{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:17:56Z","timestamp":1782973076941,"version":"3.54.5"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01938","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20847-20856","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-Time Open-Vocabulary Object Detection"],"prefix":"10.1109","author":[{"given":"Yehao","family":"Lu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghe","family":"Weng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zekang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Polytechnic Institute, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Su","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangcong","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Lu","sequence":"additional","affiliation":[{"name":"ZTE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Llava-mole: Sparse mixture of lora experts for mitigating data conflicts in instruction finetuning mllms","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"5383","article-title":"Lifelong language pretraining with distribution-specialized experts","volume-title":"ICML","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref7","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2021","journal-title":"arXiv preprint"},{"issue":"120","key":"ref8","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3678087"},{"key":"ref10","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"ICLR","author":"Gu","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref12","article-title":"Demix layers: Disentangling domains for modular language modeling","author":"Gururangan","year":"2021","journal-title":"arXiv preprint"},{"issue":"3","key":"ref13","article-title":"Feedback-aware anomaly detection through logs for largescale software systems","volume":"19","author":"Han","year":"2021","journal-title":"ZTE Communications"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref18","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref20","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Weixin Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Moe-llava: Mixture of experts for large visionlanguage models","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","article-title":"Yolo-uniow: Efficient universal open-world object detection","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"issue":"1","key":"ref25","article-title":"Scene visual perception and ar navigation applications","volume":"21","author":"Ping","year":"2023","journal-title":"ZTE communications"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref27","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","volume-title":"ICCV","author":"Bryan","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref30","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref32","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Dino-x: A unified vision model for openworld object detection and understanding","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Grounding dino 1.5: Advance the\u201c edge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref36","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.758"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_14"},{"key":"ref40","article-title":"Ov-dino: Unified open-vocabulary detection with language-aware selective fusion","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref44","article-title":"Ovlw-detr: Open-vocabulary light-weighted detection transformer","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref46","article-title":"Solving token gradient conflict in mixture-of-experts for large vision-language model","volume-title":"ICLR","author":"Yang","year":"2025"},{"key":"ref47","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pretraining for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"NeurIPS"},{"key":"ref48","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pretraining for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref52","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref54","article-title":"Real-time transformer-based open-vocabulary detection with efficient fusion head","author":"Zhao","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444433.pdf?arnumber=11444433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:16Z","timestamp":1777529836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01938","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}