{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:21:12Z","timestamp":1783174872802,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306165"],"award-info":[{"award-number":["62306165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720250031"],"award-info":[{"award-number":["20720250031"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113896","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:08:38Z","timestamp":1777561718000},"page":"113896","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Instructing visual feature modeling with semantic guidance for 3D visual grounding"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6153-5004","authenticated-orcid":false,"given":"Yachao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiran","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangyong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113896_b1","series-title":"ECCV","first-page":"202","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","author":"Chen","year":"2020"},{"key":"10.1016\/j.patcog.2026.113896_b2","first-page":"7359","article-title":"Cross-modal match for language conditioned 3D object grounding","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b3","series-title":"LidaRefer: Outdoor 3D visual grounding for autonomous driving with transformers","author":"Baek","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b4","series-title":"Humanoids","first-page":"692","article-title":"Real-time navigation in 3D environments based on depth camera data","author":"Maier","year":"2012"},{"key":"10.1016\/j.patcog.2026.113896_b5","series-title":"Deep learning for embodied vision navigation: A survey","author":"Zhu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b6","series-title":"CVPR","first-page":"6629","article-title":"Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2026.113896_b7","series-title":"CVPR","first-page":"9068","article-title":"Gibson env: Real-world perception for embodied agents","author":"Xia","year":"2018"},{"issue":"3","key":"10.1016\/j.patcog.2026.113896_b8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2480741.2480751","article-title":"3D virtual worlds and the metaverse: Current status and future possibilities","volume":"45","author":"Dionisio","year":"2013","journal-title":"CSUR"},{"key":"10.1016\/j.patcog.2026.113896_b9","series-title":"Eurographics 2013-STAR","article-title":"A survey of interaction techniques for interactive 3D environments","author":"Jankowski","year":"2013"},{"issue":"4","key":"10.1016\/j.patcog.2026.113896_b10","doi-asserted-by":"crossref","first-page":"2090","DOI":"10.1080\/10494820.2021.1874999","article-title":"Trends in VR\/AR technology-supporting language learning from 2008 to 2019: A research perspective","volume":"31","author":"Qiu","year":"2023","journal-title":"Interact. Learn. Env."},{"issue":"4","key":"10.1016\/j.patcog.2026.113896_b11","first-page":"539","article-title":"Research progress on virtual reality (VR) and augmented reality (AR) in tourism and hospitality: A critical review of publications from 2000 to 2018","volume":"10","author":"Wei","year":"2019","journal-title":"J HOSP TOUR TECHNOL"},{"key":"10.1016\/j.patcog.2026.113896_b12","series-title":"ICACT","first-page":"401","article-title":"3D interaction in augmented reality with stereo-vision technique","author":"Lee","year":"2013"},{"key":"10.1016\/j.patcog.2026.113896_b13","first-page":"1","article-title":"Pseudo-EV: Enhancing 3D visual grounding with pseudo embodied viewpoint","author":"Geng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113896_b14","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"7694","article-title":"Llm-grounder: Open-vocabulary 3d visual grounding with large language model as an agent","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b15","series-title":"Vlm-grounder: A vlm agent for zero-shot 3d visual grounding","author":"Xu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b16","doi-asserted-by":"crossref","unstructured":"J. Lin, S. Bian, Y. Zhu, W. Tana, Y. Zhang, Y. Xie, Y. Qu, SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding, in: ACM International Conference on Multimedia, 2025, pp. 1\u201310.","DOI":"10.1145\/3746027.3754985"},{"key":"10.1016\/j.patcog.2026.113896_b17","series-title":"ECCV","first-page":"422","article-title":"Referit3d: Neural listeners for fine-grained 3d object identification in real-world scenes","author":"Achlioptas","year":"2020"},{"key":"10.1016\/j.patcog.2026.113896_b18","series-title":"AAAI","first-page":"1610","article-title":"Text-guided graph neural networks for referring 3d instance segmentation","volume":"35","author":"Huang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b19","series-title":"ICCV","first-page":"1791","article-title":"Instancerefer: Cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring","author":"Yuan","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b20","series-title":"ICCV","first-page":"1856","article-title":"Sat: 2d semantics assisted training for 3d visual grounding","author":"Yang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b21","series-title":"ICCV","first-page":"3722","article-title":"Free-form description guided 3d visual graph network for object grounding in point cloud","author":"Feng","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b22","series-title":"CVPR","first-page":"19231","article-title":"Eda: