{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:03:08Z","timestamp":1772056988465,"version":"3.50.1"},"reference-count":86,"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":"publisher","award":["62325101"],"award-info":[{"award-number":["62325101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62405014"],"award-info":[{"award-number":["62405014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42372175"],"award-info":[{"award-number":["42372175"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhongguancun Academy","doi-asserted-by":"publisher","award":["02012503"],"award-info":[{"award-number":["02012503"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2025ZD1401501"],"award-info":[{"award-number":["2025ZD1401501"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3663039","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:09:43Z","timestamp":1771276183000},"page":"2167-2181","source":"Crossref","is-referenced-by-count":0,"title":["MTRAG: Multi-Target Referring and Grounding via Hybrid Semantic-Spatial Integration"],"prefix":"10.1109","volume":"35","author":[{"given":"Yili","family":"Ren","sequence":"first","affiliation":[{"name":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3201-0832","authenticated-orcid":false,"given":"Jinyang","family":"Du","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianxiao","family":"Su","sequence":"additional","affiliation":[{"name":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2871-8922","authenticated-orcid":false,"given":"Yue","family":"Deng","sequence":"additional","affiliation":[{"name":"Zhongguancun Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0504-2555","authenticated-orcid":false,"given":"Hongjue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Grounding multimodal large language models to the world","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref2","first-page":"1","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"You"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147385"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926266"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334099"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3394260"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref10","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref11","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref17","article-title":"SInViG: A self-evolving interactive visual agent for human\u2013robot interaction","author":"Xu","year":"2024","journal-title":"arXiv:2402.11792"},{"key":"ref18","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref19","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01313"},{"key":"ref22","article-title":"Instruct2Act: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023","journal-title":"arXiv:2305.11176"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref27","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"ref32","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01238"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref39","article-title":"Vision transformers need registers","author":"Darcet","year":"2023","journal-title":"arXiv:2309.16588"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2235"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref45","article-title":"ClawMachine: Fetching visual tokens as an entity for referring and grounding","author":"Ma","year":"2024","journal-title":"arXiv:2406.11327"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref47","article-title":"Sa2VA: Marrying SAM2 with LLaVA for dense grounded understanding of images and videos","author":"Yuan","year":"2025","journal-title":"arXiv:2501.04001"},{"key":"ref48","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":"ref49","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref50","article-title":"Pixel-SAIL: Single transformer for pixel-grounded understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2504.10465"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref53","article-title":"Draw-and-understand: Leveraging visual prompts to enable MLLMs to comprehend what you want","author":"Lin","year":"2024","journal-title":"arXiv:2403.20271"},{"key":"ref54","article-title":"Describe anything: Detailed localized image and video captioning","author":"Lian","year":"2025","journal-title":"arXiv:2504.16072"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01767"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref57","first-page":"9725","article-title":"Instruction-guided multi-granularity segmentation and captioning with large multimodal model","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Zhou"},{"key":"ref58","article-title":"UFO: A unified approach to fine-grained visual perception via open-ended language interface","author":"Tang","year":"2025","journal-title":"arXiv:2503.01342"},{"key":"ref59","article-title":"HyperSeg: Towards universal visual segmentation with large language model","author":"Wei","year":"2024","journal-title":"arXiv:2411.17606"},{"key":"ref60","article-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv:2404.07973"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01273"},{"key":"ref62","article-title":"Perceive anything: Recognize, explain, caption, and segment anything in images and videos","author":"Lin","year":"2025","journal-title":"arXiv:2506.05302"},{"key":"ref63","first-page":"57207","article-title":"Vitron: A unified pixel-level vision LLM for understanding, generating, segmenting, editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fei"},{"key":"ref64","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref68","first-page":"43041","article-title":"RIO: A benchmark for reasoning intention-oriented objects in open environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qu"},{"key":"ref69","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref72","first-page":"3","article-title":"LoRA: low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref73","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref74","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref77","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref84","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref85","article-title":"MM-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv:2308.02490"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11397268.pdf?arnumber=11397268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:59:15Z","timestamp":1772053155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3663039","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}