin","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8929-8127","authenticated-orcid":false,"given":"Lujuan","family":"Dang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2164-8968","authenticated-orcid":false,"given":"Liangjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-3818","authenticated-orcid":false,"given":"Badong","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3515874"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3620124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3607616"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref5","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref6","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00799"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.889"},{"key":"ref10","article-title":"Vision remember: Recovering visual information in efficient LVLM with vision feature resampling","author":"Feng","year":"2025","journal-title":"arXiv:2506.03928"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref12","first-page":"73986","article-title":"Efficient large multi-modal models via visual context compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"37","author":"Chen"},{"key":"ref13","article-title":"VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2501.13106"},{"key":"ref14","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv:2504.10479"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3302162"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3379900"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3546853"},{"key":"ref18","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref19","article-title":"SlowFast-LLaVA: A strong training-free baseline for video large language models","author":"Xu","year":"2024","journal-title":"arXiv:2407.15841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref21","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref23","first-page":"1","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. 11th Int. Conf. Learn. Represent","author":"Bolya"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02103"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00877"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref28","article-title":"LLaVA-PruMerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv:2403.15388"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01844"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34366"},{"key":"ref33","article-title":"LongVU: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024","journal-title":"arXiv:2410.17434"},{"key":"ref34","article-title":"FB-CLIP: Fine-grained zero-shot anomaly detection with foreground-background disentanglement","author":"Hu","year":"2026","journal-title":"arXiv:2603.19608"},{"key":"ref35","first-page":"5971","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process","author":"Lin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref38","article-title":"Frame-voyager: Learning to query frames for video large language models","author":"Yu","year":"2024","journal-title":"arXiv:2410.03226"},{"key":"ref39","article-title":"VITA: Towards open-source interactive omni multimodal LLM","author":"Fu","year":"2024","journal-title":"arXiv:2408.05211"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00315"},{"key":"ref41","article-title":"LLaVA-NeXT: A strong zero-shot video understanding model","volume-title":"LLaVA Blog","author":"Zhang","year":"2024"},{"key":"ref42","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv:2406.16852"},{"key":"ref43","article-title":"LLaVA-video: Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv:2410.02713"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref49","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref50","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.51"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11715982.pdf?arnumber=11715982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:11:55Z","timestamp":1791353515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11715982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3736818","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}