Explicit text-decoupling and dense alignment for 3d visual grounding","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113896_b23","series-title":"European Conference on Computer Vision","first-page":"381","article-title":"Multi-branch collaborative learning network for 3d visual grounding","author":"Qian","year":"2024"},{"issue":"10","key":"10.1016\/j.patcog.2026.113896_b24","doi-asserted-by":"crossref","first-page":"10399","DOI":"10.1109\/TCSVT.2024.3407785","article-title":"Visual grounding with dual knowledge distillation","volume":"34","author":"Wu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113896_b25","article-title":"A masked reference token supervision based iterative visual-language framework for robust visual grounding","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"9","key":"10.1016\/j.patcog.2026.113896_b26","doi-asserted-by":"crossref","first-page":"3469","DOI":"10.1109\/TCSVT.2020.3039522","article-title":"Language-guided navigation via cross-modal grounding and alternate adversarial learning","volume":"31","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113896_b27","series-title":"ICCV","first-page":"2928","article-title":"3DVG-transformer: Relation modeling for visual grounding on point clouds","author":"Zhao","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b28","series-title":"CVPR","first-page":"16464","article-title":"3Djcg: A unified framework for joint dense captioning and visual grounding on 3d point clouds","author":"Cai","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b29","first-page":"7296","article-title":"Vision-language pre-training with object contrastive learning for 3D scene understanding","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b30","series-title":"CVPR","first-page":"16454","article-title":"3D-sps: Single-stage 3d visual grounding via referred point progressive selection","author":"Luo","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b31","series-title":"ECCV","first-page":"417","article-title":"Bottom up top down detection transformers for language grounding in images and point clouds","author":"Jain","year":"2022"},{"issue":"9","key":"10.1016\/j.patcog.2026.113896_b32","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patcog.2026.113896_b33","series-title":"A survey of prompt engineering methods in large language models for different nlp tasks","author":"Vatsal","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b34","first-page":"16158","article-title":"Why do pretrained language models help in downstream tasks? an analysis of head and prompt tuning","volume":"34","author":"Wei","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113896_b35","series-title":"CVPR","first-page":"5206","article-title":"Prompt distribution learning","author":"Lu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b36","series-title":"EMNLP-IJCNLP","first-page":"2463","article-title":"Language models as knowledge bases?","author":"Petroni","year":"2019"},{"key":"10.1016\/j.patcog.2026.113896_b37","article-title":"Enhancing visual grounding in vision-language pre-training with position-guided text prompts","author":"Wang","year":"2023","journal-title":"TPAMI"},{"key":"10.1016\/j.patcog.2026.113896_b38","series-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b39","article-title":"GPT understands, too","author":"Liu","year":"2023","journal-title":"AI Open"},{"key":"10.1016\/j.patcog.2026.113896_b40","series-title":"CVPR","first-page":"14084","article-title":"Learning to prompt for open-vocabulary object detection with vision-language model","author":"Du","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b41","series-title":"ECCV","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b42","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b43","series-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113896_b44","series-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.patcog.2026.113896_b45","series-title":"NeurIPS","first-page":"1","article-title":"Language conditioned spatial relation reasoning for 3D object grounding","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113896_b46","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113896_b47","series-title":"Empowering 3D visual grounding with reasoning capabilities","author":"Zhu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113896_b48","series-title":"CVPR","first-page":"2432","article-title":"ScanNet: Richly-annotated 3D reconstructions of indoor scenes","author":"Dai","year":"2017"},{"key":"10.1016\/j.patcog.2026.113896_b49","unstructured":"J. Roh, K. Desingh, A. Farhadi, D. Fox, LanguageRefer: Spatial-Language Model for 3D Visual Grounding, in: Proceedings of the Conference on Robot Learning, 2021."},{"key":"10.1016\/j.patcog.2026.113896_b50","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008617?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008617?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:52:23Z","timestamp":1783173143000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":50,"alternative-id":["S0031320326008617"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113896","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Instructing visual feature modeling with semantic guidance for 3D visual grounding","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113896","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113896"}}