{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T01:29:22Z","timestamp":1778894962095,"version":"3.51.4"},"reference-count":132,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["62293542,U1903215,62022021"],"award-info":[{"award-number":["62293542,U1903215,62022021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01471","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"15325-15336","source":"Crossref","is-referenced-by-count":138,"title":["Universal Instance Perception as Object Discovery and Retrieval"],"prefix":"10.1109","author":[{"given":"Bin","family":"Yan","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology,China"}]},{"given":"Yi","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Jiannan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology,China"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Zehuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology,China"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref56","author":"liang","year":"2021","journal-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref55","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","author":"li","year":"2021","journal-title":"NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_42"},{"key":"ref45","article-title":"Mdetrmodulated detection for end-to-end multi-modal understanding","author":"kamath","year":"2021","journal-title":"ICCV"},{"key":"ref48","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"2018","journal-title":"ACCV"},{"key":"ref47","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","author":"ke","year":"2021","journal-title":"NeurIPS"},{"key":"ref42","article-title":"GOT-10k: A large high-diversity benchmark for generic object tracking in the wild","author":"huang","year":"2019","journal-title":"TPAMI"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref43","article-title":"Video instance segmentation using inter-frame communication transformers","author":"hwang","year":"2021","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref8","article-title":"Cascade R-CNN: high quality object detection and instance segmentation","author":"cai","year":"2019","journal-title":"TPAMI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref9","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref40","article-title":"Learning to compose and reason with language tree structures for visual grounding","author":"hong","year":"2019","journal-title":"TPAMI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref33","author":"ge","year":"2021","journal-title":"Yolox Exceeding yolo series in 2021"},{"key":"ref32","article-title":"Large-scale adversarial training for vision-and-language representation learning","author":"gan","year":"2020","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Vita: Video instance segmentation via object token association","author":"heo","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref26","article-title":"Progressive multimodal interaction network for referring video object segmentation","author":"ding","year":"2021","journal-title":"The 2nd large-scale video object segmentation challenge"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"ref22","article-title":"TAO: A large-scale bench-mark for tracking any object","author":"dave","year":"2020","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref13","article-title":"A unified sequence interface for vision tasks","author":"chen","year":"2022","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref15","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"ECCV"},{"key":"ref128","article-title":"Tracking objects as points","author":"zhou","year":"2020","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref99","article-title":"SOLOv2: Dynamic and fast instance segmentation","author":"wang","year":"2020","journal-title":"NeurIPS"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref125","article-title":"Byte-track: Multi-object tracking by associating every detection box","author":"zhang","year":"2022","journal-title":"ECCV"},{"key":"ref17","article-title":"Xmem: Long-term video object segmentation with an atkinson-shiffrin memory model","author":"cheng","year":"2022","journal-title":"ECCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref18","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","author":"cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref92","article-title":"Boxlnst: High-performance instance segmentation with box annotations","author":"tian","year":"2021","journal-title":"CVPR"},{"key":"ref95","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"wang","year":"2022","journal-title":"ICML"},{"key":"ref131","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"ICLRE"},{"key":"ref94","article-title":"Siam R-CNN: Visual tracking by redetection","author":"voigtlaender","year":"2020","journal-title":"CVPR"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01630"},{"key":"ref130","article-title":"SeqTR: A simple yet universal network for visual grounding","author":"zhu","year":"2022","journal-title":"ECCV"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref86","article-title":"UR-VOS: Unified referring video object segmentation network with a large-scale benchmark","author":"seo","year":"2020","journal-title":"ECCV"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref87","author":"shao","year":"2021","journal-title":"INTERN A new learning paradigm towards general vision"},{"key":"ref82","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2015","journal-title":"CVPR"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref84","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref83","author":"reed","year":"2022","journal-title":"A generalist agent"},{"key":"ref80","author":"pont-tuset","year":"2017","journal-title":"The 2017 davis challenge on video object segmentation"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref108","article-title":"Segment as points for efficient and effective online multi-object tracking and segmentation","author":"xu","year":"2021","journal-title":"TPAMI"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref107","author":"xu","year":"2018","journal-title":"Youtube-vos A large-scale video object segmentation benchmark"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref74","author":"milan","year":"2016","journal-title":"Mot16 A benchmark for multi-object tracking"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref76","article-title":"Trackingnet: A large-scale dataset and benchmark for object tracking in the wild","author":"muller","year":"2018","journal-title":"ECCV"},{"key":"ref103","article-title":"Seqformer: Sequential transformer for video instance segmentation","author":"wu","year":"2021","journal-title":"ECCV"},{"key":"ref2","article-title":"Pathways: Asynchronous distributed dataflow for ML","author":"barham","year":"2022","journal-title":"PMLS"},{"key":"ref1","article-title":"STEm-Seg: Spatiotemporal embeddings for instance segmentation in videos","author":"athar","year":"2020","journal-title":"ECCV"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref68","author":"lu","year":"2022","journal-title":"Unified-io A unified model for vision language and multi-modal tasks"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref67","author":"loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref118","article-title":"Joint feature learning and relation modeling for tracking: A one-stream framework","author":"ye","year":"2022","journal-title":"ECCV"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3079993","article-title":"Cross-modal progressive comprehension for referring segmentation","author":"liu","year":"2021","journal-title":"TPAMI"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref114","article-title":"Improving one-stage visual grounding by recursive sub-query construction","author":"yang","year":"2020","journal-title":"ECCV"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00679"},{"key":"ref123","author":"zhang","year":"2022","journal-title":"Dino Detr with improved denoising anchor boxes for end-to-end object detection"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref61","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2023,6,17]]},"end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10205057.pdf?arnumber=10205057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T18:03:04Z","timestamp":1694455384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10205057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":132,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.01471","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}