{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:23:29Z","timestamp":1784748209830,"version":"3.55.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888334","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":12,"title":["Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection"],"prefix":"10.1109","author":[{"given":"Haoxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingdong","family":"He","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlong","family":"Peng","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingmin","family":"Chi","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref2","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu"},{"key":"ref6","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref10","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref12","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kuo"},{"key":"ref13","article-title":"Dst-det: Simple dynamic self-training for open-vocabulary object detection","author":"Xu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref17","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pretraining for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref19","article-title":"An open and comprehensive pipeline for unified object grounding and detection","author":"Zhao","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref21","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref22","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024"},{"key":"ref23","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref24","article-title":"Mambavision: A hybrid mambatransformer vision backbone","author":"Hatamizadeh","year":"2024"},{"key":"ref25","article-title":"Samba: Simple hybrid state space models for efficient unlimited context language modeling","author":"Ren","year":"2024"},{"key":"ref26","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024"},{"key":"ref27","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.633"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref30","article-title":"Ultralytics yolov8","author":"Jocher","year":"2023"},{"key":"ref31","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"The International Conference on Learning Representations (ICLR)","author":"Gu"},{"key":"ref32","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning.","author":"Li","year":"2022"},{"key":"ref34","article-title":"MMYOLO: OpenMMLab YOLO series toolbox and benchmark","author":"Contributors","year":"2022"},{"key":"ref35","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888334.pdf?arnumber=10888334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:52Z","timestamp":1774416352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888334","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}