{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:20:14Z","timestamp":1790803214887,"version":"4.1.0"},"reference-count":106,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225603"],"award-info":[{"award-number":["62225603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Hubei Science and Technology Major Project","award":["2024BAA007"],"award-info":[{"award-number":["2024BAA007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3719473","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:06:32Z","timestamp":1786129592000},"page":"8558-8573","source":"Crossref","is-referenced-by-count":3,"title":["Extending Large Vision\u2013Language Model for Diverse Interactive Tasks in Autonomous Driving"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1309-5465","authenticated-orcid":false,"given":"Zongchuang","family":"Zhao","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Fu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3035-1373","authenticated-orcid":false,"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4752-6118","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5022-8172","authenticated-orcid":false,"given":"Dingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaomi EV.","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi EV.","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, 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":"10.1109\/cvpr52733.2024.02283"},{"key":"ref3","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref4","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":"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":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref7","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref9","article-title":"InternLM2 technical report","volume-title":"arXiv:2403.17297","author":"Cai","year":"2024"},{"key":"ref10","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref11","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01297"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"},{"key":"ref15","first-page":"22442","article-title":"OmniDrive: A holistic LLM-agent framework for autonomous driving with 3D perception, reasoning and planning","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit.","author":"Wang"},{"key":"ref16","first-page":"4698","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","volume-title":"Proc. Annu. Conf. Robot Learn.","author":"Tian"},{"key":"ref17","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv:2410.22313"},{"key":"ref18","article-title":"WiseAD: Knowledge augmented end-to-end autonomous driving with vision-language model","author":"Zhang","year":"2024","journal-title":"arXiv:2412.09951"},{"key":"ref19","article-title":"DriveMM: All-in-one large multimodal model for autonomous driving","author":"Huang","year":"2024","journal-title":"arXiv:2412.07689"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref27","article-title":"Language-image models with 3D understanding","author":"Cho","year":"2024","journal-title":"arXiv:2405.03685"},{"key":"ref28","article-title":"EMMA: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv:2410.23262"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00734"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref32","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref33","volume-title":"InternVL2: Better Than the Best\u2014Expanding Performance Boundaries of Open-Source Multimodal Models With the Progressive Scaling Strategy","year":"2024"},{"key":"ref34","first-page":"22604","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"Proc. Intl. Conf. Learn. Represent.","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref36","article-title":"HiLM-D: Towards high-resolution understanding in multimodal large language models for autonomous driving","author":"Ding","year":"2023","journal-title":"arXiv:2309.05186"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611485"},{"key":"ref40","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref41","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref42","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref45","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532688"},{"key":"ref49","first-page":"878","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Intl. Conf. Learn. Represent.","author":"Shazeer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref51","article-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","volume-title":"Proc. Conf. Lang. Model.","author":"Zhang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531452"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2235"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3523675"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_21"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00621"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00880"},{"key":"ref63","article-title":"Alpamayo-r1: Bridging reasoning and action prediction for generalizable autonomous driving in the long tail","author":"Wang","year":"2025","journal-title":"arXiv:2511.00088"},{"key":"ref64","article-title":"GPT-driver: Learning to drive with GPT","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Mao"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02568"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32524"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33067"},{"key":"ref69","article-title":"LaVida drive: Vision-text interaction VLM for autonomous driving with token selection, recovery and enhancement","author":"Jiao","year":"2024","journal-title":"arXiv:2411.12980"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01129"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00095-w"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3430473"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3526056"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2955239"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3333225"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3274479"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245337"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326394"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3201469"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref85","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref90","first-page":"146","article-title":"OPEN: Object-wise position embedding for multi-view 3D object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Hou"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref93","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref95","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref97","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref99","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref102","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref105","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv:2301.00493"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2557"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11644856.pdf?arnumber=11644856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:05:49Z","timestamp":1786993549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11644856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3719473","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}